Image processing for detection of Cataract, Retinopathy of ...€¦ · After image acquisition, the rst image processing stage is the image pre-processing. The general processes such

Image Processing for Detection of

Cataract, Retinopathy Of

Prematurity and Glaucoma

Arezoo Motamed Ektesabi

Faculty of Science, Engineering and Technology

Swinburne University of Technology

A thesis submitted for the degree of

Doctor of Philosophy

2015

i

Declaration

This thesis is the result of my own work and to the best of my knowl-

edge, includes nothing, which is the outcome of work done in collabo-

ration except where specifically indicated in the text. It has not been

previously submitted, in part or whole, to any university of institution

for any degree, diploma, or other qualification.

Signature:

Arezoo Motamed Ektesabi

2015

I would like to dedicate this thesis to my loving parents,

Mehran Motamed Ektesabi & Sharareh Soufi Siavash

and my brother, Arman Motamed Ektesabi

In memories of Shirin Salimi Pirkouhi, my grandmother,

who was always inspiring me to continue my studies.

Acknowledgements

I would forever be grateful for all those who guided me and encouraged

me to challenge myself, never give up, advance and succeed in life.

A special thanks goes to my principal coordinating supervisor, Profes-

sor Ajay Kapoor, for his mentoring and support throughout my candi-

dature. It was with his continuous guidance, commentary, suggestions

and motivation that the completion if this thesis became possible.

I hereby would also like to acknowledge Associate Professor Richard

Manasseh, my coordinating supervisor, who at many times inspired me

and directed me to clarify my thought processes and aided me in my

decisions.

Throughout my candidature I received many invaluable supports from

many individuals and many friendships were formed. In particular I

would like to thank Dr Michelle Dunn who introduced me to image

processing.

I would like to thank my mother, Sharareh Soufi Siavash, who taught

me how to write and read prior to attending school; stood beside me

throughout my studies; and who showered me with love and encouraged

me to grow.

Many thanks to my father, Mehran Motamed Ektesabi, who introduced

me to the field of engineering from an early age; who was always there

throughout all the hurdles of life and was there when I needed an

advice; who believed in me, motivated and inspired me to progress and

achieve my best.

My parents, you are my first and long life teachers, my best friends

and mentors, I can never appreciate you enough for all that you have

done for me. Words cannot express how I feel about you. I just hope

you accept my sincere thanks and admiration.

I would also like to thank my younger brother, Arman Motamed Ek-

tesabi, who made me laugh when I was down and showed me his per-

spectives about the importance of life.

My grandparents, each in their own way, motivated me. I hope I have

done them proud, specially my grandmother, Shirin Salimi Pirkouhi,

who would have loved to see this day but unfortunately lost her battle

to cancer. Her dream was so that I could continue my studies and it is

with her well wishes that I have reached this far. May one day, I could

take part in research for early diagnosis of cancer.

My family and friends, my most valued treasures of life, I appreciate

each and every one of you for your positive encouragements and price-

less support. You have shown me how to live and taught me about

life’s vast opportunities. I am pleased to have had the opportunity to

know you and be part of your lives.

Publications

Book Chapter:

• A. Ektesabi, A. Kapoor, ”Fringe Noise Removal of Retinal Fun-

dus Images Using Trimming Regions”, Emerging Trends in Image

Processing, Computer Vision, and Pattern Recognition, Elsevier

Inc. Jan, 2015.

Conference Proceeding:

• A. Ektesabi, A. Kapoor, ”Exact Pupil and Iris Boundary Detec-

tion”, International Conference on Control, Instrumentation, and

Automation (ICCIA), Shiraz, vol. 2, pp. 1217-1221, 2011.

• A. Ektesabi, A. Kapoor, ”Complication Prevention of Posterior

Capsular Rupture using Image Processing Techniques”, Proceed-

ings of the World Congress on Engineering 2012 (WCE 2012),

vol. I, July 4 - 6, London, U.K., pp. 603-607, 2012.

• A. Ektesabi, A. Kapoor, ”Removal of Circular Edge Noise of Reti-

nal Fundus Images”, International Conference on Image Process-

ing, Computer Vision and Pattern Recognition (IPCV’14), Las

Vegas., 2014.

• A. Ektesabi, A. Kapoor, ”Optic Disk Localisation Using Con-

secutive Adaptive Thresholding Technique”, IEEE International

Conference on Image Processing (ICIP 2016), Arizona., 2016 -

Under Review.

Abstract

The field of ophthalmology is in need of more support as it is unable

to meet the need of the growing population. This thesis considers pro-

cedures which may be used as part of an assistive telemedical tool for

aiding ophthalmologists in diagnosing wide range of ophthalmological

disorders including Cataract, Retinopathy of Prematurity and Glau-

coma, which affect more than 60% of the population worldwide. Many

different image processing techniques have been analysed and in the

process some of the most favourable and advanced systems have been

selected for identifying some of the key features of the eye which are

commonly used by ophthalmologists for disease detection.

To address this aim and create a more suitable telemedical solution,

different stages of image processing is reconsidered and enhances in

the study. The stages include, image pre-processing, feature locali-

sation and feature extraction. The aim is to create simple, fast but

universal algorithms and procedures which could be implemented on

any captured data with any specifications.

After image acquisition, the first image processing stage is the image

pre-processing. The general processes such as the colour conversion

to the gray scale and green band selection, masking the region of in-

terest and preliminary filtering for sharpening the images are initially

implemented. However, to improve the results in further stages, new

procedures such as a trimming circle to reduce fringe noise and im-

age colour enhancements are also implemented. The final results show

significant improvements and more accurate findings in these cases.

The next stage is the feature localisation stage. Previous studies have

shown the main areas of interest in retinal images are vessels, Optic

Disk and the Macula. The features are extracted using the new pro-

posed algorithms. The results are promising and the localisation is

compatible with previously conducted studies. Moreover, in this stage,

another approach is suggested resulting in the Iris and Pupil localisa-

tion. The method may be used both for biometric purposes as well as

inter-operatively in surgeries such as those of cataract.

In the feature extraction stage, different methodologies are suggested

for detecting the centre of the Iris, Pupil, Optic Disk and Macula. The

radius and the area of these features are also calculated and compared.

For vessels an approach is suggested for detecting its end points. The

use of the information may result in detection of different diseases such

as Cataract, ROP and Glaucoma.

To further assist the ophthalmologists and medical practitioners an

approach is proposed which results in mapping of the retina, which

may then be used as an aiding tool for disease diagnosis, progression

and treatment.

Lastly, to reduce the error associated with each result, the light refrac-

tion within the eye is considered and the error calculated. The error

can then be taken under consideration while analysing each result.

The outcomes of the following study suggests a reliable yet cost-effective,

simple and fast approaches in which captured eye images may be anal-

ysed as part of an automatic assistive telemedical tool.

CONTENTS

Contents viii

List of Figures xiii

List of Tables xvii

Nomenclature xxi

1 Introduction 1

1.1 Telediagnosis in Ophthalmology . . . . . . . . . . . . . . . . . . . . 1

1.1.1 Diseases and Features of Interest . . . . . . . . . . . . . . . 3

1.2 Research Question . . . . . . . . . . . . . . . . . . . . . . . . . . . 4

1.3 Research Objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . 5

1.4 Proposed Methodology . . . . . . . . . . . . . . . . . . . . . . . . . 7

1.5 Contributions of the Research . . . . . . . . . . . . . . . . . . . . . 8

1.6 Thesis Structure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10

2 Most Predominant Eye Diseases 14

2.1 Structure of the Human Eye . . . . . . . . . . . . . . . . . . . . . . 14

2.1.1 Iris, Pupil and Sclera . . . . . . . . . . . . . . . . . . . . . . 16

2.1.2 Optic Disk, Macula and Ocular Vascularization . . . . . . . 17

2.2 Visual Impairment . . . . . . . . . . . . . . . . . . . . . . . . . . . 18

viii

CONTENTS

2.2.1 Risk Factors of Visual Impairment . . . . . . . . . . . . . . 19

2.2.2 Ophthalmological Diseases and Complications . . . . . . . . 21

2.3 Cataract . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22

2.3.1 Worldwide Effect of Cataract . . . . . . . . . . . . . . . . . 23

2.3.2 Risk Factors of Cataract . . . . . . . . . . . . . . . . . . . . 23

2.3.3 Classification and Screening of Cataract . . . . . . . . . . . 24

2.3.4 Treatment of Cataract . . . . . . . . . . . . . . . . . . . . . 25

2.3.4.1 Intracapsular Cataract Extraction (ICCE) . . . . . 25

2.3.4.2 Extracapsular Cataract Extraction (ECCE) . . . . 26

2.3.4.3 Manual Small Incision Cataract Surgery (MSICS) . 27

2.3.4.4 Phacoemulsification . . . . . . . . . . . . . . . . . 27

2.3.5 Monitoring Surgical Trainees . . . . . . . . . . . . . . . . . . 29

2.3.6 Importance of Iris and Pupil for Diagnosing Cataract . . . . 29

2.4 Retinopathy of Prematurity(ROP) . . . . . . . . . . . . . . . . . . 29

2.4.1 Worldwide Effect of ROP . . . . . . . . . . . . . . . . . . . 31

2.4.2 Risk Factors of ROP . . . . . . . . . . . . . . . . . . . . . . 31

2.4.3 Classification of ROP . . . . . . . . . . . . . . . . . . . . . . 32

2.4.4 Screening for ROP . . . . . . . . . . . . . . . . . . . . . . . 34

2.4.5 Treatment of ROP . . . . . . . . . . . . . . . . . . . . . . . 34

2.4.6 Importance of Retinal Vasculature for Diagnosing ROP . . . 35

2.5 Glaucoma . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35

2.5.1 Worldwide Effect of Glaucoma . . . . . . . . . . . . . . . . . 36

2.5.2 Pathogenesis of Glaucoma . . . . . . . . . . . . . . . . . . . 36

2.5.3 Risk Factors of Glaucoma . . . . . . . . . . . . . . . . . . . 37

2.5.4 Classification and Screening of Glaucoma . . . . . . . . . . . 37

2.5.5 Treatment of Glaucoma . . . . . . . . . . . . . . . . . . . . 38

2.5.6 Importance of Optic Disk and Macula for Diagnosing Glau-

coma . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38

2.6 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39

3 Image Processing in Ophthalmology 40

3.1 Ophthalmological Complications . . . . . . . . . . . . . . . . . . . . 40

3.1.1 Importance of Image Processing in Ophthalmology . . . . . 41

ix

CONTENTS

3.2 Image Processing Procedures . . . . . . . . . . . . . . . . . . . . . . 42

3.2.1 Image Processing in Biometrics . . . . . . . . . . . . . . . . 43

3.2.2 Image Processing in Ophthalmology . . . . . . . . . . . . . . 44

3.2.2.1 Iris and Pupil Localisation . . . . . . . . . . . . . . 44

3.2.2.2 Retinal Vessel Detection . . . . . . . . . . . . . . . 49

3.2.2.3 Optic Disck and Macula Localisation . . . . . . . . 52

3.3 Study Design Considerations . . . . . . . . . . . . . . . . . . . . . . 56

3.3.1 Examination versus Screening . . . . . . . . . . . . . . . . . 56

3.3.2 Cost Effectiveness . . . . . . . . . . . . . . . . . . . . . . . . 58

3.3.3 Image Quality . . . . . . . . . . . . . . . . . . . . . . . . . . 58

3.3.4 Accuracy . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59

3.3.5 Reliability . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59

3.3.6 Safety . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 60

3.4 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 60

4 Image Acquisition and Fundus Mapping 61

4.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 61

4.2 Image Acquisition . . . . . . . . . . . . . . . . . . . . . . . . . . . . 63

4.2.1 Filters . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 65

4.2.1.1 Hardware Filtering . . . . . . . . . . . . . . . . . . 65

4.2.1.2 Software Filtering . . . . . . . . . . . . . . . . . . 66

4.2.2 Image Databases . . . . . . . . . . . . . . . . . . . . . . . . 66

4.3 Fundus Mapping . . . . . . . . . . . . . . . . . . . . . . . . . . . . 68

4.3.1 New Proposed Technique for Fundus Mapping . . . . . . . . 71

4.3.2 Implementation and Discussion . . . . . . . . . . . . . . . . 75

4.4 Refraction Studies . . . . . . . . . . . . . . . . . . . . . . . . . . . 76

4.4.1 Light Refraction In Retina . . . . . . . . . . . . . . . . . . . 77

4.5 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 82

5 Image Pre-Processing 83

5.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 83

5.2 Image Manipulation . . . . . . . . . . . . . . . . . . . . . . . . . . 85

5.3 Masking . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 86

x

CONTENTS

5.3.1 Otsu Method . . . . . . . . . . . . . . . . . . . . . . . . . . 87

5.3.2 New Technique for Masking Using Thresholding . . . . . . . 88

5.4 Filtering . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 90

5.4.1 2D Fast Fourier Transform . . . . . . . . . . . . . . . . . . . 91

5.5 Sharpening the Retinal Image . . . . . . . . . . . . . . . . . . . . . 92

5.6 Trimming Regions . . . . . . . . . . . . . . . . . . . . . . . . . . . 95

5.6.1 Circular Trimming Region . . . . . . . . . . . . . . . . . . . 97

5.6.1.1 Implementation . . . . . . . . . . . . . . . . . . . . 100

5.6.1.2 Results and Discussion . . . . . . . . . . . . . . . . 101

5.6.2 Elliptical Trimming Region . . . . . . . . . . . . . . . . . . 103

5.6.2.1 Implementation . . . . . . . . . . . . . . . . . . . . 105

5.6.2.2 Results and Discussion . . . . . . . . . . . . . . . . 105

5.7 Contrast Enhancement . . . . . . . . . . . . . . . . . . . . . . . . . 107

5.7.1 New Necessary Step . . . . . . . . . . . . . . . . . . . . . . 109

5.7.1.1 Intensity Adjusted . . . . . . . . . . . . . . . . . . 109

5.7.1.2 Histogram Equalization . . . . . . . . . . . . . . . 110

5.7.1.3 Adaptive Histogram Equalization . . . . . . . . . . 111

5.7.2 Results and Discussion . . . . . . . . . . . . . . . . . . . . . 112

5.8 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 114

6 Iris and Pupil Localisation and Extraction 116

6.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 116

6.2 New Technique for Iris/Pupil Localisation . . . . . . . . . . . . . . 117

6.3 Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 120

6.4 Iris and Pupil Extraction . . . . . . . . . . . . . . . . . . . . . . . . 123

6.4.1 Center Decection . . . . . . . . . . . . . . . . . . . . . . . . 123

6.4.2 Area Calculation . . . . . . . . . . . . . . . . . . . . . . . . 124

6.5 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 125

7 Retinal Vessels Localisation and Extraction 127

7.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 127

7.2 Proposed Localisation Technique . . . . . . . . . . . . . . . . . . . 128

7.3 Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 131

xi

CONTENTS

7.4 Retinal Vasculature Extraction . . . . . . . . . . . . . . . . . . . . 151

7.4.1 Localisation of the End Point of Vessels . . . . . . . . . . . . 151

7.5 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 152

8 Optic Disk and Macula Localisation and Extraction 154

8.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 154

8.2 New Technique for Optic Disk Localisation . . . . . . . . . . . . . . 155

8.3 Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 158

8.4 Optic Disk Extraction . . . . . . . . . . . . . . . . . . . . . . . . . 162

8.4.1 Center of the Optic Disk . . . . . . . . . . . . . . . . . . . . 162

8.4.2 Area of the Optic Disk . . . . . . . . . . . . . . . . . . . . . 164

8.4.3 Cup to Disk Ratio . . . . . . . . . . . . . . . . . . . . . . . 164

8.5 Macula Localisation - Proposed Technique . . . . . . . . . . . . . . 165

8.6 Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 170

8.7 Macula Extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . 172

8.8 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 172

9 Conclusions 174

9.1 Overall Research Program . . . . . . . . . . . . . . . . . . . . . . . 174

9.2 Research Findings, Perceived Contributions . . . . . . . . . . . . . 175

9.3 Proposals for Future Research . . . . . . . . . . . . . . . . . . . . 178

References 183

Appendix A 200

Appendix B 202

Appendix C 205

Appendix D 207

Appendix E 210

xii

LIST OF FIGURES

1.1 Stages undertaken in Image Processing . . . . . . . . . . . . . . . . 5

1.2 Thesis Outline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13

2.1 Chapter Two Outline . . . . . . . . . . . . . . . . . . . . . . . . . . 14

2.2 Anatomical structure of the eye . . . . . . . . . . . . . . . . . . . . 16

2.3 Regions of the eye - pupil, iris and sclera [9] . . . . . . . . . . . . . 17

2.4 Retinal fundus image where the location of the OD, macula and the

vessles are indicated. . . . . . . . . . . . . . . . . . . . . . . . . . . 18

2.5 Global causes of blindness and the percentage of affected popula-

tion [1] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21

2.6 Template used in the Wisconsin Cataract Grading System for lo-

cating the Cataract in the right eyes. . . . . . . . . . . . . . . . . . 24

2.7 Intracapsular Cataract Extraction [48] . . . . . . . . . . . . . . . . 26

2.8 Extracapsular Cataract Extraction [50] . . . . . . . . . . . . . . . . 26

2.9 Manual Small Incision Cataract surgery [54] . . . . . . . . . . . . . 27

2.10 Phacoemulsification surgery [61] . . . . . . . . . . . . . . . . . . . . 28

2.11 Illustration of differences between normal and abnormal retinal blood-

vessel development in the child with ROP. . . . . . . . . . . . . . . 30

2.12 Classification of ROP for the left eyes [17] . . . . . . . . . . . . . . 32

3.1 Chapter Three Outline . . . . . . . . . . . . . . . . . . . . . . . . . 40

xiii

LIST OF FIGURES

3.2 Stages undertaken in Image Processing . . . . . . . . . . . . . . . . 42

3.3 Suggested Image Processing stages. . . . . . . . . . . . . . . . . . . 57

4.1 Chapter Four Outline of Image Processing Stages . . . . . . . . . . 61

4.2 Image capturing set up . . . . . . . . . . . . . . . . . . . . . . . . . 64

4.3 Capturing device, (1) Camera, (2) Lighting, (3) Hardware light filter 65

4.4 The difference between the view angle of normal angle, narrow angle

and wide angle fundus cameras. . . . . . . . . . . . . . . . . . . . . 69

4.5 Importance of fundus mapping . . . . . . . . . . . . . . . . . . . . . 70

4.6 Geometric representation of the proposed method for merging mul-

tiple retinal images. Radius of the Curve (R), Central Angle of the

Curve (∆), Cord Length (C), Tangent Length (T ), Middle Coordi-

nate (M), External Distance (E) and the Middle (PM), Left (PL)

and Right (PR) points can be viewed in the image. . . . . . . . . . 71

4.7 Approximation of retinal curvature using the Middle Coordinate . . 74

4.8 Average light refraction indices for different regions of an eye. . . . 77

4.9 Comparison of incident ray and refractive ray - 180 degrees . . . . . 78

4.10 Comparison of incident ray and refractive ray - 90 degrees . . . . . 79

4.11 Example of bending of the refractive ray in the eye . . . . . . . . . 79

5.1 Chapter Five Outline of Image Processing Stages . . . . . . . . . . 83

5.2 Colour band separation of a coloured image with respected histograms 85

5.3 Colour component separation of RGB image in horizontal direction 86

5.4 Example of a possible mask for the sampled image . . . . . . . . . . 87

5.5 Histogram used to determine a threshold for masking the ROI . . . 89

5.6 Implementing 2D FFT on a retinal image . . . . . . . . . . . . . . . 92

5.7 Used Kernels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 93

5.8 Two examples of retinal fundus images. If observed closely, a bright

fringe can be seen at the left hand corner of the image (b) which

may result in inaccurate OD detection. The bright fringe cannot be

seen in the image (a). . . . . . . . . . . . . . . . . . . . . . . . . . . 95

xiv

LIST OF FIGURES

5.9 Example of results obtained for plotting a trimming region. The

green (+) signs indicate the preliminary estimated points. The

orange (+) signs indicate the calculated points, including the es-

timated center. The yellow circle is the trimming region which has

been plotted using the information. . . . . . . . . . . . . . . . . . . 101

5.10 Examples of retinal images using different capturing devices. . . . . 103

5.11 (a) Inaccurate circular trimming circle (yellow) for an elliptical

shaped captured fundus image. (b) Trimmed image. . . . . . . . . . 103

5.12 (a) Accurate circular trimming circle (yellow) for an elliptical shaped

captured fundus image using long axis as the radius. (b) Trimmed

image. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 104

5.13 Example of the effect of Intensity Adjustment . . . . . . . . . . . . 109

5.14 Example of the effect of Histogram Equalization . . . . . . . . . . . 110

5.15 Example of the effect of Contrast Limited Adaptive Histogram Equal-

ization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 111

6.1 Chapter Six Outline of Image Processing Stages . . . . . . . . . . . 116

6.2 Proposed steps for Iris and Pupil localisation. . . . . . . . . . . . . 118

6.3 Example of the possible inaccurate results obtained from two dif-

ferent Iris localisation techniques. Results from approach one and

two are outlined in green and red respectively. . . . . . . . . . . . . 119

6.4 Original image used for localisation of Iris and Pupil . . . . . . . . 120

6.5 Result obtained when localising the iris and pupil outer boundaries

using the proposed new algorithm . . . . . . . . . . . . . . . . . . . 120

7.1 Chapter Seven Outline of Image Processing Stages . . . . . . . . . . 127

7.2 Proposed steps for retinal vessel localisation. . . . . . . . . . . . . . 128

7.3 Some of the possible vessels end point using template matching . . 152

8.1 Chapter Eight Outline of Image Processing Stages . . . . . . . . . . 154

8.2 Proposed steps for Optic Disk localisation. . . . . . . . . . . . . . . 155

8.3 The gradient plot histogram used to set the threshold for the OD

localisation. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 156

xv

LIST OF FIGURES

8.4 Example gradient plot histograms and set thresholds for OD local-

isation for different images. . . . . . . . . . . . . . . . . . . . . . . . 157

8.5 Some possible templates for determining vessels intersection . . . . 163

8.6 Center localisation of the OD, method 1 is represented as a blue

(+) sign and method 2 as red (+) sign . . . . . . . . . . . . . . . . 163

8.7 Detection of the OC (green) and OD (red) . . . . . . . . . . . . . . 164

8.8 Different positions of macula in retinal images, in images (a) and

(d) macula is located in the center while in images (b) and (c) no

macula is present. The macula has been manually defined and can

be viewed in the images. . . . . . . . . . . . . . . . . . . . . . . . . 165

8.9 Proposed steps for Macula localisation. . . . . . . . . . . . . . . . . 166

8.10 The retinal image has been deperated into blocks. . . . . . . . . . . 167

8.11 Neural network model determining the OD block. . . . . . . . . . . 168

8.12 Complementary image. (a) Original Image, (b) Complement Image. 170

8.13 Localisation of Macula using the proposed technique. . . . . . . . . 170

9.1 Chapter Nine Outline . . . . . . . . . . . . . . . . . . . . . . . . . . 174

xvi

LIST OF TABLES

2.1 World statistics on visual impairment . . . . . . . . . . . . . . . . . 19

4.1 Refractive Index of the light passing through different regions of the

eye. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 78

4.2 ANOVA of the incident and refractive rays for 0-90◦ range . . . . . 80

5.1 Comparison of the masks formed by Otsu method and the suggested

new Thresholding method. . . . . . . . . . . . . . . . . . . . . . . . 90

5.2 Sharpening the retinal image using 2D FFT . . . . . . . . . . . . . 94

5.3 Comparison table of the proposed trimming circle with those sug-

gested previously in literature . . . . . . . . . . . . . . . . . . . . . 99

5.4 OD localisation using trimming circle . . . . . . . . . . . . . . . . . 102

5.5 Proposed Circular and Elliptical Trimming Regions . . . . . . . . . 104

5.6 Implementation of both circular and elliptical trimming regions for

circular and elliptically shaped retinal fundus images . . . . . . . . 105

5.7 OD Detection for Circular and Elliptical Trimming Region . . . . . 106

5.8 OD localization for contrast enhanced images. . . . . . . . . . . . . 113

6.1 Example of Iris Localisation Results . . . . . . . . . . . . . . . . . . 121

6.2 Iris localisation for different images. . . . . . . . . . . . . . . . . . . 122

7.1 Modeling and implementation of different filters for vessel detection 131

xvii

LIST OF TABLES



7.2 Combining results of different filters . . . . . . . . . . . . . . . . . 134

7.3 Vessel localisation for Image 1 . . . . . . . . . . . . . . . . . . . . . 136





8.1 Step by step results for OD detection, applying the proposed con-

secutive adaptive thresholding method. . . . . . . . . . . . . . . . . 159

8.2 OD localisation for different images. . . . . . . . . . . . . . . . . . . 161

8.3 Macula localisation for different images. For cases where the Macula

cannot be seen the process is stopped, such as the case for Image 6. 171

1 Angle of light as it enters the eye (Incident Ray), passes through

different interfaces within the eye and reaches the back of the eye

(Refractive Ray). . . . . . . . . . . . . . . . . . . . . . . . . . . . . 200

2 Gray Scaled and colour component separation of coloured images . 202

3 Masks created for different images using Thresholding technique . . 205

4 2D FFT filtered images. . . . . . . . . . . . . . . . . . . . . . . . . 207

5 Sharpening the retinal images using 2D FFT filtered images. . . . . 210

xviii

NOMENCLATURE

A Area of a Circle

AC Anterior Chamber

AHE Adaptive Histogram Equalization

ALT Adaptive Local Thresholding

AMD Age-related Macular Degeneration

ANOV A Analysis of variance

BMF Binary Matched Filter

C Cord Length

CHT Circular Hough Transform

CLAHE Contrast Limited Adaptive Histogram Equalization

CNS Central Nervous System

CSLT Confocal Scanning Laser Tomography

CT Curvelet Transform

∆ Central Angle of the Curve in degrees

xix

Nomenclature

df Degrees of Freedom

DH Desired Histogram

E External Distance

F − test Fisher’s test

FDOG First Order Derivative Gaussian

FFT Fast Fourier Transform

FLDA Fisher Linear Discriminant Analysis

FOV Field Of View

GMF Gaussian Matched Filter

R Histogram Equalization

HRT Heidelberg Retinal Tomograph

HT Hough Transforme

IFFT Inverse Fast Fourier Transform

IUWT Isotropic Undecimated Wavelet Transform

KMF Kirsch Template Matched Filter

L Curve Length Distance between PI to the V ertex

M Middle Coordinate

MF Matched Filter

MS Mean Sqaures

NN Neural Networks

OC Optic Cup

OCT Optical Coherence Tomography

xx

Nomenclature

OD Optic Disk

ONH Optic Nerve Head

P Perimeter of a Circle

PACG Primary Angle Closure Glaucoma

PCA Principal Component Analysis

PCR Posterior Capsular Rupture

R Radius

RNFL Retinal Nerve Fiber Layer

ROI Region of Interest

ROP Retinopathy of Prematurity

RTA Retinal Thickness Analysis

SIM Statistic Image Mapping

SS Sum of Sqaures

SVM Support Vector Mechanism

T Tangent Length

TCA Topographic Change Analysis

UBM Ultrasound Bio-Microscopy

WHO World Health Organization

xxi

CHAPTER 1

INTRODUCTION

1.1 Telediagnosis in Ophthalmology

Vision is by far the most important sensory organ in the body and has a significant

impact on humans everyday life. With more than 284 million people who are

suffering from visual impairments, from which 39 million are legally blind [1],

ophthalmology has been an important area of research.

There are many different eye conditions and disease due to complexity of the

eye and the related organs in the visual pathway. Some of the most common

eye conditions which affect a large population are Refractive errors, Cataract,

Glaucoma, Age-related Macular Degeneration, Retinopathy and Trachoma.

If left untreated these conditions may become more severe and in some cases

lead to irreversible blindness. The cause and severity of these diseases vary depend-

ing on several factors including the age, lifestyle and environmental influences. To

improve the world’s visual acuity and reduce the lifelong effect of eye conditions,

continuous monitoring and visual inspection of the eye by optometrists and oph-

thalmologists are advised throughout one’s life. This may not be feasible for all

due to the associated costs, restrictions in the available technology and resources,

limitations in experts in developing regions and rural areas as well as the lack of

information and knowledge in some communities.

Many people who would benefit from timely correct diagnosis of uncorrected

1

1. INTRODUCTION

vision especially in regions where accessibility to the experts and resources are

limited. To achieve this and improve the health of many, for years many have

worked towards the betterment of the current ophthalmological procedures, incor-

porating knowledge from different fields. One of the areas which have proven to

have a significant positive impact in the ophthalmology and ophthalmological dis-

ease diagnosis has been image processing. Thus far, image processing applications

have been implemented in all stages of ophthalmology including image capturing,

disease diagnosis, prognosis and treatment. However, these advancements are yet

to meet the need of the growing population.

In recent times, the use of automated diagnostic system in remote locations

by a trained technician without the need of an expert on sight and with no to

minimal user input has been the drive for many investigations.

Majority of the current available diagnostic tools are limited such that these

processes are only functional when the images are of good contrast and the features

are well separated and easily distinguishable. Therefore these systems are not very

reliable or have low accuracy when the optimal conditions are not met [2].

Furthermore, these systems solely look into diagnosis of a single disease. At the

first glance, a wide range of diseases may appear to have similar characteristics and

side effects, which might be lost by an inexperienced technician or young medical

interns. Therefore, the use of these systems would limit the diagnosis and critical

information may also be lost as a result.

Another critical factor which has to be considered for a diagnostic tool is the

cost, accessibility and availability of the system in developing regions. Many de-

vices may require input information from advanced instrumentations. This may

not be possible in remote locations. Therefore this also has to be considered for

such system.

In this doctoral work, the objective has been to aid the surgeons and ophthal-

mological medical practitioners with an automated assistive tool which could be

used to detect some of the most widely affecting diseases. As a result some of the

most widely affected ophthalmological disorders such as Cataract, Retinopathy

of Prematurity (ROP) and Glaucoma which affect more than 60% of the visual

impaired population, have been investigated and their key diagnostic features de-

termined. These features were then determined by suggesting several image pro-

2

1. INTRODUCTION

cessing approaches. The fact that a broad range of features and diseases have been

considered in this case opens up the opportunity for a single diagnostic tool to be

used by all ophthalmologists for broad range of disease diagnosis. This diagnos-

tic tool may also be used as the initial tool for separating the high risk patients

from the normal population. These patients can then be referred to the medical

specialist.

1.1.1 Diseases and Features of Interest

In order to resolve any problem, it is crucial to have an in-depth awareness of

its background information such as its cause, short and long term effect, current

available solutions, appropriateness and reliability of those solutions, and possible

new approaches.

In this case, prior to studying current available techniques and proposing new

ones, detailed understanding and defining ophthalmological diseases, their cause

and impact in the world, and key features of detection is important. As each

disease affects a certain region of the eye, it is essential to investigate those regions.

However, with such a broad range, all aspects could not have been covered in this

study. Since majority of diseases affect the retina in one way or another, studying

retina has been the main area of interest in the performed research. A selected

number of eye and retinal features were chosen for further investigation.

Iris and Pupil have been chosen to aid ophthalmologists in diagnosis and treat-

ment of Cataract which mainly occurs in the older population. At the occurrence

of Cataract, there is a change in shape and clarity of the eye lens. The lens is

visually inspected through the Iris and Pupil. Hence detecting the Iris and Pupil

and monitoring the changes can be useful in complication avoidance. Furthermore,

the proposed procedures for Iris detection can also help in biometrics applications

which have been used globally for security purposes.

Vessels are the most important key feature of the retina as many different

diseases directly influence the appearance and growth of the retinal vasculature.

One of such conditions is the blinding disease of ROP, which affects premature

infants. The life threatening impact of this disease is very significant as it can

influence the lives of the patients, their families as well as the society. As a result,

3

1. INTRODUCTION

studying the vessels and their growth could be beneficial for these patients. In

this study, the vessels and their end-points have been detected to help the lives of

these patients.

Another leading ophthalmological disorder in the world affecting the ageing

population is Glaucoma. It is known to impact the shape of the Optic Disk (OD).

Therefore, studying the OD and its variation in shape can have a major impact

on the patients who might be suffering from this disease. The OD and Macula of

the eye have been investigated and the features extracted in order to help classify

diseases such as Glaucoma.

Despite the fact that each of the features may be used individually to detect

or determine the progression of a specific disease, there are times where the com-

bination of the results obtained from analysing these features would reveal more

information. This would result in an increase in the accuracy and assurance of

disease classification.

The features can also aid in development of a fundus map as their location

would be used as a marker. With an increase in the number of markers, the errors

associated with the mapping decreases and so the precision of the prognosis made

by ophthalmologist significantly improves.

Detection of each individual feature has been proposed by many researchers

but none have considered accuracy of detection by combination of few features.

For the purpose of this study, new methodologies are proposed to determine all

the key features of the eye using image processing.

1.2 Research Question

This study has concentrated on developing and improving the current image pro-

cessing techniques in order to assist ophthalmologists in their preliminary stages

of diagnosis of diseases such as Glaucoma, ROP and Cataract by extracting infor-

mation from the key identifiers of these diseases.

Thus far, visual analyses performed by ophthalmologists have been the best

processing tools for image analysis in disease prognosis. With the recent advance-

ments in image capturing devices, more information and intricate details have been

revealed by the images. With the aid of the computer vision and image processing

4

1. INTRODUCTION

approaches many of these information have been detected and outlined in order

to assist the medical practitioners in their prognosis. Due to non-invasiveness,

functions, reliability and accuracy of the image processing procedures, they have

been of interest by many ophthalmologists globally.

Many studies have been performed towards these ophthalmological tools. How-

ever, the limitations such as the availability of resources, experts, costs, accessibil-

ity and affordability of the devices have restricted the research in the developing

regions or remote locations in developed countries where it is needed most.

In developed countries, the use of the computer vision tools to analysis eye

images in combination with ophthalmological expertise have shown to be more

successful in disease diagnosis and therefore have been of great interest. To enhance

the precision, achieve the desired consistency in the results and the anticipated

automation further improvements are needed.

In order to propose new methodologies which may be incorporated as part of

this telemedical ophthalmological tool, as illustrated in flowchart shown in Fig-

ure 1.1 the main stages of image processing have been considered. The suggested

techniques have to be of high accuracy, adaptable and simple so that they could

be used as part of this tool offsite in remote and rural locations and onsite, by

medical practitioners.

Eye Image Acquisition Image Processing Interpretation Display/Transmission/Storage

Figure 1.1: Stages undertaken in Image Processing

1.3 Research Objectives

The overall objective of this research has been to work towards aiding medical

practitioners in the disease prognosis with a single, cost-effective, diagnostic as-

sistive tool for detection of Cataract, ROP and Glaucoma. In both developing

and developed countries, there has always been the need for such a device due to

limited amount of expertise, instrumentations and resources in remote rural areas.

5

1. INTRODUCTION

The key objectives of this study were to study and examine all stages of im-

age processing and suggest new methodologies to improve the overall results for

ophthalmological diagnosis:

• Image Acquisition stage:

– Create a fundus map to enhance the field of view by using multiple

retinal images

– Study the effect of light refraction

• Image Pre-processing stage:

– Enhancing the contrast

– Introducing additional trimming region

• Feature Detection and Extraction Stage in order to assist ophthalmologists

in their diagnosis stage in particular for wide spread diseases of Cataract,

ROP and Glaucoma:

– Cataract - Detect Iris and Pupil and extract information by locating

the center and calculating the area

– ROP - Detect the retinal vessels and localise the end-points

– Glaucoma - Detect the OD and Macula and extract information by

detecting the center and calculating the area

In order to work towards the objectives, the following factors were also consid-

ered:

• Working towards creating a cost-effective solution for diagnosing diseases in

remote or rural areas

• Increasing the overall accuracy of the image processing procedures

• Suggesting reliable and robust approaches

• Considering the non-invasiveness and safety of the procedures

• Improving the processing time

6

1. INTRODUCTION

1.4 Proposed Methodology

Once the images have been obtained, the image processing may take place. As

mentioned previously, localisation of the features of the eye; iris, pupil, OD, macula

and vessels; have been the basis of the study.

Since majority of the underlying image processing procedures are the same in

all cases, they may be performed once and the output used for further stages.

The first stage in image processing is pre-processing. In the literature, many

different procedures have been suggested, some of which have been chosen and

implemented. However, to further enhance the results, this study has shown

that other procedures such as, redefining the masking region via implementing

a trimming region, as well as enhancing the contract of the images would result

in better outcomes. Therefore, the proposed procedures are also performed in the

pre-processing stage.

Once the images have been prepared and manipulated, the main features of

the eye may be localised in the feature localisation stage. For each case, based on

the features specification, a methodology has been proposed.

The iris and pupil localisation has been performed by the suggested method-

ology of implementing two methods of thresholding and active contour procedure

simultaneously and combing the results to enhance the outcome. The vessels have

been localised using the proposed method of applying edge detection on the 2D

Fast Fourier Transform filtered image. The positions of the OD and macula have

been found using the novel approach of consecutive adaptive thresholding.

This is then followed by extraction of features such as endpoint of the vessels,

the radius of the OD or localisation of its centre.

For a more reliable and practical result, an error study has been performed in

order to better match the approximated results with those of the real life.

To achieve the overall purpose of telemedicine, a new procedure has also been

suggested for fundus mapping, revealing more information to the medical experts

in regards to patients’ health.

All the information obtained and procedures performed can then the displayed

to aid the ophthalmologists in the disease classification.

7

1. INTRODUCTION

1.5 Contributions of the Research

The conducted research, concentrated on incorporating image processing into the

field of ophthalmology. Different stages of image processing, interpretation and

displaying results; their importance and approaches have been considered and new

methodologies suggested for each stage, complementing the available techniques.

The image processing section has been separated into four subsections of image

acquisition, image pre-processing, feature localisation and extraction. The main

contributions of the project are explained briefly in the following:

1. Image Acquisition:

In this stage the best image has been captured and set for the consequtive

sections.

• Light Refraction:

Image capturing procedure is not ideal; moreover, in majority of cases

the refraction of the light has also been ignored. As a result, the errors

associated with light refraction has been calculated and suggested to be

taken under consideration for future studies.

• Fundus Mapping:

In the study, a new approach in creating a fundus map has been sug-

gested, improving the accuracy of the current available procedures.

2. Image Pre-Processing:

In the image pre-processing, in conjunction with the implementation of the

previously proposed techniques in the literature, further modification have

also been recommended.

• Trimming Regions:

New trimming regions have been proposed to remove the bright regions

around the image, which have been caused by the ambient light. The

circular or elliptical trimming region have proven to increase the accu-

racy of detection in particular for the localisation of the OD.

8

1. INTRODUCTION

• Contrast Enhancement:

Since the images have been obtained from different instrumentations

and also the responces of each patient varies from one another, it is

important to enhance the contrast of the image. It has been suggested

to implemnt the further processes on both the original raw data as well

as the contrast enhanced data so that the performance is more accurate.

3. Feature Localisation:

For the second stage of image processing, feature localisation, features such

as iris, pupil, vessels, OD and macula have been detected.

• Iris and Pupil:

For the case of iris and pupil, the use of combination of two readily

available methodologies from the literature has been suggested. Once

the procedures were implemented concurrently, two separate masks were

obtained. Overlapping the masks ensures that the interferences are

reduced and the regions of interest are detected with a higher precision.

• Vessels:

For vasculature detection, different methodologies were considered. Ves-

sels are detected by performing the 2D Fast Fourier Transform filtering

and edge detection filters.

• Optic Disk and macula:

The OD and macula were localised using a novel approach of consec-

utive Adaptive Thresholding technique. In the case of the OD, the

brightest regions were considered, while for macula, the dark regions

were of interest. This technique proved to accurately detect the re-

gions in comparison to the previously suggested approximations from

the literature.

4. Feature Extraction:

The fourth section of the image processing sections is the feature extraction.

In this study, endpoints of the vessels, radius, centre and area of the Optic

9

1. INTRODUCTION

Disk, Macula, Iris and Pupil are calculated. The results would then aid in

interpretation section.

• Endpoints of the Vessels:

In some diseases such as the ROP, determining the endpoints of the

vessels are of great importance as they indicate the regions where the

treatment is required. These points have been detected using the neural

network concept.

• Centre and Radius:

For the centre localisation, two different approaches are suggested. The

first one considers the centre as the middle value of the detected bound-

aries from the feature localisation stage. However, for the case of OD,

the centre may also be located as the origin of vessel formation.

Once the centre is estimated, the radius can then be determined by

calculating the distance between the centre and the boundary of the

detected region.

• Area:

Two different approaches were suggested to calculate the area. The first

approach was to use the calculated radius and apply it to the equation

for the area of the circle to approximate the result. The second approach

was to determine the area using the perimeter of the detected region.

1.6 Thesis Structure

This thesis is organised as:

1. Introduction:

Chapter 1 has been reviewing and introducing the study, considering the

overall purpose of the research. In this chapter, the importance of image pro-

cessing applications in ophthalmological telemedicine has been highlighted.

The research objectives have been defined as assisting ophthalmologists by

improving the diagnosis process of widely affecting diseases of Cataract, ROP

10

1. INTRODUCTION

and Glaucoma. The undertaken methodologies, achievements and contribu-

tions to the field of study have been briefed, outlining the structure of the

thesis.

2. Literature Review:

Prior to the introduction of the proposed methodologies, it is of importance

to study the key areas which are to be detected and studied with the as-

sistance of the image processing technique. Examining the current state of

the art image processing procedures and determining the advantages and

disadvantages of the current approaches would also assist in determining the

areas in need of further improvements.

Chapter 2 introduces some of the ophthalmological diseases such as Cataract,

ROP and Glaucoma, which impact a wide population globally. Their cause,

impact on future generations and importance of early detection and treat-

ment has also been reviewed. The main key features which ophthalmologists

use to detect these conditions have been identified and aimed to be detected

using image processing in the consecutive chapters.

Chapter 3 reviews the important advances in image processing approaches.

The past and current applications have been considered so as the impact of

image processing in the field of medicine in particular in ophthalmology. The

previous literature identifying the key features defined in chapter 2 has also

been reviewed in this chapter. This has then been followed by the general

outline of the image processing procedures undertaken in the study.

3. Contributions of the Research:

In the remaining chapters, image processing techniques have been imple-

mented to detect the features. It should also be noted that in order to im-

prove or resolve any procedure, it is essential to gain vast knowledge about

the extent of the problem as well as the downfalls of the techniques used,

which has been considered throughout the study and each section refers to

a different part of the literature.

Chapter 4 considers the image acquisition and its quality. Image capturing,

Fundus mapping and the impact of light refraction on the findings have

11

1. INTRODUCTION

been considered in this chapter. For the image acquisition section of the

study, open source images have been attained. To improve the precision of

the study, it is necessary to study the light refraction and bending of light

within the eye. Majority of the studies performed previously seem to have

overlooked this crucial fact. the actual angle at which the light enters and

reaches the back of the eye has been calculated and the precision of the

accuracy is determined. Moreover, using similar concept, a new approach

has been suggested in forming a fundus map which may be used to assist the

experts’ decision further, via providing them with a wider view of the retina.

Chapter 5 proposes and implements different pre-processing approaches.

This includes the stages such as image manipulation, masking the region of

interest and filtering. To further improve the accuracy of detection, modifi-

cations such as contrast enhancement and trimming region for noise removal

had been suggested.

Once the image have been prepared, the key features can then be detected.

It should be noted that each feature would have its own specifications and

characteristics which can be used to distinguish them from one another. The

next three chaptes considers the feature localisation and extraction stages of

image processing

Chapter 6 presents the proposed approach for detection of Iris and Pupil,

which may be used as part of Cataract diagnosis or biomedical applications.

Chapter 7 looks into the localisation and extraction of retinal vasculature.

The findings can be used for detection and treatment of diseases such as

ROP.

Chapter 8 considers the image processing approaches which may be used

for detection of OD and Macula. These features are the identifying regions

of diseases such as Glaucoma.

4. Conclusion:

Chapter 9 is the conclusion and possible future contributions in the field

of ophthalmology. In this chapter, the overall contributions have been high-

lighted. Moreover, since technology is a growing field and with forthcoming

12

1. INTRODUCTION

advancements the current techniques may enhance further, potential im-

provements have also been suggested for future reference.

In the flowchart depicted in Figure 1.2, the overall outlay of image processing

stages undertaken in the study is illustrated and the content of each chapter is

shown.

Chapter 1

Chapter 2

Chapter 3

Chapter 4

Chapter 5

Chapter 6

Chapter 7

Chapter 8

Chapter 9

Introduction

Eye

Diseases:

— Cataract

— ROP

— Glaucoma

Image Processing in Ophthalmology

Image Acquisition Image Databases

Fundus Mapping

Refraction Study

Image Pre-Processing

Implementation:

— Colour Separation

— Masking ROI

— Filtering/Noise Removal

— Image Sharpening

Further Modification:

— Contrast Enhancement

— Trimming

ROPFeature Localisation:

— Retinal Vasculature

Feature Extraction:

— End-point

Cataract

Feature Localisation:

—Iris

— Pupil

Feature Extraction:

— Center

— Area

Glaucoma


—OD

— Macula

Feature Extraction:

— Center

— Area

Conclusion

Figure 1.2: Thesis Outline

13

CHAPTER 2

MOST PREDOMINANT EYE DISEASES

Introduction Literature Review

Most Predominant Eye Diseases Image Processing in Ophthalmology

Thesis Outline Conclusion

Figure 2.1: Chapter Two Outline

2.1 Structure of the Human Eye

Humans have five main sensory organs from which the vision is by far the most

important sense throughout their lives. From the moment a child is born, he/she

would start learning by observing the surroundings.

Vision has a great impact in all aspects of one’s life. Describing or distin-

guishing an object would be by far easier if the object is viewed. Imagining and

dreaming becomes more realistic if there is a visual perception behind it. Being

able to see objects would also allow individuals to easily move in their surround-

ings or do all sort of different tasks such as being employed without limitations in

their desired field.

However, currently in the world there are a large number of people who are

14

2. MOST PREDOMINANT EYE DISEASES

visually impaired. This has significant effect in their everyday lives and restricts

them to a certain extent. Moreover, the substantial social implications associated

with these complications would have irreversible emotional impacts in their lives.

There will also be a greater need for extra special resources, facilities and staff

to meet the needs of the visually impaired population resulting in more financial

liability on the governments and the communities. It is therefore essential to reduce

the number of incidences of the complications and patients.

Over the past few decades, with an increased interest in ophthalmological re-

search, there have been significant improvements in ophthalmic disease diagnosis

and treatments, which has reduced the number of severe cases and irreversible

blindness. However, with the growing population there is still need for further

studies and developments, in particular incorporating the biomedical engineering

advancements into the field of ophthalmology.

This thesis will introduce the novel image processing methodologies to extract

key features of interest for ophthalmological disorders. However, prior to doing

so, it is important to know more about the underlying problems, the requirements

and how the image processing applications could aid the medical practitioners in

resolving these issues.

This chapter will discuss a detailed overview of the field of ophthalmology, in

depth study of selected number of ophthalmological major complications, their

categorization and diagnosis. To have a better understanding of these concepts, it

is essential to have a better understanding of the eye and its underlying structure.

Eye is an important sensory organ in the body. A great amount of information

received and processed by human beings is acquired through the eyes.

The human eye is a spherical shaped structure. On average radius of the eye

is about 12mm and the length of the pupillary axis1 is between 23-25mm [3, 4].

Human eye comprises of six main regions: cornea, aqueous humour, iris, lens,

vitreous humour and sclera. The other ocular domains consist of retina and

choroid [3, 5]. Some of these features, including the clear curved cornea, the

colored iris, protective lid, eyelashes, pupil and sclera [6] can easily be viewed by

the naked eye.

1Pupillary axis is the distance between the cornea and the posterior region of the eye.

15


Figure 2.2: Anatomical structure of the eye

Figure 2.2 represents the major regions of the eye [7], each having their own

specific function.

For the purpose of this study, only certain features of the eye are of interest,

including the Iris, Pupil, and other retinal layer internal structure. In the following

section, these features, their structure and biological characteristics are discussed

briefly.

2.1.1 Iris, Pupil and Sclera

Iris is the pigmented structure of the eye and so determines individuals eye colour.

The black circular region surrounded by the Iris is called Pupil which is the opening

of the eye. Iris and Pupil are shown in Figure 2.2 and 2.3.

Based on the Iris, the eye is separated into two regions of the anterior and

posterior regions. The structures in front of the Iris are classified as an anterior

ocular region and the structures behind it are classified as the posterior ocular

region [3, 8].

The white outer layer surrounding the iris is the sclera which continues ante-

riorly into the cornea. The sclera is the connective tissue layer which appears as

the white outer layer of the iris. Due to the intraocular pressure, it has a rigid

structure which allows it to support the eye under muscular control and keep the

16


optical length constant [6].

Another major function of the iris is that it controls the change in the diameter

of the pupil based on different ambient lighting conditions. The iris consists of the

stroma1 which connects to the sphincter pupillae2 and dilator pupillae3. Using this

structure, it can control the size of the pupil. In low light intensity conditions, the

pupil of the eye dilates to about 9mm while at the luminous conditions it shrinks

to about 1mm [3].

Figure 2.3 illustrates the location of the iris, pupil and the sclera of the eye [9].

Figure 2.3: Regions of the eye - pupil, iris and sclera [9]

2.1.2 Optic Disk, Macula and Ocular Vascularization

As it can be viewed in Figure 2.2, retina is the innermost layer of the eye. Since

retina and the optic nerve originate as the outgrowths of the brain during the em-

bryonic development, they are parts of the central nervous system (CNS). Retina

is also the only part of the CNS which can be imaged directly [3, 10].

Using neural cells, the retina, which is a very light sensitive layer, can transform

light energy into neural signals [3, 7]. The signals are then transmitted into the

brain through the optic nerve head into the optic nerve. The optic nerve is also

commonly known as the Optic Disk (OD). All the central retinal vessels and the

arteries of the eye enter through the trunk of the OD.

It should also be noted that about 80% of the ocular blood flows occurs in

the choroid, which is in the mid layer of the eye and has a highly vascularized

structure [11].

1Stroma is a fibrovascular tissue.2Sphincter pupillae are constricting muscles.3Dilator pupillae are dilator muscles.

17


Another region within the retinal of the eye is the macula. Due to the presence

of the carotenoid pigments in the retina and the pigment granules in the retinal

pigments epithelial layer beneath the retina, the macula usually appears darker

than the neighbouring tissue. It should also be noted that the macula’s structure,

size and pigmentation may vary greatly across individuals [11].

Figure 2.4 shows the position of the OD, macula and the vasculature of the

eye.

Figure 2.4: Retinal fundus image where the location of the OD, macula and thevessles are indicated.

2.2 Visual Impairment

Based on the studies performed by World Health Organization (WHO) in 2011,

there are about 284 million people in the world who are visually impaired. This

includes the 245 million people who have low vision, which means that they have

moderate or severe visually impairment. Unfortunatelty, the remaining 39 million

people have irreversible visual impairment and are blind [1, 9, 12]. The leading

causes of blindness include Cataract, Glaucoma and Age-related Macular Degener-

ation (AMD). Table 2.1 indicates the world statistic on vision which was obtained

by WHO [1].

18


Table 2.1: World statistics on visual impairment

Population (Million)

World 6.8× 103 [13]

Visually Impaired 285

Low Vision 246

Blind 39

Blinded by Cataract 18

Blinded by ROP 0.05

Blinded by Glaucoma 50

The significant number of people who are visually impaired has been the main

reason for the wide range of studies performed in the field of ophthalmology, since

loss of vision can be tragic for humans as it would present challenges both for

individuals and the society. Therefore, Saving and restoring vision has been the

main desire and drive for many biomedical and ophthalmological researchers for

better understanding of the eye and its function [6].

2.2.1 Risk Factors of Visual Impairment

Majority of the ophthalmological diseases are multifactorial in the origin. The

factors such as the ocular structure, function, ethnic group, inheritance, location,

life style , presence of other health conditions, age and gender could be the cause

of diverse range of diseases [1, 14].

Statistics reveal that about 87% of the visually impaired live in developing

countries, which indicates that one’s lifestyle, income and the availability and

access to resources could increase the chances of individuals being visually im-

paired [1, 15].

Ones diet and life style can also affect the chances of them being visually

impaired. Factors such as alcohol consumption may increase the chance of occur-

rences of diseases such as Cataract. Several studies have indicated that although

19


moderate alcohol consumption may decrease the chances of Cataract formation,

excess drinking may increase the chance significantly [16].

Studies performed by WHO has also indicated that all over the world, the risk

of visual impairment in females of all ages is higher than the males [1].

Studies have shown that the most common factor for majority of visual impair-

ments is age. 19% of the world population consists of people over 50, from which

82% are visually impaired [1]. With the growing population and the increase in life

expectancy the chances of occurrences of diseases would also increase, in particular

for age related diseases such as AMD and Glaucoma [14].

Other diseases such as Retinopathy of Prematurity (ROP) can also be age

related. The number of incidences of this disease varies depending on the birth time

of the infant. Significant increase in number is observed for infants who are born

before 31 week of gestation or are weighing less than 1250 grams [17, 18, 19, 20].

Visual impairment in children is another area of concern, with more than 12

million children between the ages of 5-15 being visually impaired due to uncor-

rected refractive errors (near sightedness, farsightedness or astigmatism). From

this, 1.4 million children are blind. The lifelong effect, resources and complica-

tions that the children are facing is tremendous and would have an impact on

them as well as the society [1].

What is interesting is that the studies have indicated that about 85% of the

visually impairment in the world could be avoided [1] if:

• Healthcare services are improved, increased and made more affordable.

• Further research and studies are performed for cure and prevention of oph-

thalmological complications by the national leaders, medical professionals

and private and corporate partners.

• The general population becomes more aware and educated about the avail-

able health care services.

• The infectious causes of vision loss is eliminated via effective eye health

strategies.

20


2.2.2 Ophthalmological Diseases and Complications

There are many different eye conditions. The most widely affected diseases which

result in visual impairment include Cataract, Glaucoma, AMD and Uncorrected

refractive errors. Other diseases affect smaller number of people in the society,

a few examples could include ROP, Diabetic retinopathy, Corneal opacity and

blinding trachoma. Figure 2.5 depicts the percentage of the population affected

by these diseases based on the statistics obtained by WHO in 2011 [1].

Corneal Opacity5%

Diabetic Retinopathy

5%

Childhood Blindness

4%

Trachoma

3%Cataract

48%

Other

14%Glaucoma

12%

Age-Related Macular Degeneration9%

Figure 2.5: Global causes of blindness and the percentage of affected population [1]

As it can be seen in the figure 2.5, Cataract is the leading cause of visual

impairment in the world. It causes about 48% of the blindness especially in the

developing countries where about 18 million people are blinded by Cataract [21,

22, 23]. Cataract occurs when the protein structure within the lens is denatured,

resulting in clouding of the lens and impeding the light from passing through it.

Later on in this chapter, more details regarding the cataract, its aetiology and

stages will be discussed.

Another condition which affects a significant number of people is Glaucoma. It

affects the ganglion cells and their axons, and as a result it alters the topography

of the OD [24, 25]. In depth review of Glaucoma will be provided in Section 2.5.

AMD is an age related disease which affects the macula and results in loss of

21


central vision [26]. It is one of the main ophthalmological complications since with

an increase in the growing elderly population; the number of AMD also increases.

Another disease of interest is the ROP which occurs in the premature infants.

It affects the vessel formation in the retina as a result of variation in oxygen

consumption [27]. ROP has been covered in more details in this chapter.

Studies performed by Taylor et.al. indicated that in 2004 in Australia, 480,300

people had low vision, including the 50,600 people who are blind with the numbers

excepted to double by 2024. The common causes of the blindness were found to

be uncorrected refractive error which counted for 62%, Cataract, 14%, and AMD

10%. Moreover it was suggested that about 76% of the uncorrected refractive error

and cataract could have been avoided and treated if detected early [28]. Therefore,

it can be seen that vision loss even in Australia as a developed country is a critical

problem and should be further examined.

In this study, some of the diseases including the Cataract, Glaucoma and ROP

are chosen for further investigation. For each of them, in the following section,

a brief history, the cause and biological pathogenesis, risk factors, classifications,

screening and treatment is explained in more details.

2.3 Cataract

Cataract is one of the leading vision loss disorders in the recent times. Cataract

is a condition where the protein structure within the crystalline lens of the human

eyes is denatured, causing its opacity to change, appearing to be cloudy. This

opacification obstructs the path of the light entering the eyes, blurring the patients’

vision [23, 29].

The major leading factor in cataract formation is age, since with aging the

protein structure within the lens of the person starts binding or cross linking with

one another, becoming stiffer and forming cloudy spots [29, 30].

Patients with cataract experience range of visual deficits including: detrition

of visual acuity, problems under glare condition, altered colour recognition, loss of

contrast sensitivity [31, 32]

In the past few decades there has been an increase in the rate of cataract in the

world even in the western countries. Due to its negative effects in health related life

22


qualities such as difficulty in visual associated daily activities, impaired physical

performance, reduced health status and associated costs, it has become an area of

concern [33]. Therefore, many researchers have concentrated on cataract, its early

diagnosis and treatment.

2.3.1 Worldwide Effect of Cataract

The impact of cataract globally is very significant. It has been found that cataract

is the leading cause of blindness worldwide, accounting for 39.1% of the total

blindness if refractive error’s statistics is considered and 47.8% of blindness if the

refractive error’s statistics is excluded. This suggests that cataract by itself is the

cause of blindness in more than 17.7 million people [22] in both developing and

developed countries, with the number increasing each year [21].

Lawani et.al. and Agarwal et.al. have found that in developed countries,

cataract is the cause of loss of sight in 5% of the population, while in developing

countries it is responsible for more than 50% of the blindness [34, 35].

2.3.2 Risk Factors of Cataract

There are several risk factors [16, 22, 36] associated with cataract formation, some

of which include:

• Age - Increasing age would increase the change of cataract formation.

• Gender - Females have higher tendency in contracting cataract.

• Life style - Higher chance of cataract if living in warmer, sunnier climates,

engaged in outdoor activities.

• Latitude - people living in northern latitudes are more likely to have cataract.

• Income - The low to middle income families especially in developing countries

has a higher chance of having cataract.

• Ultraviolet light - People living in regions with higher ambient ultraviolet

light have higher risk of cataract.

23


• Alcohol consumption - Although moderate drinking reduces the chances

of cataract formation but high alcohol consumption increases the risk of

cataract formation such as the posterior sub-capsular cataract.

2.3.3 Classification and Screening of Cataract

Accurate diagnosis and treatment of cataract is essential and can prevent vision

loss. The preliminary stage in treatment is to precisely categorize the cataract and

based on that choose the appropriate treatment method. The ophthalmologists

have to examine the Iris and Pupil of the eye to determine the existence of Cataract.

Based on the location of the development of the cloudy spots, the cataract is

categorized into three types [29, 37]:

1. Posterior subcapsular Cataract - occurs at the back of the lens

2. Cortical Cataract - occurs at the lens cortex and extends its spokes from the

outside to the center of the lens

3. Nuclear Cataract - is the most common type of the cataract and occurs in

the nucleus

Measuring the severity of the cataract is also important for choosing the right

treatment methodology. Several different techniques for quantification of severity

of cataract have been suggested in the literature [29, 38, 39, 40, 41, 42] includ-

ing a very common technique of Wisconsin Cataract Grading System [38]. Fig-

ure 2.6 shows the grid used in the Wisconsin Cataract Grading System for defining

cataract location in the right eyes.

Figure 2.6: Template used in the Wisconsin Cataract Grading System for locatingthe Cataract in the right eyes.

24


2.3.4 Treatment of Cataract

The common treatment for cataract is performing the cataract surgery which is

highly effective and results in somewhat immediate visual rehabilitation. It im-

proves the visual acuity of patients considerably. The most common cataract

surgery types include:

1. Intracapsular Cataract Extraction (ICCE)

2. Extracapsular Cataract Extraction (ECCE)

3. Manual Small Incision Cataract Surgery (MSICS)

4. Phacoemulsification

The impact of cataract surgery is very significant in an individual’s life as it

provides them a better chance for performing daily activities, as well as improving

their social and emotional life components. The evidence also suggests that the

surgery improves the visual functions in co-morbid eye conditions especially if

performed in the early stages of disease [23].

Although the cataract surgery has proven to be very successful and cost-

effective, its performance in developing countries are somewhat challenging [22,

35, 43]. Moreover with the advancements in technology, patients’ expectations

will undoubtedly increase in the future [21].

Since the scope of the project does not require the detailed procedure of differ-

ent types of cataract surgeries, they have been briefly explained in the following.

The following literatures maybe referred to for more information [44, 45, 46, 47].

2.3.4.1 Intracapsular Cataract Extraction (ICCE)

The initial surgical technique to treat cataract was Intracapsular Cataract Extrac-

tion (ICCE). In the ICCE a large incision is used to remove the entire natural lens

of the eye, including its capsule.

This technique was unable to correct refractive error and so the visual recovery

was not sufficient [22]. Over the years the use of this technique has declined with

the introduction of ECCE procedure and the use of Intra-Ocular Lens (IOL).

25


The associated steps in the Intracapsular Cataract Extraction has been shown

in the Figure 2.7.

Figure 2.7: Intracapsular Cataract Extraction [48]

2.3.4.2 Extracapsular Cataract Extraction (ECCE)

Extracapsular Cataract Extraction (ECCE) procedure has shown to be more suc-

cessful and result in better visual outcome and quality of life in comparison to

the ICCE method [22]. In this surgery, the incision size is smaller in comparison

to the ICCE, about 8-12mm, and only the lens is removed while the capsule is

untouched [49].

The Extracapsular Cataract Extraction has been shown in the Figure 2.8.

Figure 2.8: Extracapsular Cataract Extraction [50]

26


2.3.4.3 Manual Small Incision Cataract Surgery (MSICS)

Manual Small Incision Cataract Surgery (MSICS) is the most commonly used

technique in developing countries and it surfaced literature in the early 1990s [51].

In the MSIC process, the lens is removed as a whole through a self-sealing scleral

tunnel wound [52]. The wound does not require any sutures and is smaller than

the ECCE surgery, about 6.5mm [53].

Figure 2.9, represents the steps in Manual Small Incision Cataract surgery for

Cataract removal.

Figure 2.9: Manual Small Incision Cataract surgery [54]

MSICS is more cost effective, has faster rehabilitation and would result in bet-

ter visual acuity in comparison to the ECCE [21, 22, 35]. However, in comparison

to the Phacoemulsification technique the outcome of the surgically induced astig-

matism is higher in MSICS [21] and it may lead to several post-operative refractive

errors [22]. Overall the visual acuity of the phacoemulsification has proven to be

better in comparison to other available techniques [55, 56].

2.3.4.4 Phacoemulsification

Phacoemulsification is the most modern technique in Cataract surgery. It refers

to the procedure were the lens is divided into pieces and emulsified by an ultra-

sonic surgical handpiece. The pieces are aspirated out with the chamber fluid.

The anterior chamber pressure is kept constant via irrigation of the balanced salt

solution [57].

The ultrasonic surgical device currently used in phacoemulsification was first

introduced by Kelman in 1967 and has improved extensively since [58, 59, 60].

Figure 2.10, illustrates the Phacoemulsification surgery for Cataract removal.

27


Figure 2.10: Phacoemulsification surgery [61]

Some of the advantages of phacoemulsification technique [21, 55, 62] over other

available techniques could be as follow:

• Smaller incision size - 1.0 ± 0.12 mm

• Less invasive - Smaller incision size, no sutures

• Short surgical time - about 10 minutes

• Less surgically induced astigmatism

• Less leakage of fluids - Type and direction of the incision as well as the blades

used ensures that the anterior chamber fluid leakage is minimal.

• Rapid recovery

• Better visual acuity - Corrected vision as a result of lens replacement

The most recent advancements in phacoemulsification are that the needle

tip vibrates longitudinally and horizontally at frequencies ranging between 28-

50 kHz [59]. As a result the patients are exposed to low frequency ultrasonic

energy and the heat it may produce. It should also be noted that since the heat

28


may damage the corneal endothelium and hence affect the overall surgical out-

come, the exposure time and average power of the device should be monitored

constantly [60].

2.3.5 Monitoring Surgical Trainees

Majority of the surgeons’ today use computer based training tools as a preliminary

basis for performing Cataract surgeries. However, with only a few hours of training,

their level of expertise may not be sufficient when it comes to real life complications.

Moreover, majority of the performed surgeries are also subjective with no ref-

erence to a validated standard. They are based on the surgeons’ experience. The

limited experience or severity of the surgical complication could result in the life-

long side effects in patients’ life.

As a result it is essential to have a monitoring system to see the overall progress

of the surgeons. This system can also be used as an assistive tool to train and

guide the surgeons through the surgery. For the case of Cataract, the first step in

creating this device is to exactly locate the Iris and Pupil which has been further

investigated in the following chapters.

2.3.6 Importance of Iris and Pupil for Diagnosing Cataract

Based on the above factors, locating the Iris and Pupil during the surgery can

be used to determine whether a complication has occurred or not. This can be

achieved by studying the extent of the variation which occurs in shape of the Iris

and Pupil.

2.4 Retinopathy of Prematurity(ROP)

Approximately about 1% of the neonates are born prematurely, with a birth weight

below 1,500g, while roughly about 0.5% weight less than 1000g. The overall birth

rate is about 1 per 100 inhabitants per year [17].

Usually the premature infants’ retinas have underdeveloped vascularisation.

ROP is believed to affect the postnatal abnormal growth of these retinal blood

29


vessels, resulting in the formation of vascular shunts, retinal neovascularization,

and even tractional retinal detachment which in severe cases may lead to blind-

ness [17]. It is a disease which affects both eyes of the infants and in some cases

the effect may be irreversible and lead to blindness.

Figure 2.11 illustrates how the vasculature differs between the normal out-

growth and the patients with ROP [63].

Figure 2.11: Illustration of differences between normal and abnormal retinal blood-vessel development in the child with ROP.

ROP was first described by Terry in 1942-1943 as ”retrolental fibroplasia” [64,

65]. In the following 10 years, ROP was recognised as the largest cause of blindness

in developed countries and was growing in epidemic proportions.

Soon after, oxygen therapy 1 was recognised as the major cause of ROP and

hence the use of it was restricted [65]. As a result of this discovery, the incidence

of ROP decreased significantly. However, this adverse reaction was also associated

with an increase rate of morbidity and mortality in the premature infants [66, 67].

Therefore the oxygen therapy was once again brought in but supplemental oxygen

delivery to the premature infants was monitored carefully to main adequate blood

levels [68].

During 1980s and 1990s new treatment modalities such as vitamin E supple-

mentation, cryotherapy, laser photocoagulation and nursery light levels were stud-

ied and considered effective in reducing chances of occurrence of ROP [17, 65].

Even with the controlled oxygen level and the new treatments, the number of

1Oxygen therapy is the administration of oxygen for chronic or acute patient care.

30


infants with ROP has increased since then [69, 70]. This is mostly due to the

advancement in technology and hence the increased survival rate of very low birth

weight infants [70, 71].

2.4.1 Worldwide Effect of ROP

Throughout the years ROP occurrence has remained very high and one of the

areas of interest and research. This may be due to the fact that this disease affects

premature infants and in some cases leaves long lasting irreversible results. In such

cases, the patient may be severely visual impaired or even blind. These patients

will have to go through life with a condition which could have been easily avoided

or minimised if they were treated on time.

Despite the available treatments and research being conducted in the field of

ophthalmology, ROP still is known to be one of the major causes of blindness

in children in both developed and developing world [70, 72]. The proportion of

childhood blindness caused by ROP goes from 8% in high income countries to

40% in middle income countries. In Australia and New Zealand, every 1 in 10

premature infants develop severe ROP [73].

Retinal detachment is quite uncommon in children, accounting for only about

1.7% and 5.7% of all retinal detachments [74], but it is the cause of blindness in

ROP. In general, retinal changes which may be indication of regressed ROP, include

myopic changes, displacement of macula and retinal vessels, retinal folds, pigmen-

tary changes, incompletely vascularized peripheral retina, abnormal branching and

tortuous and telangiectatic vessels [75].

2.4.2 Risk Factors of ROP

There are many risk factors associated with ROP. With advances in the neonatal

care, the number of surviving premature infants has increased significantly, which

in some case may lead to development of ROP.

The low birth weight and low gestational age are known to be strong risk factors

of ROP, where the smallest infants are more likely to develop ROP.

Oxygen has been recognized as another significant risk factor since the 1950s.

31


However, the direct correlation of duration and concentration of oxygen with sever-

ity of ROP is not yet confirmed.

Other factors such as degree of illness, sepsis, blood transfusions, white race,

multiple births, and being born outside a hospital also increase the chances of

developing ROP [17, 65].

Socioeconomic factors and health care conditions of each country should be

considered while recognising the risks associated with ROP. Statistics have shown

that the occurrence of ROP is significantly increased in the developing countries

due to health care system and lifestyle in comparison to developed countries.

2.4.3 Classification of ROP

Once the patient is diagnosed to have ROP, to begin the treatment, the first step

is to classify the ROP. The studies have shown that more aggressive diseases are

located in the posterior section of the eye. Figure 2.12 represents the zones and

extent which are used to determine the classification of the ROP [17].

Figure 2.12: Classification of ROP for the left eyes [17]

The classification comprises of three parameters:

1. Location - zone of the disease in the retina [17]:

• Zone I is the posterior circle centred on the optic disc. Its radius is

about twice the distance from the disc to the centre of the macula. It

is defined as the most posterior location of disease.

• Zone II is a circle centred on the disc with a radius equal to the distance

to the nasal ora-serrate.

32


• Zone III comprises the remaining temporal crescent.

2. Extent by clock hours of developing vasculature involved

3. Severity - stage of the observed abnormal vascular response [76]:

• Stage I - mild abnormal blood vessel growth.

– No treatment is required and the child eventually may develop nor-

mal vision without further progression.

• Stage II - moderate abnormal blood vessel growth.

– No treatment is required and the child eventually may develop nor-

mal vision without further progression.

• Stage III - Severe abnormal blood vessel growth.

– Abnormal blood vessels formation towards the centre of the eye

instead of following the normal growth pattern along the surface of

the retina.

– Some infants may not need treatment and develop normal vision.

– Some infants who have certain degree of Stage III and ”plus dis-

ease1” need treatment to avoid retinal detachment 2.

• Stage IV - Partial detachment of retina.

– Treatment is required. The bleeding caused by scars of the abnor-

mal blood vessels cause traction and pulls the retina away from the

wall of the eye.

• Stage V - Complete detachment of retina.

– Treatment is required. If the eye is not treated, the child may have

severe visual impairment and even blinded.

1Plus disease is when the blood vessels of the retina have become enlarged and twisted. Thisindicates the worsening of the disease. Treatment may prevent retinal detachment. Prior to theformation of plus disease, significant vasoconstriction may be present.

2Retinal detachment occurs as a result of accumulation of the Sub-retinal fluid in the spacebetween the neurosensory retina and the underlying retinal pigment epithelium. It is classifiedinto Rhegmatogenous, Tractional and Exudative based on the mechanism of the sub-retinal fluidaccumulation [77].

33


2.4.4 Screening for ROP

The suggested examination time for the first visit is about 32-34 week of post

menstrual age and for the second visit is about 38-40 weeks post menstrual age [17].

Prior to screening the pupil of the eye needs to be dilated. To dilate the pupil

three times every 5-10 minutes eye drops are used.

At the time a nurse needs to be present to constrain the movement of the

infant and also look out for vital signs and clear airways, as Bradycardia due to

the oculocardiac reflex is a recognized to cause complication during the examina-

tion [17, 69].

During the screening process, follow-up and therapy the location, extent and

severity of disease are monitored and evaluated. The changes in the different

segment s of the eye, presence of persistent and dilated vessels in the retina are

monitored to see whether the treatment is needed [17].

Digital retinal wide-field imaging system is used to monitor and capture images

of the retina. Using the obtained data evaluation of the shape, degree of arbori-

sation, diameter of retinal vessels and estimate the severity of the disease even in

the absence of complete imaging has become feasible.

2.4.5 Treatment of ROP

Once the patient is diagnosed and is in need of treatment, photocoagulation ther-

apy or cryotherapy is recommended. Since the early 1990s, laser photocoagulation

has been used [78, 79, 80, 81] and is the preferred treatment method in comparison

to cryotherapy [17, 82, 83, 84].

Incidence of ROP have significantly reduced as a result of by better screening

and prophylactic cryotherapy or laser photocoagulation [75]. The treatments

have reduced the occurrence of blindness by approximately 25%; however, the

visual outcomes after treatment are often poor and patient may not have 20/20

vision.

The American Guidelines indicate the time to treatment has to be within 72

hours [17], but in some cases treatment should be provided without further delay.

These include patients with advance stage of the disease or those with zone I and

rapid progression disease.

34


Recently it has been advised to start early treatments to avoid rare potentially

blinding disease. Earlier treatment is now recommended for aggressive forms of

ROP, such as zone I and posterior zone II disease. In these cases the treatment

can occur as early as 30.6 weeks post menstrual age [17].

2.4.6 Importance of Retinal Vasculature for Diagnosing

ROP

As indicated several occasions in section 2.4, ROP is an ophthalmological disease

which is caused due to abnormal growth of the vasculature in the retina. The extent

of the damage of this complication is dependent on the screening and diagnosis time

as early detection reduces the possibility of severe complications and blindness.

Hence an automated monitoring system could be used as an assistive tool to

aid the technicians and medical practitioners in their diagnosis. This system can

be used in remote, rural areas as a preliminary diagnostic tool which distinguishes

the patients prone to ROP from the normal patients. Moreover, by further analysis

of the retinal vessels in cases where severe cases of ROP are detected, the system

may outline the regions of the retina which are affected and are in need of further

treatments.

In order to create this system, it is crucial to extract the exact location of

the retinal vasculature. This can be achieved by analyzing the fundus retinal

images using image processing techniques. In this study, new automated image

analysis approaches have been considered for vascular localization and key feature

extraction. More details are included in the consecutive chapters.

2.5 Glaucoma

In Greece in 400 BC, the term Glaucoma was first used by Hippocrates to describe

a dimming of vision. Many years later, in 1862, the pharmacology of Glaucoma

was first detected with the isolation of physostigmine from the calabar bean [85].

Glaucoma is now the second leading cause of irreversible visual loss and blind-

ness [1]. Due to asymptotic characteristics of this disease [86] and with the aging

population and health issues such as diabetes [87], the incidences of Glaucoma

35


remain high and an area of concern. Hence, to minimise vision loss in patients,

early detection and treatment of Glaucoma is essential.

It has been found that the cause of Glaucoma is the progressive loss of Retinal

Ganglion Cells and their axons.

This in turn causes morphological changes in the OD and visual field [35, 88,

89]. The initial signs observed are usually hemorrhage-associated retinal nerve fibre

layer defects. This is then followed by the visible changes of the OD, including the

thinning of the neuroretinal rim, pallor and progressive cupping of the OD. Often,

the visual field defects are detected at the later stages, where more than 40% of

axons are lost [35].

2.5.1 Worldwide Effect of Glaucoma

The leading cause of the irreversible blindness in the world is Glaucoma. It is also

the most common cause of blindness after Cataract. Worldwide, it has contributed

to the 14% of the blind population. Those accounts for about 70 million people,

from which 10% have been bilaterally 1 blinded by this disease [90].

2.5.2 Pathogenesis of Glaucoma

It is believed that Glaucoma damages the ganglion cell and its respective axons,

which comprise the Retinal Nerve Fiber Layer (RNFL) [90].

The progression of this damage results in asymmetric changes to the Optic

Cup (OC) and as a result visual field loss. Since there is no functional loss prior

to severe structural damage, up to 40% [35, 90], it is quite difficult to detect

Glaucoma early on in the disease progression.

The morphology of the defected RNFL appears to follow the normal structural

pattern of the retinal RNFL. The RNFL is usually striated. It radiates from the

OD and is thickest in the superior and inferior poles in comparison to the nasal

and the temporal poles. However, the Glaucomatous RNFL changes can present

as focal wedge-shaped defects of varying width radiating from the optic nerve head

or as diffuse loss of the striations in RNFL [90, 91]. Focal loss is often detected in

1Bilaterally means affecting both eyes

36


the superior and inferior nerve fibers as Glaucoma usually affects these regions.

2.5.3 Risk Factors of Glaucoma

In the literature, several factors have been found which may influence and increase

the possibility of occurrence of Glaucoma [92]. These factors include:

• Age - older people are more likely to develop Glaucoma

• High Intraocular Pressure (IOP) - leading cause of Glaucoma

• Ethnicity - African, Latino and Asian descendants are more likely to have

Glaucoma

• Family History of Glaucoma

• Diabetes - the chance of Glaucoma doubles in diabetic patients

• Myopia (shortsightedness) - changes the internal structure of the eye, in-

creadint the chance for formation of Glaucoma

• Extremely high or low blood pressure - deprives the eye from adequate blood

flow, affecting the the rate of oxygen and nutrients as well as the waste

removal from the eye

• Long term usage of Steroid/Cortisone - increases the IOP and so results in

Glaucoma

• Injury to the eye

2.5.4 Classification and Screening of Glaucoma

Diagnosis and early treatment of Glaucoma is essential in prevention of vision loss.

Prior to implementing the right treatment method, the exact type of Glaucoma

has to be categorised.

There are several different types of Glaucoma. Some of which includes [90]:

1. Primary Open Angle Glaucoma - gradual increase in IOP

37


2. Normal Tension Glaucoma - known as Low Tension Glaucoma and occurs

when there is a progressive damage to the optic nerve under normal IOP

3. Angle Closure Glaucoma - inherited

4. Acute Glaucoma - sudden increase in IOP

5. Pigmentary Glaucoma - type of an inherited Open Angle Glaucoma

6. Trauma related Glaucoma - acute or chronic development as a result of an

injury to the eye

7. Childhood Glaucoma - occurs in children when there is an abnormal increase

in the IOP

2.5.5 Treatment of Glaucoma

As mentioned earlier, Glaucoma may cause an irreversible blindness, therefore

early diagnosis and treatment of it could be crucial to manage this disease. De-

pending on the severity of the Glaucoma, several different treatment options are

available [90], including:

• Eye drops

• Medication

• Surgery - Traditional or Laser

2.5.6 Importance of Optic Disk and Macula for Diagnosing

Glaucoma

For years, clinical approaches were used for monitoring patients with Glaucoma.

The ophthalmologists considered OD and its variation in shape to monitor the

progression of this disease. However, due to limitations of the subjective nature

of the evaluation and progression of the disease, the use of computerised image

analysis technique is suggested.

38


The automated assistive tool can aid in localising and extracting the infor-

mation from the OD and Macula. The obtained information can then assist in

diagnosis and prognosis of diseases such as Glaucoma. Further details in regards

to the image processing procedures involved in localisation of the OD and Macula

is covered in the consecutive chapters.

2.6 Summary

This chapter has covered the importance of vision in humans life. The field of

ophthalmology and some of the most common ophthalmological complications were

also discussed.

Three of the major leading causes of impairment in vision were investigated

in details, including the Cataract, ROP and the Glaucoma. The key features in

diagnosing these diseases have been defined and will be examined in more details

in the coming chapters.

The key features that have been found for Cataract, ROP and Glaucoma are

Iris and Pupil, Retinal Vessels, and OD and Macula respectively.

39

CHAPTER 3

IMAGE PROCESSING IN OPHTHALMOLOGY

Introduction Literature Review

Most Predominant Eye Diseases Image Processing in Ophthalmology

Thesis Outline Conclusion

Figure 3.1: Chapter Three Outline

3.1 Ophthalmological Complications

For years, diagnosing of ophthalmological disorders was being performed by obser-

vation. The results were very subjective and could have varied based on individuals

perspective and experience level.

In recent years, with advancements in biomedical applications and in particu-

lar image processing, new procedures have been implemented to provide a more

objective review of diseases and their diagnosis. To gain a better understanding

the current procedures, this reviews the available technology and image processing

methodologies.

Since the field of ophthalmology is quire broad and covers a wide range of infor-

mation, an in depth review of some of the main ophthalmological complications has

40

3. IMAGE PROCESSING IN OPHTHALMOLOGY

already been conducted and covered in the previous chapter. The diseases include

the Cataract, ROP and Glaucoma. The key features of interest in recognising

these diseases were also identified, including the Iris and Pupil, retinal vessels, OD

and Macula.

3.1.1 Importance of Image Processing in Ophthalmology

For years, health care system was only progressing based on the experiences and

knowledge of the health care professionals. However, with an increasing popula-

tion, longer life span and technological advancements, there is a need to change

the traditional methods of manual patient examination with more modern semi-

automated or automated procedures. This could be beneficial for both the patient

and the medical experts especially in regions where the number of experts are

much less than the number of patients.

Incorporation of the medical field with engineering, has led to a new field of

biomedical engineering. Biomedical engineering has played significant role in all

stages of medical procedure, including the prognosis, detection, treatment and post

treatment. This collaboration has led to increasing number of successful cases.

One of the main areas which has helped majority if not all the medical fields

significantly is imaging. With the advancements in imaging devices, nowadays

many of diseases and complications may be detected early on, leading to less

severe cases and early treatments.

Despite these significant life changing outputs, there is still much more to be

done and imaging continues to be a growing field.

Ophthalmology is also benefited significantly from imaging devices. Similar to

other medical fields, imaging has helped ophthalmologists in their prognosis of dis-

eases and their progression, detection of complications, inter-operative procedures,

post treatments and many more. It has also allowed researchers to have better

knowledge and view of the underlying structures of the eye, and its complications.

Imaging consists of different sections. The foremost step is the image capturing.

It is important to consider the requirements and the purpose of the image; based on

these specifications the image can then be obtained. Once the image is captured,

the image may be analyzed manually by the ophthalmologists. However, in many

41


cases the analysis by an expert may not be possible.

With the increase in world population and limitations in the experts and ad-

vanced resources, the manual analysis of the captured images may not be possible;

as a result a new field of telemedicine is introduced. Telemedicine is especially in

use in growing and developing countries and remote locations of developed coun-

tries such as Australia. This is where the images and preliminary analysis is done

remotely and automatically.

This new field is very much dependent on the collaboration and close work of

medical professionals and biomedical engineers. The knowledge of the engineers in

image analysis and the experiences of the medics have allowed the image processing

to be achievable and of great importance even in the field of ophthalmology.

The flowchart 3.2 illustrates the steps undertaken in image processing.

Eye Image Acquisition Image Processing Interpretation Display

Figure 3.2: Stages undertaken in Image Processing

3.2 Image Processing Procedures

As mentioned thus far, image processing has been the key for much advancement

in both fields of ophthalmology. The basis for the validity of the knowledge and

understandings in these fields had become feasible due to applications of image

processing.

The name ”Image Processing” indicates a system or program which is capable

of manipulation of an image. Based on this, the first step to consider would be

the image which is the input to this system.

Once the image has been acquired, the next stage would be manipulation or

processing this image such that the required information could be obtained. This

can be achieved by applying a computer based procedure, a program, or an algo-

rithm to the image. The objective at this stage is to extract the region of interest

such that the required information could be obtained.

42


The next stage is to interpret the findings which could be a visual interpretation

or a quantitative analysis of the results. The findings can then be displayed to the

user.

All the image processing applications follow these basic steps. However, de-

pending on the objective of the research and the required results, there might be

some minor changes to the steps.

In this study the main objective has been to detect the key features of the

eye, including the Iris, Pupil, retinal vessels, OD and Macula. To gain a better

understanding of the available literature and possible processes in biometrics and

ophthalmology, in this section, some of the image processing methodologies used

to detect these features have been reviewed and discussed.

3.2.1 Image Processing in Biometrics

Another area in which image processing plays a significant role, is Biometrics.

Biometrics refers to characteristics, physiological and behavioural, which may be

used to identify individuals.

There are several distinctive physiological characteristics, such as finger print,

DNA, facial recognition, Iris recognition and many more. The behavioural char-

acteristics include the locomotion, voice and other behaviours which may be used

to distinguish people.

For years, each of these characteristics has been investigated. Many studies

have looked into the advantages and disadvantages of each of these biometric

characteristics.

One of the most recent fields of interest in biometrics is the Iris recognition.

In recent years, the Iris recognition systems have become of significant interest, in

particular for security applications. Therefore, many studies have been performed,

aiming to identify this biometric characteristic. Image processing procedures have

been the main tool used for this characterisation.

This is due to the higher sensitivity, accuracy and automation capability of the

image processing tools. Its flexibility and robustness has been able to provide the

users with extensive amount of precise information.

The chosen area of interest in this study is the Iris. Therefore, it is important

43


to propose a methodology to detect and localise its boundaries with high precision.

Many approaches have been suggested, but majority assume that the Iris is circu-

larly shaped. Some of the current available procedures have been discussed in more

details in the image processing procedures for Iris recognition in Section 3.2.2.1.

3.2.2 Image Processing in Ophthalmology

For each ophthalmological feature of interest, many different approaches have been

investigated and studied in the literature. Some of the most widely techniques for

detection of the Iris and Pupil, retinal vessels, Optic Disk and Macula has been

reviewed and discussed in this chapter.

3.2.2.1 Iris and Pupil Localisation

Majority of the performed procedures can be separated into two groups, consid-

ering two different assumptions. The first group considered Iris and Pupil to be

circularly shaped and therefore the suggested procedures approximate the loca-

tion accordingly. The second group aimed to exactly localise the Iris and Pupil

boundaries.

Circular Assumption:

The two commonly used method of Iris and Pupil localisation are the Daugman

and Wildes.

For localisation Daugman proposed the use of Integral Differential Operator

which acts as circular edge detector, implemented on camera shot images. This

procedure was first introduced in 1994 for biometric applications with the false

acceptance probability of about 1 in 1031, accuracy of 98.6% and processing time

of about 7 seconds [93, 94].

Nishino continued on the work of Daugman by introducing an elliptical shape

assumption of the Iris and Pupil. This improved the procedure as gaze direction

was no longer of importance and non-forward looking images could have been

analysed [94, 95].

As mentioned, Daugman is a very well-known method which has been modified

by many over the years. One of the more recent modifications and extension of this

approach has been suggested by Ferreira et.al. [96]. The results from the use of

44


Template Matching in order to reduce the computational complexity and reflexion

removal have shown to be successful in faster detection of Iris and Pupil by about

7 to 10 times of the Daugman method, with the recognition rate of about 87.2% -

88% for different databases. However, since in the proposed procedure templates

have been used, the exact boundaries have not been extracted.

One of the widely used approaches for detection of features of interest of the eye

is Circular Hough Transform (CHT). It was initially introduced by Wildes, where

the edge detection and Hough Transform (HT) were applied in order to determine

the Iris boundary for biometric purposes [94, 97]. The results are of very high

accuracy, 99.9%, with the processing time of about 9 seconds. However, since CHT

is a three dimensional process, it is computationally complicated and requires large

storage spaces. Moreover, it requires pre-filtering and prior knowledge regarding

the location of the Iris or Pupil.

Cui et.al. localised the Iris and Pupil by following a coarse to fine strategy,

applying Canny edge detection first, followed by HT in order to increase the speed

of detection [94, 98]. The proposed algorithm detected the boundaries of the

Pupil using the low frequency of the simplest Wavelet Transform, Haar Wavelet

Transform, and Iris with an Integral Differential Operator. This robust process

has a high accuracy of 99.54% and the processing time of about 0.2 second. The

precision of detection is less than those proposed by Daugman and Wildes but the

processing time is improved rapidly. The downfall of this process is that it only

estimated the boundaries of the Iris and Pupil.

In another study performed by Daouk et.al. [99], similar steps are undertaken

while considering the Iris localization, pattern extraction and matching. The au-

thors have proposed the fusion of Canny edge detection and CHT for detection of

the Iris. The Haar wavelet transform is applied in this in order to extract the Iris

patterns. The pattern matching is performed and quantized using the Hamming

Distance Operator. The success rate is 93% with the average computational time

of 31 seconds. The concept used by this group can be beneficial for the biomet-

ric identification systems. However, due to long processing time, it may not be

feasible to be used in ophthalmological applications.

A more recent modified version of the Wildes approach using gradient of the

image, has been implemented by Moravik et.al. [100]. The gradient is found using

45


the first derivative of the image, followed by CHT. The obtained results indicate

that due to loss of image resolution; the circle configuration in many cases will

be lost, resulting in misdetection and reduction of accuracy in comparison to the

CHT process.

Another approach suggested for Iris and Pupil detection is using a Wavelet

Analysis to base a Minimum Variance method in order to detect the Pupil bound-

ary and the brightness gradient method to detect the Iris boundary. This approach

has been suggested by Shen et.al. [94, 101]. The Minimum Variance method in-

creases the speed of detection while the gradient method enhances the precision

via restricting the search area. The processing time is faster and the results are

better than the CHT method.

The use of Fisher Linear Discriminant Analysis (FLDA) method and Principal

Component Analysis (PCA) method has been suggested by Haq et.al. for Iris and

Pupil localisation and normalisation for biometrics applications. The first step is

to use a threshold value to extract the darkest region, defined as a Pupil. The

calculated radius and center is then used to draw the Pupil boundary. Another

threshold value is then applied to the image in order to darken the areas associated

with the Iris and Pupil of the eye. Then the medial filter is applied multiple times

to the complement of this image. Using the Sobel edge filter and estimated radius

size of the Iris, the outer boundary of the Iris is then approximated. The features

are extracted using the FLDA and PCA. The suggested technique has a recognition

rate of 97% and has been suggested to be suitable for real time applications [102].

However, the methodology is an approximation of the boundaries and depending

on the chosen thresholds used in the process, it may or may not be suitable for all

images.

Non-circular localisation of the Pupil has also been studied by Basit et.al. In

this study, initially a point inside the Pupil is detected by using the decimation

algorithm. Once the point is determined, the centre of the Pupil is calculated using

its centroid. This is followed by determining its radius using the binary image of

the region. The exact pupil boundary was then discriminated by joining a sequence

points selected with maximum rate of change. The Iris boundary was circularly

approximated in this study using the intensity gradient in radial direction. The

results show high accuracy of up to 99.86% and 99.3% for Pupil boundary detection

46


and 99.6% and 99.21% for Iris boundary detection [94].

Using the least significant bit plane the Iris pattern has been extracted by

Bonney et.al. [103]. In this case, the Pupil boundary has been detected by applying

the binary morphology to the bit plane. The least significant bit place, bit-plane

0, is used to determine the Pupil as it is quite homogenous and identifiable. For

the Iris boundary, the standard deviation along the vertical and horizontal axis

of the image intensity plot has been determined. Using the thresholded results,

multiple attempts are made in order to match the deviation vectors with the actual

Iris boundaries. About 10%-25% of the outcomes showed poor localisation. The

advantage of this technique over the other available processes is that there are

no requirements of the frontal view and it may be implemented on the off-angle

images.

Another study which considered the Pupil boundary detection was conducted

by Mehrabian et.al. [104]. The suggested Graph Cuts procedure uses the gray

level pixel values to determine the weights of the links to the graph. In this case

the Pupil is considered as the region of interest, while the remaining areas of the

image are considered as the background. The advantage of this technique over

the majority of the other approaches is that it may be used for off view angles

images. Although the procedure has high detection precision, the downfall of this

procedure is that a circular boundary has been used to outline the Pupil.

Intensity gradient values can also be used to detect the position of the Iris and

Pupil. Basit et.al. [105] have used this approach. In this case, the inner boundary

of the Iris is locates via determining the center and radius of Pupil. Firstly, moving

Average filter is used to determine a point inside of the Pupil. For binarization,

the maximum threshold value of the histogram is used. Finding the centroid of

the binary image defines the center of the Pupil. The average number of non-

zero pixels in any direction can then be used as the radius of the Pupil. Using

the center and radius, the Pupil boundary is then plotted. To determine the Iris

boundary, the image is first filtered using the Gaussian filter. To circle bands

are set, defining the region of interest such that the Iris boundary is in between

them. By determining points with the maximum gradients in this region, the Iris

boundary is then set. The proposed results are of very high accuracy of about 99%

for Iris localisation, with the processing time of about 0.3-0.4 second. However,

47


the obtained boundaries are assumed to have a circular shape and therefore cannot

be used for exact boundary detection.

Non-circular Assumption:

The use of pointwise level set algorithm has been suggested for precise localisa-

tion of the Iris. This method uses the stepwise deformation of the initial contour.

Using horizontal and vertical histogram of the image, the center of the Iris is cal-

culated ad is set as the initial point of the contour and its tracing. The iterative

algorithm of the contours starts from the Iris center going outwards. As long as

the variations between the gray levels are small it will continue, but as soon as

the variation becomes significant it stops. The number of iterations used for each

image in this study was about 25 with the processing time of about 2 seconds.

On average this process is quite robust, with success rate of greater than 95%.

There are no constraints in detection and therefore can be used to detect the Iris

in presence of eyelids and eyelashes. The main disadvantage of this process is that

it is sensitive to the rotation of the fundus image [106].

For detecting the Iris and Pupil, Masek et.al. proposed the use of CHT [107].

Firstly the edges have been detected using Canny edge detection. The gradients

from both vertical and horizontal direction have been determined, weighted and

used as thresholds for recognition of boundaries. By manually setting an approxi-

mate range for radii of the Iris and Pupil, then the boundaries have been detected

by applying Hough Transform. The accuracy of detection in this case was about

83%. This technique is quite robust. However, further improvements on the pro-

cess are needed, such as automating the estimation of the radii of Pupil and Iris

as well as improving the accuracy.

In order to localise the Pupil, Ritter et al. [108], suggested the use of active

contour models. In this case, the internal (desired characteristics) and external

(image characteristics) forces have been set and moved across the image, until

equilibrium has been reached creating the contour and locating the boundary of

the Pupil. For this case, the internal forces have to form an expanding discrete

circle from the center of Pupil, while the external force have been found using

variance of the image. Localisation of the boundary has been successful but further

refinement and calculations of the results were needed.

As it can be seen, majority of the proposed techniques in the literature have

48


assumed Iris and Pupil to be circularly shaped and localised the regions accord-

ingly. As part of this study, the author has looked into exact localisation of the

Iris and Pupil boundary. More details are provided in Chapter 6.

3.2.2.2 Retinal Vessel Detection

Localisation of the retinal vasculature has been one of the main areas of interest in

ophthalmology. This is mainly due to the fact that many of the ophthalmological

disorders affect the retinal vessels and its shape, such as the case of ROP which

was mentioned in Chapter 2. In this section, some of these approaches have been

discussed in more details, including the use of different filters, Matched Filters and

Wavelet Analysis techniques.

A study performed by Chanwimaluan et.al. [109] has used the Matched Filters

(MF) to enhance the blood vessels by detecting piecewise linear segments. For

each image, more than twelve 16 by 15 pixel kernels are convoluted to the image

in order to maximise the response. This has then been followed by a local Entropy

based thresholding procedure to detect and segment the spatial structure of the

vessels using the co-occurrence matrix. Lastly the Length filtering has been imple-

mented to remove the misplaced pixels and connect the discontinued vessels. The

detection has been successful; however there is still need for further improvements

for robustness of the procedure as well as the removal of additional lesions which

cause misdetection in the results.

Rahebi et.al. [110] has proposed the use of Gabor filter on a Threshold MF

images in order to classify each pixel as a vessel and non-vessel. The authors

applied a threshold value to the MF response of images and then adjusted the

threshold using the response from the Gabor filter which is a Gaussian kernel

shaded by a sinusoidal sheet wave. The obtained results had a reasonable accuracy

of about 93.80-94.82%.

One has suggested the use of zero mean GMF with First Order Derivative

Gaussian (FDOG), proposing a method called MF-FDOG. The vessels are first

detected using threshold response from the GMF. The results are then modified

based on the response of the FDOG. This approach has improved the process-

ing time by reducing the computational complexity. However, the accuracy of

49


the results is about 93.82% with 10 seconds processing time. The accuracy and

sensitivity of the process may further improve by further investigations in noise

removal [111].

Three different Template Matching Algorithms have been used to compare the

detection of vessels in the study performed by Banumathi et.al. [112]. The Gaus-

sian Matched Filter (GMF), Binary Matched Filter (BMF) and Kirsch Template

Matched Filter (KMF) have been applied. For each case about 8-12 minimum

number of templates were used. For processing the GMF and KMF required more

memory. The results indicate that BMF provided better results for detection of

small vessels and capillaries, while KMF process could have been performed to

both gray level and coloured images. The processing time of the GMF, BMF and

KMF were 20 minutes, 4 minutes and 1.5 minutes respectively. Furthermore, in

the GMF and BMF processes, more noise was removed in comparison to the KMF

process. Since the processing time is quite long and the obtained results are quite

noisy, it can be said that the MF approach may not be a suitable process for fast

vasculature detection.

Canny filters have been used to detect the edges of the vessels in the study

performed by Fiorin et.al. [113]. In this study, the centreline of the vessels has

been manually selected. After image enhancement with the use of Canny filters

the vessels edges were extracted and vessels tortuosity calculated. To reduce the

processing time, pixels which belong to the vessels or their neighbouring vessels

were detected in order to decrease the region of interest. Despite the success in

calculating the tortuosity of the vessels, since this process was semi-automatic

and the location of vessels were somewhat selected at the beginning, the obtained

results cannot be compared with the other techniques.

Another simple, fast and sensitive algorithm in the literature has been sug-

gested by Zhang et.al. [114]. The authors have proposed the use of directional

local contrast as the vessel detection feature. In this case, the blood vessel shape

kernel is set as a vessel. Each pixel is analysed using the Weber contrast mea-

sure in all directions. The pixel is then defined as a vessel of background. This

process is continued for small vessels adjusting the parameters of the blood vessel

shape kernel. The processing time is about 5-7 seconds, with the true positive

rate of about 82%. Despite the fact that this procedure has high sensitivity, it is

50


not robust and would require high quality images which may not be feasible in

developing regions or rural areas.

An automated process for vasculature detection has been proposed by Siddalin-

gaswamy et.al. [115]. In the proposed hybrid methodology, the blood vessels have

been enhanced while the background has been supressed using Gabor filter. The

vessels have then been segmented using the Entropic Thresholding. The obtained

results appear to have successfully located the retinal vessels with the sensitiv-

ity of 79%-91% and specificity of 94%-98% with a processing time of 20 seconds.

This suggests that the results are promising, however in comparison to the other

techniques the process may further improve by reduction in processing time and

increase in accuracy.

The use of Wavelets has been another approach in detection of blood vessels.

Bankhead et.al [116] have used the Isotropic Undecimated Wavelet Transform

(IUWT) to outline the blood vessels. Coefficients less than the set threshold of

20% for each wavelet level are set as vessels. Based on grain sized, the noises are

removed. To improve the precision of detection, a thinning algorithm is used. The

image profiles have then been perpendicularly computed across the spline fit of

each of the detected vessels centerlines. The accuracy of this procedure has been

about 93.71% with a processing time of 9-25 seconds. A limitation of this study

is that with decrease in contrast, the appropriate crossing may not be found in

order to detect the edges of the vessels and therefore affecting the accuracy of

the procedure. The use of interpolation was suggested but no further results were

included in this case.

In another study performed by Selvath et.al., the Curvelet Transform (CT) has

been used as an efficient edge detection methodology. Using the combination of

the CT and Support Vector Mechanism (SVM), the pixels have been segmented

as vessels and non-vessels. The authors have enhanced the retinal images using

the CT which is more efficient than the Wavelet Transform. CT occurs when the

Fourier space is divided into concentric circle and then into wedges which captures

the structural activity. Once the images are enhanced, the features are extracted

and segmented using the SVM and Radial Basis Function kernel. It is a pixel based

classification technique which finds the hyper-planes with maximum separation

between the decision function vector and the support vector. The results indicate

51


better segmentation with enhancement of images. However, the accuracy of this

procedure is not quite high and varies between 78.59%-91.13%. For more accurate

vascular localisation this method may not be sufficient and so further investigation

has to be performed [117].

Combining the Adaptive Local Thresholding (ALT), CT and SVM concept has

been the basis of another study conducted by Xu et.al. [118]. The ALT has been

applied to produce a binary image which has then been used to normalise the

image. The grain sizes less than 100 in this case are considered as noise and are

removed. This process has outlined the location of large vessels. Similar to the

previous technique, the smaller vessels where then segmented by CT and classified

by SVM. In this case the computational complexity is reduced. The accuracy

of this procedure is about 93.2% and sensitivity of 77.60%. The process has a

reasonable sensitivity, however further improvements is needed to improve the

accuracy especially in the pre-processing stage as it had inflated the width of the

large vessels.

From the above literature discussing the retinal vasculature localisation, it can

be concluded that majority of the approaches consider edge detection procedures.

Therefore, in order to help in diagnosis and treatment of diseases such as ROP,

in Chapter 7, multiple commonly used edge detection filters have been examined

and compared for vessel localisation.

3.2.2.3 Optic Disck and Macula Localisation

As mentioned in Chapter 2, other main key features of retinal images which may

be used for disease diagnosis are OD and Macula.

Optic Disk:

Over the years, there have been many different approaches and investigations,

aiming to locate the OD and extract its features. Some of them have been discussed

in more details in this section.

Localisation of OD Center:

The use of Histogram Matching for center localisation of the OD has been sug-

gested by Dehghani et.al. [119]. The authors of this paper have found the average

histogram of each colour component of the image, in order to create a template

52


for locating the OD center. The obtained results display high accuracy for center

localisation of the OD, 91.36%-10% for different databases. The processing time

for a single image is about 27.6-32.5 seconds. The objective of this study was to

locate the OD center and use that in the future studies for locating the OD bound-

ary. Therefore, further investigation is still needed to detect the OD boundary and

improve the accuracy of the results due to high number of misdetections.

Sekhar et al. [120] used clustering and histogram technique to detect the geo-

metric shape of the OD. In the initial step, the brightest pixels in the image have

been clustered together. Three windows for pixel selection have been formed, max-

imum difference, maximum variance and highest gray level value after Gaussian

low pass filtering. The histograms for the images associated with these windows

were then found. Using that, the location of the OD has been defined by selecting

the image with the largest number of brightest pixels. The OD localisation using

this technique has an accuracy of 99.5% and the best results were obtained for

images without dilation. This methodology only looked into approximating the

location of the OD and did not define its boundary.

Youssif et al. [121] proposed the use of directional pattern of the retinal blood

vessel to localise the OD center. The retinal region of the images were masked and

adjusted for illumination and intensity. Vessels direction map was then obtained

using a simple two dimensional GMF. With the aid of resized GMF, the difference

between the vessels direction and the MF was measured. The estimated centre

was then determined, as the point of the minimum difference. The OD center

detection using this technique had a very high accuracy of about 98.77%-100% for

different databases. However this technique is quite time consuming, taking about

3.5 minutes to detect the center. Moreover, using this technique only the center

of the OD is found and its boundary was not defined.

OD Boundary Using Vessels Location:

An automatic OD localisation approach, suggested by Mendoca et.al. has

combined the vascular and the intensity information [122]. By choosing the high

intensity regions in the calculated entropy of the obtained vascular directions, the

OD and its center have been localised. The method is of very high accuracy as

the obtained results indicate between 98.8-100% success rates. Despite the high

precision, since the vessels are localised first this method can take up to 90 seconds

53


to process a single image. Therefore, it may not be of interest in cases where fast

processing time is essential.

Two different methods were suggested by Zhu and Rangayyan et al. [123, 124].

The first one is to use the Sobel filter and CHT for localising the OD bound-

ary [123]. Using Sobel filters the edges have been found in the images. A threshold

value was used to normalise the image. CHT has been applied to detect the cir-

cular region of the OD and approximate its center and radius. The process had a

success rate of about 90%-95% which suggests the need for further improvement.

Moreover, since the edge detection was the preliminary process, other filters may

also be investigated in order to improve the accuracy of detection.

The second study considered the use of Gabor filters and phase portrait analysis

to detect peaks in the node map [124]. Similar to the previous method the edges

have been detected using filters, however in this case the Gabor filter was used.

Using phase portrait analysis and intensity based condition; the peaks in the node

map have been checked and selected is they were part of the OD.and used to define

the OD boundary. The accuracy of detection in this case was about 88.9%-100

Welfer et.al. [125] proposed the use of a mathematical Morphology Model for

detecting the vascular structure. Using this, several marker points are chosen

and by implementing the watershed transform, OD boundary is detected. The

success rate of this study was about 97.75%-100%. However, this model was also

computationally complex and time consuming.

Direct OD Boundary Detection:

The use of Hybrid Level Set Model and Template Matching has been suggested

by Yu et.al. [126] in order to obtain regional information and local edge vector

for localisation of the OD. The OD size is initially estimated and the image is

normalised. With the use of TM and Directional MF, the OD is then localised.

To segment the OD, the location of the OD and its estimated size is the used in

the red channel of the original image to check the saturation level. Using this, the

blood vessels are then removed. The Hybrid Level Set Model and the Least Square

Ellipse Fitting is used to detect the segment the OD. The overall processing time

of the proposed technique is about 6.6 seconds, with a very high success rate of

99% for OD localisation. Using this technique, errors in detection may occur in

cases where brighter regions such as advance retinopathy are present in the image.

54


The accuracy detection may also be reduced in special cases where the OD size

varies to the estimated size at the initial step of processing.

Joshi et al. [127] enhanced the previous work conducted by Chan-Vese [128],

using region-based active contour model to segment the OD, while incorporating

information from multiple image feature channels.

Esmaeili et al. [129] proposed the use of Digital Curvelet Transform and thresh-

olding on retinal images to estimate the location of OD. As a secondary analysis

for smaller sized ODs, Canny edge detector is suggested for locating the disc. This

method is computationally complicated.

Macula:

In comparison to the Iris and Pupil, retinal vessels and OD, not many studies

in the literature have considered or localised the Macula. A few of the proposed

procedures from the literature have been discussed further in this section.

Superpixel-based approach has been used by Wong et.al. to locate the center of

the Macula [130]. Using the suggested approach, the Maculas center was detected

with the average error of 30pixels.

Another approach has been to locate Macula based on the distance and position

of the OD [131]. It has been suggested that the Macula is located about 2 disc

diameter (DD) temporal to the OD. The mean angle to the horizontal between the

Macula and the center of the OD varies between -2.3 to -8.9 degrees. Using this

information, the location of the OD has been approximated with a sensitivity of

about 96.6%. Since the retinal features of each individual person varies to another

person, and more over the specifications of each image varies to the next, this

method may not be robust enough to accurately locate Macula for wide range of

images. It also does not work in cases where the OD has not been localised and

Macula is the only feature of interest.

Considering the literature and the importance of OD and Macula localisation

for disease diagnosis, this study considers other approaches for detecting these

features. In-depth discussion of the proposed techniques and the associated results

are discussed in Chapter 8.

55


3.3 Study Design Considerations

Thus far, the literature on image processing techniques for detection of different

ophthalmological features has been discussed. In order to achieve the objectives

of this research, meaning revising image processing procedures and introducing

new techniques to assist medical practitioners in their diagnosis, it is important

to consider several factors covered in this section, as part of the study design

consideration.

To design any system it is important to have a realistic vision of its possibilities

and restrictions. For the case of an automatic diagnostic tool for ophthalmology,

several variables which have been considered are mainly influenced by the location

of the use and the experience of the medical practitioner. These factors include:

• Device, its specifications and functionality

• Person who is capturing the images, whether it is an ophthalmologist or a

trained technician

• Number of images being captured

• Image specification and the conditions under which the images are being

captured under

• Patients collaboration

The above points are only some of the factors which may have influenced

the captured images and therefore have had a direct impact on the final results

obtained from the image processing procedures in this case.

3.3.1 Examination versus Screening

As part of the design consideration, one has to decide on the purpose of the

intended function of the device. Medical devices have been used in all aspects

of ophthalmology. Two aspects are usually considered for automated diagnostic

tools. The first one is to use the device for examining the possible patients and the

56


other is to screen and refer the patients to the medical experts for further diagnosis

and treatment.

For a complete diagnostic tool for screening the patients, a significant amount

of information and experts input is required. Additionally, many other unexpected

factors or complications such as rare diseases may also influence this system by

making it more difficult to achieve.

Since in this study, a broad range of features have been considered, the best

function for this automatic diagnostic tool would be to examine the patients and

provide the information to the ophthalmologists for further screening, diagnosis

and treatment.

Figure 3.3 illustrates the overall view of the proposed assistive diagnostic tool.

As it can be seen in the figure, the technician uses the fundus camera to capture

the retinal images from the patients. The suggested image processing procedures

and modifications in this thesis can be then implemented and performed as part

of the telemedical tool, on site in the preliminary image processing section. The

data can then be transferred directly or online for further examination. The final

results can then be provided to the ophthalmologist so that the diagnosis could be

made.

Figure 3.3: Suggested Image Processing stages.

While considering the ethical aspects, the stored data from this process can also

be used for future studies, monitoring the patients and creating a large database for

disease diagnosis. This can be the first step towards a single automatic diagnostic

57


tool for all ophthalmological diseases.

3.3.2 Cost Effectiveness

The need for automatic diagnostic tool has become apparent with an increased

number of patients but limited number of medical experts. Additionally, objective

analysis of diseases and complications are now of more interest.

Despite the great need and interest in this system, one of the major drawbacks

of this is its associated costs. The directions of recent studies have been to reduce

these costs. Majority of the current technologies still rely on advanced image cap-

turing devices in their diagnostic tools. These devices are expensive and acquiring

it in remote locations are very difficult.

To avoid this issue, in this study, the basic retinal images obtained from fundus

cameras have been used for further processing. This technology is available in

majority of countries and does not require any further purchases.

3.3.3 Image Quality

As mentioned in the design consideration section, there are several factors which

influence the quality of images. Image capturing is the initial and main step in

any image processing procedure, as it directly affects the whole process.

High quality images can result in more accurate and clearer feature detection.

Once the features have been localised, the extraction of the information can also

be more easily performed. The precision of detection is greatly improved by high

quality images. However, high quality images need more storage facilities, which

may not be feasible or justified in many occasions.

For example, large numbers of patients are usually monitored in rural areas and

so if all the data has to be stored and backed up, large quantity of storage facilities

would be needed, which in turn could result in higher expenses and longer process-

ing times. Some might suggest the use of advancements in wireless transmission

of the information to another location. This may be feasible in developed nations,

but in remote locations and the developing regions, the costs of the equipment

are high while the accessibility to them is limited. As a result, the best way to

compensate for this problem is using images with a reasonable quality.

58


Additionally, the diagnostic tool should be set such that at any given instance,

large quantities of images could be inputted, automatically detected and their

results stored for further review and examination of the patients.

3.3.4 Accuracy

Accuracy comes at a price. Majority of the performed procedures in the literature

can locate the Region of Interest (ROI) with very high precision. However, the

downfall is that they are computationally complicated and very time consuming.

Consequently, it is important to consider the extent for which this accuracy is

needed when it comes to designing an automated diagnostic tool. The required

precision is relevant to the image processing procedures, equipment and resources,

image quality and patient examination time. For example, in the initial examina-

tion where all the key features of the retina are to be considered and examined,

the processing time for each feature has to be shorter, which reduces the accuracy

of the detection. This might not be the case for the consecutive examinations,

where a certain feature at risk is critically examined.

Considering the limitations, the accuracy needed for detection varies. In this

study simpler image processing approaches have been proposed so that they are

less computationally difficult, with faster processing time.

3.3.5 Reliability

All the systems have to be reliable, meaning that they should perform and function

to the expected level at all times. Since the information and the results provided by

the assistive tool is the basis of the ophthalmologists’ judgements, it is important

for the system to be reliable.

The automated diagnostic tool should also be reliable in a sense that it would

perform in a similar manner under the same conditions. For a highly reliable

system, the overall result should not alter for similar specifications and conditions.

It should also be compatible with other available devices, suggesting that given

another input image using a different capturing device, the automatic assistive

tool would be able to provide a reasonable response with minor variations to the

accuracy of the final outcome.

59


For the case of this research, the suggested and implemented procedures have

been chosen such that they provide a reasonable and reliable result for different

images and specifications.

3.3.6 Safety

One of the key factors considered when designing a medical device is safety. Pa-

tients and users safety are substantially important in this field.

Majority of the population would prefer procedures which are non-invasive.

The reason being is that there would minimal to no side effects and the recovery

time would be quite fast as well.

In the case of the automatic diagnostic tool, no direct treatment on the patient

is being performed. Therefore, there are no safety concerns in that regard. How-

ever, this system would be using images to perform its tasks. Some of the available

capturing technology may have some side effects which might cause concern for

the patients.

All the diagnosis and further treatment has to be suggested by expert medical

practitioners in this case. Therefore, the suggestive assistive tool is very safe.

3.4 Summary

In the continuous of Chapter 2, this chapter reviewed different image processing

approaches for detection of the key features of interest of the eye. The main

features of interest included the Iris, Pupil, retinal vessels, OD and Macula. Several

current available procedures for detection of these features were considered and

investigated. The advantages and disadvantages of each were studied and outlined

in this chapter.

Several study design considerations were also considered, including the impor-

tance of the study, its cost effectiveness, image quality, and accuracy of detection,

reliability and safety of the suggested procedures.

Furthermore, the general steps in image processing were also discussed as part

of Figure 3.2. The remaining chapters of this thesis use this outline for further

investigation and improvements to the available methodologies.

60

CHAPTER 4

IMAGE ACQUISITION AND FUNDUS MAPPING

Introduction Literature Review Thesis Outline Conclusion

Image Acquisition Image Pre-Processing

Image

Fundus Mapping Refraction Study

Feature Localisation Feature Extraction

Figure 4.1: Chapter Four Outline of Image Processing Stages

4.1 Overview

Improvements in the field of ophthalmology are indebted to advancements in im-

age capturing procedures and instrumentation. Previously, the visual inspection

of the eye was the only source for disease detection and treatment. However, en-

hancements in imaging and its processing significantly changed these traditional

approaches.

61

4. IMAGE ACQUISITION AND FUNDUS MAPPING

Implementing image processing procedures would require images and data.

The data is obtained through the ophthalmological image capturing devices. Each

device would have certain capabilities and restrictions, resulting in variety of dif-

ferent outputs. Therefore, depending on the disease of interest, the availability of

resources and technical knowledge, the required device could vary. Detail under-

standing of the disease and its characteristics can aid in choosing the device which

can provide the expected outcomes.

Moreover, majority of the times the raw data would not be sufficient for prog-

nosis of the disease. As a result further processing would be required at this stage

including the image mapping and the analysis of the associated errors in captured

images in comparison to the actual feature.

One of the processes which may be implemented to enhance the Field Of View

(FOV) of the results is the retinal fundus mapping. Fundus mapping is when

using a single instrument, multiple images are obtained and combined to create

a wider view range, which in turn could be used for better diagnosis of diseases.

As parts of this chapter, an improvement to the readily available fundus mapping

techniques is introduced.

Furthermore, it was noted that in majority of retinal images captured, the

study of light and its refractions through different matters have been ignored.

Although the variation in the light refraction between each matter is very small

but it is crucial to be investigated for each case, in order to determine the accuracy

of the captured image, disease diagnosis and also treatment. This is due to the

fact that each section of the human eye has its own refractive index and so this

affects how the light passing through these regions would bend. These indices

would also vary between individuals and the results can be obtained in the initial

patient monitoring. Using this initial information, the variation between the actual

location of the region of the eye and the image can then be defined.

In this chapter, the preliminary stage of image acquisition, fundus mapping and

studying the errors associated with images using the light refraction are considered.

The requirements for image capturing and preparation for further manipulation is

considered such that the optimum information could be extracted from the data.

62


4.2 Image Acquisition

The foremost step in image processing is image acquisition. The intended purpose

of this step is to obtain the best possible data required by the specification of the

study. Therefore, prior to image capturing it is essential to investigate the overall

objective of the project and the desired specifications.

The objective of this study has been to introduce new image processing ap-

proaches on a readily available data sources. However, in order to distinguish and

characterise the findings it is important to have a sound knowledge about all the

stages of image processing. Therefore, in this section, the factors which have been

considered for acquiring a capturing device are discussed in more details.

There are few factors to consider prior to image capturing. The main factors

would be the available resources, funding and specialisation. Depending on the

disease characterisation, image requirements can be set, one of which could be

specifying the wavelength of interest from the electromagnetic spectrum.

In majority of cases where high precision is of interest, it is essential to ob-

tain images which would be of the highest possible quality, with good resolution.

However, in such cases the processing time of further stages of feature detection

and analysis may take longer. Higher resolution of images means more data to

analyse, hence slower processing time. As a result it is also important to consider

the processing time.

Other factors which may be considered prior to choosing the device [132] for

imaging include:

• Devices of interest

• Required resolution

• Speed of capturing

• Field of View (FOV) of the device

• Required lighting and ambient light

• Hardware processors

• Image Processing capabilities

63


• Desired software package for image processing

It is also important to be aware of the device capabilities and restrictions so

that the best data maybe captured. Once the device is chosen, the images may

then be captured.

If the obtained data is in the form of video recording, certain frames maybe

selected as images with the use of a frame grabber. The frame grabber device

can capture, store and transmit images via interfacing and synchronising with a

camera [133]. The obtained images are then used for further analysis and manip-

ulations.

Figure 4.2, demonstrates a desktop setting for image capturing. The capturing

device is used to take recordings of the required object. The information is trans-

ferred to the hardware processor. Depending on the requirements of the study and

the set specifications of the device, the hardware processor can perform preliminary

modification and storage of data, which can then be transferred or transmitted to

the image processor. Majority of the image processing occurs at this point and

the results can then be displayed on the monitor.

Figure 4.2: Image capturing set up

In this study, the most important factor is obtaining fast image processing

response, post capturing of the data and irrespective of the device specifications.

However, the processing procedure should be compatible and implementable to

64


any given image. To check the validity of this assumption, open source data are

used instead of collecting high resolution images.

4.2.1 Filters

To enhance the images, they are usually filtered. This filtration may occur using

the capturing device (Hardware filtering) or after the image has been obtained

(Software filtering).

4.2.1.1 Hardware Filtering

Usually, there are noises associated with image capturing. This is mainly due to

the slight movements of the patient and specifically their eyes. To reduce this

noise, hardware processor implements hardware filters.

Moreover, depending on the desired bandwidth of interest in the electromag-

netic spectrum certain wavelengths may be required to be removed which is achiev-

able via implementing hardware filters. An example of which is shown in Fig-

ure 4.3.

Another common hardware filtering is the illumination compensations. Since

the obtained images are not captured in an ideal environment, the ambient lighting

may affect the images and change the contrast. To minimise this affect, the lighting

may need to adapt accordingly. Therefore it is essential to consider and study the

light source prior to image capturing.

Figure 4.3: Capturing device, (1) Camera, (2) Lighting, (3) Hardware light filter

65


Some of the factors which have to be considered while choosing a light source [132]

include:

• Type of the light source

• Intensity of the light source

• Direction of the light

• Angle of the light

• Location of the light source

• Distance from the object

• Surface of the eye

• Structure of the eye

Once the factors have been taken into the consideration the selected image

capturing device maybe used for acquiring the images.

4.2.1.2 Software Filtering

Once the images have been acquired, further filtering may be used to minimise

noises. In the literature, many different filtering techniques have been introduced

and investigated, each having specific advantages and disadvantages in comparison

to others. In upcoming Section 5.4, a few of such methodologies have been selected

and investigated further .

4.2.2 Image Databases

Once the device is chosen it may then be used to capture the desired images.

The objective of this study has been to investigate different image processing

approaches in identifying key features of the eye in order to aid ophthalmologists

in the prognosis process of diseases. Therefore the desired images have been taken

from the human eye and its retina.

66


When considering live subjects, factors such as the number of subjects, privacy

of patients, invasiveness of the procedure and most importantly obtaining the eth-

ical approval for research purposes has to be taken under consideration. Majority

of the captured images in clinics and hospitals do not have the ethical approval

and cannot be used in the study.

To avoid this problem, open source online databases have been suggested to be

used. Since the databases were collected for research purposes, the ethical process

has already been conducted. Another advantage of these databases is that it can

be used to test the compatibility of the image processing procedures on different

images with different settings.

Many databases have been investigated, including:

• Methods to Evaluate Segmentation and Indexing techniques in the field of

Retinal Ophthalmology (MESSIDOR) [134]

• Retinal Vessel Image set for Estimation of Widths (REVIEW) [135]

• Retinopathy Online Challenge (ROC) [136]

• Collection of Multispectral Images of the Fundus (CMIF) [137]

• UPOL Iris Image Database (UPOL) [138]

• Digital Retinal Images for Vessel Extraction (DRIVE) [139]

• Structured Analysis of the Retina (STARE) [140, 141]

The specifications for the above databases are discussed below.

The 1200 colour fundus images in the MESSIDOR database [134] were collected

across three ophthalmologic departments. The images were captured by 8 bits per

colour plane at 1440×960, 2240×1488 or 2304×1536 pixels using colour video

3CCD camera on Topcon TRC NW6 non-mydriatic retinograph with 45◦ FOV.

The Retinal Vessel Image set for estimation of width (REVIEW) [135] database

consists of four subsets, which are the High Resolution Image Set (HRIS), Vascular

Disease Image Set (VDIS), Central Light Reflex Image Set (CLRIS), and Kick

Point Image Set (KPIS). The 16 images are 1360×1024 to 3584×2438 pixels and

are manually marked for vessel segmentation by three observers.

67


The Retinopathy Online Challenge (ROC) [136] database comprises of 50 im-

ages from patients with diabetes and signs of microaneurysms and/or hemorrhages.

These images were acquired using the default resolution and settings of the Topcon

NW 100, NW 200 or Canon CR5-45NM cameras.

The Collection of multispectral images of the fundus (CMIF) [137] database

consists of 17 images from healthy patients which were captured using Zeiss RCM250

camera with 40◦ FOV.

Due to limitations in time, for the purpose of this study, out of the many widely

used publicly available databases, three of the most popular databases have been

considered to investigate the suggested methodologies.

The first one is the Digital Retinal Images for Vessel Extraction (DRIVE)

database [139]. These images have been collected by Staal et.al. The forty collected

images have been captured by Canon CR5 non-mydriatic 3CCD camera with 45◦

FOV. Each image is 8 bits per colour plane at 768×584 pixels. The diameter of

the circular FOV is approximately 540 pixels.

The second database is the Structured Analysis of the Retina (STARE) database [140,

141]. In 1975, Michael Goldbaum initiated the collection of this dataset. Roughly

it contains about four hundred fundus retinal images. The images were captured

by TopCon TRV-50 fundus camera with 35◦ FOV. Each image is 8 bits per colour

plane at 605×700 pixels.

The third database is the UPOL Iris database [138]. It contains 384 Iris images,

including both right and left eyes. The RGB images are 24 bits, 576×768 pixels.

They were captured by SONY DXC-950P 3CCD camera and scanned by TOPCON

TRC50IA optical device.

It should be noted that since the obtained results have already been captured

and stored, this study will only concentrate on the software analysis.

4.3 Fundus Mapping

As mentioned previously, different Fundus cameras have different specifications

and therefore produce different images with a wide range of visual fields. There

are three different types of cameras, including the normal angle, narrow angle, and

wide angle of view cameras.

68


The commonly used cameras which are considered to have normal angle of view

are 30◦. The features captured by these cameras are about 2.5 times larger than

their real life size [142].

The fundus cameras which magnify the images more than the normal angle of

view cameras are called narrow angle fundus cameras and have an angle of view

of 20◦ or less [142].

The new wide angle fundus cameras have the capability to capture wider retinal

images, rather than the traditional 30◦ angle fundus cameras. The FOV of these

cameras range from 45◦ to up to 140◦ FOV [142]. Nowadays, the use of such devices

has become quite popular as the wider FOV allows the ophthalmologist to detect

the diseases and the affected areas more accurately and so perform the treatments

earlier on, prior to disease progression. A disadvantage of this technology is that

the magnifying power of these cameras is less than the normal angle view cameras.

Moreover, this new technology is not accessible or price effective in remote ar-

eas or in many of the developing countries. Therefore a new approach has to be

developed to provide such information to the optometrists and the ophthalmolo-

gists.

Figure 4.4 illustrates the difference between the angles for each of the normal

angle (green), narrow angle (red) and wide angle (yellow) fundus cameras.

Figure 4.4: The difference between the view angle of normal angle, narrow angleand wide angle fundus cameras.

69


Fundus mapping is a more time consuming approach in comparison to the use

of wide angle of view cameras. However, the main advantage of this technique is

that the wide angle view is obtained using more magnified images, revealing more

details to the ophthalmologists. This in turn may improve the accuracy of disease

diagnosis and treatment despite.

Moreover, the availability and cost effectiveness of the normal angle of view

cameras make the fundus mapping more feasible and desirable especially in devel-

oping regions.

Since in both developing an developed countries the typically used cameras are

the normal angle of view, it is advised to use images from normal angle of view

cameras for further investigation. As it can be seen in Figure 4.5, using multiple

images and combining the results expands the field of view and be more useful

than just a single image when it comes to disease diagnosis.

Figure 4.5: Importance of fundus mapping

In this section, merging multiple images in order to obtain a wider view of the

retina from the typically used 30◦ fundus camera has been considered.

This would be quite different to those of the previously performed montage

models represented in the literature. In general, montage model is thought to be

a time consuming procedure and difficult to perfect. There seems to be problems

with presence of artefacts to the montage images.

70


To address these problems the following procedure has been suggested.

4.3.1 New Proposed Technique for Fundus Mapping

The objective of this section is to merge multiple fundus images together in order

to attain a wider FOV of the back of the eye. To do so, the geometric properties

or the eye is studied and the following method is introduced.

It is known that the back of the eye is curved; this property may be used to

introduce the following equations representing its horizontal curvature character-

istics. Moreover, in Figure 4.6 a geometric approximation of the retinal image is

illustrated.

Figure 4.6: Geometric representation of the proposed method for merging multipleretinal images. Radius of the Curve (R), Central Angle of the Curve (∆), CordLength (C), Tangent Length (T ), Middle Coordinate (M), External Distance (E)and the Middle (PM), Left (PL) and Right (PR) points can be viewed in theimage.

The Tangent Length, T , may be represented by the Equation 4.1. In this

equation, the Radius of the Curve is represented by R and the Central Angle of

the Curve in degrees (◦) is represented by ∆.

T = R× tan(

∆

2

)(4.1)

71


The External Distance, E, can be shown as:

E = R

(1

cos(

∆2

) − 1

)(4.2)

Moreover, the Cord Length, C, is:

C = 2Rsin

(∆

2

)(4.3)

The Middle Coordinate, M , can be defined as:

M = R

(1− cos

(∆

2

))(4.4)

Lastly, L, which is the Curve Length Distance between PM to the V ertex

(Right angle triangle to T and R) can be written as:

L =R∆π

180(4.5)

Since in capturing the fundus image, the device and its specifications are known,

the Central Angle of the Curve in degrees (∆) would also be known. For example,

for the Fundus camera with 30◦ FOV, the Central Angle of the Curve for each

image would be 60◦ based on the inscribed angle theorem.

As a result of this, the Cord Length, C, would also be constant for all the

captured images. This agrees with the observation that all the retinal images

obtained from the same device with same setting appear to have the same shape

and diameter. Therefore, calculating the diameter of the fundus images, would

define the Cord Length value.

Based on these, the Radius, R, may now be calculated by re-arranging the

Equation 4.3 and resulting in Equation 4.6.

C = 2Rsin

(∆

2

)R =

C

2sin(

∆2

) (4.6)

72


The equation found for the Radius, R, may now be substituted back into the

previously defined equation. Substituting Equation 4.6 into Equation 4.1 would

result in:

T = Rtan

(∆

2

)=C

2

(sec

(∆

2

))(4.7)

E, the External Distance, may now be defined by substituting Equation 4.6

back into the Equation 4.2:

E = R

(1

cos(

∆2

) − 1

)

=

((C

2sin(

∆2

)cos(

∆2

))−( C

2sin(

∆2

))) (4.8)

To simplify this further, the double angle formula may be used:

2sin(θ)cos(θ) = sin(2θ) −→ C

2sin(

∆2

)cos(

∆2

) =C

sin(∆)

Continuing on Equation 4.8, the External Distance, E, may now be:

E =

((C

sin(∆)

)−

(C

2sin(

∆2

)))

= C

(csc (∆)− 0.5csc

(∆

2

))(4.9)

Obtained result in Equation 4.6 can also be substituted into the Equation 4.4,

resulting in:

73


M = R

(1− cos

(∆

2

))=C

2

((csc

(∆

2

))−(cot

(∆

2

)))(4.10)

Similarly, substituting the obtained result in Equation 4.6 into the Equa-

tion 4.5, would now result in:

L =R∆π

180

=C∆π

360sin(

∆2

) (4.11)

From this it can be said that, all the required properties for approximating the

retinal horizontal curvature can now be calculated.

It is now time to merge multiple of these images, increasing the FOV. To merge

multiple images, it is best to have some overlapping regions. The overlapping

regions ensure that the possible artefacts which may have been formed due to

inaccurate positioning in the result are reduced.

Figure 4.7: Approximation of retinal curvature using the Middle Coordinate

74


The number of markers can also be increased as the OD and macula can be

detected. Using these markers in conjunction with the normal vasculature mark-

ers, the fundus map can be created with higher accuracy. Moreover, using the

approximation of the retinal curvature found via considering the Radius and the

Middle Coordinate of the eye, a 3D effect can be given to the outcome. Figure 4.7

illustrates this concept.

4.3.2 Implementation and Discussion

In order to map the fundus, it is important to define markers on each image so

that they could be used to overlap the image.

The advantage of the proposed approach over the readily available method-

ologies is that in the suggested case, the number of the markers has increased by

inclusion of the location of other retinal features. In the previous techniques, the

markers have been usually set based on the localized vessels. However in this case,

in conjunction with the localized vessels, other key features of the retinal image

including the location of OD and macula have also been used as markers.

Increase in the number of markers ensures that the error in creating the fundus

map is decreased and the overall image does not contain any duplicate images,

reducing the unwanted artefacts.

Moreover, the overlapping region has to be present, so that the combination of

the images could be achieved. Without the overlapping region, the images cannot

be placed next to one another as their location and the direction may be unknown.

The greater the overlapping region improved the accuracy of the fundus map,

but it also increases the computational complexity, reduces the speed of mapping

and also increases the need for using more images to create the full view of the

fundus map.

Based on this, it can be said that if time permits, fundus mapping could be

applied and used in developing or regional areas where the available resources

are limited. The advantage of this approach is that with minimal information;

knowing the fundus camera angle and the cord length of the taken images; a

simple yet reliable process can be applied. Moreover, since the number of markers

has increased, naming the location of the retinal vessels, OD and Macula, the

75


accuracy of the fundus mapping has also increased.

4.4 Refraction Studies

In image acquisition and interpretation, the light characteristics and effects are

of great importance. In ophthalmological instrumentations, many different light

sources, settings and angles have been considered for capturing images. Based on

the results and the desired outcome, the best light characteristics has then been

chosen and applied to obtain images.

However, once the images have been captured, the effects of the light beams

on the accuracy of the results in the interpretation stage have not been considered

in many studies. It is essential to know more about the light characteristics when

analyzing the results as it directly affects the accuracy of the calculations as it is

one of the main variables. In this section, the light refraction and how it effects

the overall interpretation of results is reviewed and studied.

The light beams tend to refract when leaving a matter and entering another

matter with a different density values, which are commonly known as refractive

index values. Therefore, when studying the light, considering the light refraction

based on these refractive index values are crucial and many studies have missed

this in their interpretations.

Air

Eye

θ2

θ1

Equation 4.12 indicates the relation between the index value of the angle of

incidence and refraction when light passes through two different materials.

n1sin(θ1) = n2sin(θ2) (4.12)

76


Where n1 and n2 refer to the refractive index values of the materials where the

light leaves and enters respectively. θ1 is the angle of incidence of light and θ2 is

the angle which the refractive ray created with the normal.

When light enters a material with higher refractive index, the angle of refraction

will be smaller than those of the angle of incidence, and hence the light will be

refracted towards the normal of the surface. However, if the refractive index of the

material is smaller, the refractive angle will be larger and light will be refracted

away from the normal.

n1 > n2 −→ θ1 < θ2

n1 < n2 −→ θ1 > θ2

4.4.1 Light Refraction In Retina

Based on the studies conducted by Hecht et.al. [143], the internal components of

the eye each have their own refractive index, hence the angle in which the light

enters the eye will not be the same as those reaching the back of the eye. As a result,

studying and implementing refractive index should be taken into consideration

while capturing or studying images.

Figure 4.8: Average light refraction indices for different regions of an eye.

77


Using the Equation 4.12, the angle of refraction of the light as it passes through

each sections of the eye can then be calculated. The results can be viewed in

Table 4.1.

Table 4.1: Refractive Index of the light passing through different regions of theeye.

N1 1

N2 1.376

N3 1.336

N4 1.406

N5 1.337

N1N2

0.726744186N2N3

1.02994012N3N4

0.950213371N4N5

1.051608078

All 0.747943156

Using the results from Table 4.1 in the Appendix, the comparison between the

calculated angle of the refraction and the expected incident ray over 180◦ and 90◦

has been plotted and can be viewed in Figures 4.9 and 4.10 respectively.

Figure 4.9: Comparison of incident ray and refractive ray - 180 degrees

78


Figure 4.10: Comparison of incident ray and refractive ray - 90 degrees

Figure 4.11 is an example of how the incident ray enters the eye and the refrac-

tive ray reaches the back of the retina. As a result of the difference in refractive

indices for each region of the eye, the bending of the ray is visible. The differ-

ence between the actual location of the ray and the expected location can also be

viewed.

Figure 4.11: Example of bending of the refractive ray in the eye

79


The graphs clearly show that there is a significant difference between the inci-

dent ray angle and the refractive ray angle. This may suggest that the expected

location of ray will differ from the actual location of the ray reaching the back of

the eye.

In order to statistically determine the significance of the results obtained for

the refractive ray in comparison to those from the incident ray, in this section the

Analysis of Variance (ANOVA) has been performed and shown in Table 4.2.

Table 4.2: ANOVA of the incident and refractive rays for 0-90◦ range

Summary

Groups Count Sum Average Variance

Incident Ray 19 855 45 791.6666667

Refractive Ray 19 554.3631598 29.17700841 261.1563218

ANOVA

Source of Variation SS df MS F-value P-value F-crit

Between Groups 2378.497 1 2378.487 4.518 0.040 4.113

Within Groups 18950.814 36 526.411

Total 21329.301 37

In the Table 4.2, for each group of results, incident ray and refractive ray

over the range of 0-90 degrees, the number of variables (count), their overall sum,

average and variance have been calculated and displayed in the summary section.

Moreover, for comparing the results using ANOVA, the Sum of Squares (SS),

Degrees of Freedom (df), Mean Squares (MS), the calculated F-value, P-value and

critical F-value (F-crit) have also been calculated and presented in the ANOVA

section.

The p-values are commonly used to determine whether the null hypothesis

could be accepted and rejected. The null hypothesis in this case is that there is

no significant difference between the incident ray and the refractive ray and the

study is to prove whether that is true or not. Depending on the p-value this could

80


be achieved.

P-values could mean:

• p ≤ 0.01 :very strong presumption against null hypothesis

• 0.01 < p ≤ 0.05 :strong presumption against null hypothesis

• 0.05 < p ≤ 0.1 :low presumption against null hypothesis

• p > 0.1 :no presumption against the null hypothesis

Based on the results illustrated in Table 4.2, the p-value is 0.040 which is less

than 0.05 but greater than 0.01. This means that there is a strong presumption

against the null hypothesis of no statistical significance between the two data sets.

This means that the two sets are significantly different and so when analytically

studying the images, the refraction of the light and its effect should also be con-

sidered.

Furthermore, the Fisher’s test (F-test) has also been found. The statistical

F-test determines whether the F-distribution is true under the null hypothesis.

The following is the formula for the one-way ANOVA F-test statistic:

F − test =Explained Variance

Unexplained Variance(4.13)

Using the Equation 4.13, the F-value has been obtained and as shown in Fig-

ure 4.2, it can be seen that the F-value is 4.518, which is slightly greater than

the critical F-value of 4.113. This suggests that the results may be significant at

the 5% significance level. Therefore, the null hypothesis can be rejected, suggest-

ing that there is strong evidence that the expected values in the incident ray and

refractive ray differ. This agrees with the results found for P-value.

Based on the above observations and results, it can be concluded that there

is significant different between the angle of incident and those of the refractive

angles and as a result should be taken under consideration when analysing the

outcomes. This may be beneficial to surgeons in their diagnosis of diseases as the

approximate location of the retinal features could be more accurately calculated

and determined using the angle of incident.

81


4.5 Summary

In this chapter the preliminary step of image processing was considered. The

image acquisition, light refraction and improvements to the field of view using

fundus mapping were the main areas of interest in this section.

Different factors for device and light source selection were considered in order

to highlight their importance in image acquisition and its impact to the overall

outcomes of the project. After due consideration, the eye and fundus images

used in this case study were obtained from online sources, captured from wide

range of devices with different settings. The main sources were the DRIVE and

STARE databases. The images were chosen to test the flexibility of the suggested

methodologies and determine the accuracy of the obtained results.

Furthermore, the impact of fundus mapping and light refraction has been in-

vestigated. In the image capturing, the effect of light refraction is significant and

therefore has been carefully studied in this chapter. The results have shown that

there is a significant difference in the incident and refractive rays and therefore

the variation has to be considered in order to aid the medical practitioners by

detecting the actual location of the key features of the retina.

Diagnosis and treatments of the retinal diseases can also benefit from wider

view of the retina, using fundus mapping. The use of multiple images from nor-

mal 30◦ angle of view retinal fundus images have been considered to create the

retinal fundus map with the proposed approach. The accuracy mapping has been

increased by using multiple different markers, including the location of the vessels,

OD and macula.

82

CHAPTER 5

IMAGE PRE-PROCESSING



Implementation:

— Colour Separation

— Masking ROI

— Filtering/Noise Removal

— Image Sharpening

Further Modification:

— Contrast Enhancement

— Trimming

Feature Localisation Feature Extraction

Figure 5.1: Chapter Five Outline of Image Processing Stages

5.1 Overview

Improvements in the field of ophthalmology are indebted to advancements in im-

age capturing procedures and instrumentation. Previously, the visual inspection

83

5. IMAGE PRE-PROCESSING

of the eye was the only source for disease detection and treatment. However, en-

hancements in imaging and its processing significantly changed these traditional

approaches.

Implementing image processing procedures would require image and data. Ma-

jority of the times, the raw data would not be sufficient for prognosis of the dis-

ease. As a result further processing would be required. Image processing can

provide more information via analysing the outcome and detecting information

which might be missed by visual inspection. In order to do so, the image has to

be prepared and modified in the pre-processing stage.

In the pre-processing stage the acquired images are manipulated and noises

removed in order to enhance the speed of detection and results obtained in the

consecutive stages of feature detection and extraction.

Despite the rapid technological progression and knowledgebase understanding

of the eye structures and the underlying processes; in many regions especially

the developing countries, current resources may still not be available. On many

other occasions, the capturing devices may not produce high quality images or the

obtained images, maybe too noisy. Hence, it is important to filter images while

preserving critical information.

Consequently, the accuracy of the images and their readability may be affected,

further resulting in poor study of the patients’ health and imprecise disease de-

tection. It is of great importance to ensure that the readily available resources

and obtained results are well prepared for further prognosis by experts in the best

possible timely manner.

As a result, it can be said that the preliminary stage of image pre-processing

and modification plays an important role in disease detection. In this chapter, the

pre-processing stage has been considered.

The procedures include colour separation of the captured images, masking

the ROI, filtering and noise removal of the images and sharpening them. The

performed procedures ensure that the ROI is accurately detected and the overall

precision of detection is enhanced.

Furthermore, new modifications including the contrast enhancement and trim-

ming regions for ROI is also suggested. The trimming regions are defined so that

the errors associated with the localisation of the ROI, such as the OD is reduced.

84


Moreover, for betterment of the feature localisation, contrast enhancements are

suggested to be used.

5.2 Image Manipulation

Fundus retinal images captured are usually coloured images. Based on the work

conducted by Gonzales et.al. the coloured images are best to be converted into

either indexed or RGB (Red, Green and Blue) images [144, 145].

Gray scaled images have proven to reduce the complications and processing

time significantly. Therefore, the first step in image manipulation would be gray

scaling the RGB image. An example of such transition can be viewed in Figure 5.2,

part (a).

(a) Gray Scale (b) Red (c) Green (d) Blue

Figure 5.2: Colour band separation of a coloured image with respected histograms

The coloured image can also be separated in to its primary components of

85


the red, green and blue. The obtained results and their respected histograms are

displayed in Figure 5.2.

Figure 5.3: Colour component separation of RGB image in horizontal direction

Observing the results in Figure 5.2 and those in Figure 5.3, suggests that the

red channel of the RGB image is saturated, while the blue channel is empty.

Therefore, for the purpose of this study, the green channel is chosen for further

investigation.

This result agrees with the previous findings in the literature [115, 117, 146].

Similarly, Al-Rawi et.al. [147] conducted a study to determine the performance of

each of the colour bands in the DRIVE database by plotting the Receiver Oper-

ation Curve (roc) on an improved matched filter. The results indicated that the

average roc area for the red, green and blue bands were 0.9348, 0.9352 and 0.9339

respectively, once again suggesting that the green band is the most appropriate

channel for digital retinal imaging.

Based on this finding, all the coloured images in this study have been grey

scaled and their green channel have been chosen and used for further processing.

Some sample results are included as part of Appendix B.

5.3 Masking

After deciding on the channel of interest, which is the green channel of the image,

the region of interest (ROI) needs to be defined using a mask.

86


In retinal images, the main area of interest is surrounded by a black region.

Figure 5.4 illustrates a possible mask which could be used to define the ROI for

the sampled image. The white region in the mask is the ROI, while the black

region is the regions which are not of interest in the study.

(a) Image (b) Mask

Figure 5.4: Example of a possible mask for the sampled image

In the literature, there are many examples of how to mask the ROI. In many

studies, this mask is manually or automatically pre-defined and used for all images.

In other studies, methods such as the Otsu Method [148, 149] or Circular Hough

Transform [150] have been used to define the mask.

5.3.1 Otsu Method

Otsu method is based on the discriminate analysis and was first proposed by

Otsu in 1979 and since then was widely used in image processing applications.

Otsu method finds the optimal threshold in an image by thorough search of pixel

intensities for maximising the between class variances [148].

In the Otsu method, the image is separated into two classes of ”Object” and

”Background”, represented as C0 and C1 at the grey-level t.

C0 = {0, 1, 2, ..., t} C1 = {t+ 1, t+ 2, ..., L− 1}

Respectively, the within class variance 1, between class variance 2 and the total

variance are σ2W , σ2

B, σ2T . Based on the Otsu method, in order to find the optimum

1Within class variance is the weighted sum of the variances for each cluster.2Between class variance is the difference between the total and the within class variance.

87


threshold, one of the following functions with respect to t should be minimised

[149].

λ =σ2B

σ2W

η =σ2B

σ2T

κ =σ2T

σ2W

Since η is the simpllest of the three equations it is usually chosen and so the

optimal threshold is defined as:

t = ArgMin(η)

η =σ2B

σ2T

κ =σ2T

σ2W

Otsu method has been implemented and the results can be viewed in part (a)

of Figure 5.1.

5.3.2 New Technique for Masking Using Thresholding

In the study, a similar approach to the Otsu method is suggested and implemented.

Since fundus images are obtained using different devices with different settings, a

universal adaptive approach is needed, where the ROI could be defined for each

individual image, regardless of the capturing device settings. Since each device

setting is unique, for a universal automated process, the images obtained have

to be individually analysed and therefore each image would need to be masked

separately in order for its ROI to be defined.

The suggested method is an adaptive thresholding technique. It is quite fast,

reliable and easy to perform. The first step is to obtain the intensity of the image

and plot the histogram of the plane of interest, which in this case is the green

plane.

Studying the histogram closely reveals that there is a large peak at the lower

pixel intensities, which suggests presence of a significant dark region in the image.

Since the surrounding region is coloured black and the ROI is lighter, defining that

88


region and masking it would result in separation of the two regions.

To define the mask for the background region, a threshold is set where the

first major minimum occurs in the smoothed histogram. An example is shown in

Figure 5.5.

Figure 5.5: Histogram used to determine a threshold for masking the ROI

Once the threshold is set, all the pixel values in the image which have the pixel

intensities below the defined ROI is set to ”0”, and any values above it, is set to

”1”. The result is the creation of a binary mask, defining the ROI. The mask is

smoothed out by removing or filling up any noise which might appear as black

”holes” in the image.

An example of the proposed mask is shown in Table 5.1. In the figure, the re-

sults obtained using the proposed technique is compared with the results obtained

by implementing the Otsu method.

89


Table 5.1: Comparison of the masks formed by Otsu method and the suggestednew Thresholding method.

Technique Mask Masked Image

Otsu Method

New Thresholding Method

The comparison suggests that the proposed method is as accurate as the pre-

viously suggested Otsu technique. This approach has been implemented on more

than twenty images and the results indicate an accurate localisation of ROI for all

cases. The obtained masks have been included in the Appendix C.

Furthermore, in cases such as this one, where the two clusters are easily distin-

guishable, simpler yet reliable approach of thresholding is desirable. The suggested

approach is also faster and computationally less complicated in comparison to the

Otsu method as it only considers the occurrence of first major minimum instead

of calculating the minimised variances of different sections of the image. There-

fore the proposed technique can be used to define a mask for ROI as a universal

automated approach.

5.4 Filtering

Despite the presence of hardware filters, the obtained images are not ideal and

are still noisy. Therefore, it is essential to filter images and minimise noise prior

to any further processing. Since the used images are from open source databases

and so no further hardware filter may be implemented. Moreover, software filters

90


can be implemented on all images irrespective of the specifications of the image

capturing devices. Therefore, the study concentrated on software analysis of the

images and this section software filters have been applied and the details are as

follow.

5.4.1 2D Fast Fourier Transform

To enhance the processing time and reduction in computational complexity, the

2D Fast Fourier Transform (FFT) is suggested to be used as a filter. FFT is

computationally simpler because the filter is multiplied in frequency domain, while

in spatial domain it would have to be convoluted, therefore the FFT would result

in faster response time. It has been implemented and used as the basis of multiple

upcoming stages in this thesis.

FFT is an important tool in signal and image processing. In order to filter a

two dimensional image, it is best to convert the image to its frequency domain.

2D FFT is simply the FFT which has been applied to one direction followed by

the FFT implemented in another direction of the data. 2D FFT represents the

frequency spectrum in both dimensions, allowing filtering operations to be visually

studied.

To implement the 2D FFT, the following Equation 5.1 may be used:

F (u, v) =1

MN

M−1∑x=0

N−1∑y=0

f (x, y) e−j2π(uxM

+ vyN ) (5.1)

Similar to the 2D FFT, the inverse 2D FFT is simply Inverse FFT (IFFT) which

has been applied to both directions of the data. The Equation 5.2 represents the

2D IFFT:

f (x, y) =M−1∑u=0

N−1∑v=0

f (u, v) ej2π(uxM

+ vyN ) (5.2)

To better visualise the results obtained via implementing the 2D FFT, an

example is shown in Figure 5.6.

91


(a) Image (b) Magnitude Plot (c) Phase Plot

Figure 5.6: Implementing 2D FFT on a retinal image

Studying the magnitude plot of the obtained 2D FFT, reveals that most of

the energy is concentrated in the centre of the image. This corresponds with low

frequency data in the frequency domain, suggesting gradual changes in the image.

Moreover, in the result, there are no sharp lines away from the centre of FFT,

suggesting that there is no great energy in the higher frequencies.

The phase of the FFT is somewhat hard to interpret visually and generally looks

like noise. However, it holds a great deal of the information needed to reconstruct

the image. Therefore, including the phase plot in the results is essential as the

output of the research should not alter the original data and should have the

capability to reconstruct it if necessary.

The results obtained in this section are the preliminary stage of the processes

in the next Section and Section 7.1. Therefore, this process has been implemented

on over twenty different images and the results are included in Appendix D.

5.5 Sharpening the Retinal Image

There are times where certain features of the image need to be enhanced in order to

be detected. An example could be when the vessels in the retina are to be detected.

In such cases, it is advised to sharpen the image prior to feature localization. To

sharpen an image, the filtered image may be added to the original image. This

would result in highlighting the key features and emphasising on their edges.

In the study, to sharpen the image, the use of the 2D FFT and convoluting it

92


with a kernel of set value is suggested. It should be noted that for different image

sizes the kernel sizes may also vary based on the level of details required. For the

purpose of this study sSeveral different kernel sizes have been examined. In order

to observe the effect of the kernel, two kernels of 10×5 and 3×2 have been used

to compare their effects and the obtained results are displayed in Table 5.2. They

provided the best clarity in the results and observations of the studied images and

therefore were chosen to be implemented in the consecutive stages of the study as

well. The two kernels have been shown in Figure 5.7.

(a) 10×5 (b) 3×2

Figure 5.7: Used Kernels

Kernels are used to dilate the images. Dilation is a commutative process,

operating to grow or thicken and object in a binary image [144]. It can be used to

enhance a certain feature of the image. Opposite to dilation is erosion, in which

the object in the binary image shrinks or thins [144]. It may be used to remove

unwanted smaller objects, including the non-variable holes or dusts [144, 151]. It

should be noted that during both the erosion and dilation process, small cells,

noise and some details are lost, but the essential characteristics remains [151].

Comparing the outputs displayed in Table 5.2, it can be seen that the results

for the two suggested kernels slightly vary. The smaller kernel size, results in a

better sharpened image and so more details can be viewed in this case. On the

other hand, if larger details are of interest, the use of larger kernel size would be

more appropriate.

93


Table 5.2: Sharpening the retinal image using 2D FFT

10 × 5 kernel 3 × 2 kernel

Green Channel of Image

Magnitude Plot

Real Part of Spectrum

Imaginary Part of Spectrum

Filtered Image

Subtract Filtered Image from

Original Image

Inverse - Subtract Original Im-

age from Filtered Image

Moreover, the two kernel sizes which were selected and implemented were just

94


samples so that the effects of the variation in kernel size on the overall outcome

could be visualized. For different cases and capturing devices, this kernel size may

vary and so should be reset if necessary in order to provide the sharpest image

possible. This process has been implemented on all the images within the DRIVE

databas. The results are included in Appendix E and indicate similar outcomes

as the above discussion.

5.6 Trimming Regions

Many of the studies performed previously suggest that the outcomes from the

automated feature localisation stage are not 100% accurate. To overcome this

problem and enhance the results, in such cases the manual input from the user is

suggested to be used. The downfall of this would be that the outcome might vary

depending on the individuals with different experience levels. Moreover, in cases

where the expert opinion is not available the semi-automated system might not

provide the ideal result. In the study, for a fully automated detection process it

has been suggested to consider and resolve errors which result in the misdetection

of the feature of interest.

(a) (b)

Figure 5.8: Two examples of retinal fundus images. If observed closely, a brightfringe can be seen at the left hand corner of the image (b) which may result ininaccurate OD detection. The bright fringe cannot be seen in the image (a).

One of the common problems with obtained images is the unbalanced bright-

ness in the fringe of the rim, which is caused when the patients do not place their

95


eyes tightly against the capturing device. This leads to misdetection of the ROI,

which in this case is the OD.

In this study, 10% of the images with the database illustrated signs of fringe

noise presence.

To overcome this problem, study conducted by Zhang et.al. in 2010 [152]

has proved to be vital for system’s uniformities and accurate detection of ROI.

The authors introduced a pre-processing step, known as the fringe removal. They

proposed a trimming circle, where its center and radius were defined based on the

least-square fitting technique, previously suggested by Kasa [153].

The suggested trimming circle is represented by Equation 5.3, has its center

located at (Cx,Cy ) and its radius is shown in Equation 5.6. It should be noted that

in order to remove all the bright regions caused by ambient light, the estimated

radius is set to be smaller than the calculated radius [152].

X2 + Y 2 + (AX) + (BY ) + C = 0 (5.3)

Cx =−A2

(5.4)

Cy =−B2

(5.5)

r =

√A2 +B2

4− C(5.6)

Furthermore in this study, the OD region was considered to be the 0.5% of

the bright spots in the trimmed fundus image. The centroid of the region was

considered as the center. The ROI boundary was limited by considering a radius

twice those of the normal OD [152].

Implementing the circle on the image and then processing the fundus image to

detect the OD, resulted in successl rate of 96% detection. In the remaining cases,

the manual input of the user, was used to adjust the region of interest [152].

Since only 5% of the pixels has been considered as OD, this method may or may

not have the desired accuracy as different image intensity may reduce the precision

of localisation. Moreover, the OD was approximately determined by considering

96


a boundary twice hose of the normal OD. As a result, the chosen OD pixels may

not be correctly selected and so critical information may have been lost. Therefore

this study introduced a new methodology in localising the exact OD region, more

details have been provided in Chapter 8.

To further improve the accuracy of detection, in this study another circular

trimming region has also been suggested. Since not all fundus images appear to

be circular, the trimming region is further modified to provide the best possible

outcomes in such cases. More details are provided in section 5.6.2

5.6.1 Circular Trimming Region

As it can be seen the previously suggested technique was not ideal and there was

still a need for manual user input. To improve the results and the success rate of

detection, the previously proposed procedure has been re-examined and the new

approach suggested.

As it is known, a circle, centerd at (h, k) is represented by the equation:

(x− h)2 + (y − k)2 = r2 (5.7)

The result of expanding and rearranging this equation would be:

x2 + y2 − (2hx)− (2ky) + h2 + k2 = r2

x2 + y2 − (2hx)− (2ky) + h2 + k2 − r2 = 0 (5.8)

Comparing Equation 5.3 with that of Equation 5.8 suggests similarities between

the two, and hence equating them would provide:

X2 = x2 −→ X = x (5.9)

Y 2 = y2 −→ Y = y (5.10)

97


Now compare the third and fourth terms:

AX = −2hx

Based on Equation 5.9, it can be said that: X = x, therefore:

A = −2h −→ h =−A2

(5.11)

Moreover:

BY = −2ky

Based on Equation 5.10, it is known that: Y = y, therefore:

B = −2k −→ k =−B2

(5.12)

Comparing Equation 5.3 with the Equation 5.8 indicates that the constant

term is:

C = h2 + k2 − r2 (5.13)

Substituting Equations 5.11 and 5.12 into 5.13 and simplifying would result in:

C =

(−A2

)2

+

(−B2

)2

− r2

=A2

4+B2

4− r2 (5.14)

Using Equation 5.14, the variable r is made the subject:

r2 =A2 +B2

4− C

r =

√A2 +B2

4− C (5.15)

In Table 5.3, the suggested trimming region by Zhang et.al. and the suggested

trimming circle in the study is represented.

98


Comparing the two trimming regions, concludes that the location of the center

for both cases is the same and is represented by (h, k); however, as it can be seen

in Table 5.3 their radii are defined differently. Under the same conditions and

specifications, the calculated radius of the new proposed trimming technique is

smaller than those suggested by Zhang et.al.

It should be noted that similar to the previous technique, the radius of the

proposed trimming circle is also set to be smaller than the estimated radius. This

marginal variation in radius ensures that all the bright regions have been removed

from the image. The amount for the variation would depend on the number of

image pixels, general location of the OD in the image and its distance to the black

boundary.

Table 5.3: Comparison table of the proposed trimming circle with those suggestedpreviously in literature

Trimming region (Zhang et.al.) Proposed trimming circle

Equation X2 + Y 2 + AX +BY + C = 0 (x− h)2 + (y − k)2 = r2

CenterCx = −A

2

Cy = −B2

h = −A2−→ h = Cx

k = −B2−→ k = Cy

Radius r =√

A2+B2

4−C r =√

A2+B2

4− C

Therefore, when analyzing a new set of database, with different capturing set-

tings, it is suggested to visually observe a few of the retinal images so that if

required, the variation in radius could be changed for all the images within that

database.

99


5.6.1.1 Implementation

In order to implement the trimming region on wide range of databases and retinal

images with variety of resolutions and capturing settings, it is essential to create an

algorithm in which the required variables are detected for each individual image.

The key requirement in plotting the region is to locate its center. The steps

undertaken to determine the center of the analysed retinal images are as follow:

1. The first non-zero pixel is determined. The first pixel would be the one which

is not black and so is not part of the background black boundary. This would

represent the most left non-zero pixel in the retinal image.

2. Last non-zero pixel is then found. This would be the last pixel which is not

black and is located on the right hand side of the image.

3. To estimate the center, the horizontal and vertical pixel locations of the pin-

pointed pixels are used and the middle values are calculated and considered

as a preliminary location of the center.

4. Using the horizontal middle value found previously, the first and last non-zero

values in vertical directions are determined. These points would represent

the furthest top and bottom points where the pixel values are still non-zero.

5. Similarly, using the vertical middle value found in step 3, the first and last

non-zero values in horizontal directions are also determined.

6. Once the points are determined, their average values are taken, resulting in

the re-calculated center location of the trimming region. The final center

point can be seen as orange (+) sign on the images where the trimming

regions are plotted.

The other necessary value needed to plot the region, would be its radius. The

radius can easily be calculated using the difference between the number of pixels

from the center to any of the four previously founded points in the top, bottom,

left or right hand side.

100


Figure 5.9: Example of results obtained for plotting a trimming region. Thegreen (+) signs indicate the preliminary estimated points. The orange (+) signsindicate the calculated points, including the estimated center. The yellow circle isthe trimming region which has been plotted using the information.

Based on the above process and the obtained values for the radius and center

location, the trimming region may now be plotted as depicted in Figure 5.9. More-

over, since the above process is repeatable, it can be implemented on any given

RGB image, with any specifications.

5.6.1.2 Results and Discussion

The proposed circular trimming region has been implemented and results have

been displayed in this section. The first point to consider is to explain the im-

portance of using modified radius value instead of the estimated radius. Table 5.4

displays the results obtained from implementing the suggested trimming circle

using both estimated and modified radius values.

The left hand column represents the results obtained from implementing the

circular trimming method using the calculated radius, while the right hand column

shows the results for the same image, when a smaller radius has been used. This

small change in radius ensures that all the fringes are removed and the OD is

accurately detected.

The variation between the estimated radius and the implemented radius could

be defined based on the ROI. As mentioned previously, this type of error mainly

101


occurs when detecting the OD. Therefore, it is important to choose the radius so

that all the bright fringes are removed while the OD remains untouched.

Table 5.4: OD localisation using trimming circle

Trimming Region

(Estimated radius)

Trimming Region

(Modified radius)

Trimming Region

(Yellow)

Circularly Trimmed

Brightest Regions

(Possible OD)

Estimated OD

(Red)

102


Observing the results suggests that the use of proposed circular trimming re-

gion with modified radius would provide more accurate results for localization of

OD. However, not all fundus images are circular and so this method would be

insufficient and the results imprecise. Therefore, there is a need for another ap-

proach and so the author has suggested the use of elliptical trimming region when

the outcomes of the circular trimming is invalid.

5.6.2 Elliptical Trimming Region

As shown in Figure 5.10, depending on the setting of the capturing device, the

trimming region, may not be circular, and may be more of a truncated shaped.

Figure 5.10: Examples of retinal images using different capturing devices.

If the radius based on the short axis was calculated, the circular region may be

similar to those found in Figure 5.11. The obtained results clearly indicate that

some of the ROI has been cut out and hence the localisation will be inaccurate as

critical information has been removed.

(a) (b)

Figure 5.11: (a) Inaccurate circular trimming circle (yellow) for an elliptical shapedcaptured fundus image. (b) Trimmed image.

103


To avoid the loss of critical information, it is essential to revise the suggested

methodology. Hence, the long axis has to be considered and used to calculate

the radius of the estimated trimming circle or a secondary analysis has to be

implemented using an elliptical trimming region. Using the long axis to calculate

the radius of the circle would provide results as indicated in Figure 5.12.

(a) (b)

Figure 5.12: (a) Accurate circular trimming circle (yellow) for an elliptical shapedcaptured fundus image using long axis as the radius. (b) Trimmed image.

The results obtained in Figure 5.12 suggests that a circular trimming circle

may be sufficient to remove all the noise close to the black boundary. However, it

is also possible to use an elliptical trimming region as shown in Table 5.5.

Table 5.5: Proposed Circular and Elliptical Trimming Regions

Proposed Trimming Circle Proposed Trimming Ellipse

Equation (x− h)2 + (y − k)2 = r2 (x−h)2

a+ (y−k)2

b= 1

Center (h, k) (h, k)

Radius r =√

A2+B2

4−Cx−Radius = a

y −Radius = b

Referring to Table 5.5, it is apparent that the two regions only vary in radius,

104


where in an ellipse both short and long axis are taken into consideration, which is

basically what is assumed in the previous section for the circular trimming of an

oval shaped fundus image.

5.6.2.1 Implementation

The implementation would be similar to that of the circular trimming region,

with the minor variation of short and long axis. Table 5.6 shows examples of

the results obtained for both circular and elliptical trimming regions for different

fundus images.

Table 5.6: Implementation of both circular and elliptical trimming regions forcircular and elliptically shaped retinal fundus images

Circular Image Elliptical Image Elliptical Image

Trimming Region

(Yellow - Circular

Green - Elliptical)

Circularly

Trimmed

Elliptically

Trimmed

5.6.2.2 Results and Discussion

The obtained results suggests that for fundus images which appear to be circu-

lar, both the elliptical and circular trimming regions would approximately be the

same, hence the use of circular trimming region which has less variables would be

105


sufficient and provide good accuracy. However, for the truncated retinal images,

the two trimming regions of circular and elliptical will not be the same. In such

cases, the use of elliptical trimming region is suggested.

If the ROI is OD and the objective is to localise it, elliptical trimming region can

provide an accurate but faster results than those of the circular trimming region.

As discussed previously, this is due to the fact that the radius of the circular

trimming region may need to be re-calculated. However, if the elliptical region is

implemented, all the fringe noises are removed with the preliminary calculation of

the both short and long axis radii without the need for any recalculations. The

results can be seen in Table 5.7.

Table 5.7: OD Detection for Circular and Elliptical Trimming Region

Trimmed Image OD Detection

Circular

Trimming

Region

Circular Image

Elliptical Image

Elliptical

Trimming

Region

Circular Image

Elliptical Image

This is only true for cases where the OD or Macula localisation and their anal-

106


ysis are of importance. In other cases, such as vasculature detection, it is essential

to preserve data and information as much as possible. As a result, using ellipti-

cal trimming region, where great extent of data is removed, affects the accuracy

of detection significantly and is undesirable. In such cases, circular trimming re-

gion might be the better option. It should be noted that to improve the results

even further, multiple radius values may be used for individual images in order to

determine the best radius for the circular trimming circle.

In conclusion, using the suggested trimming circle and ellipse with adjusted

radius and applying them to the variety of data bases and re-examining the OD

detection using the proposed methodologies, suggested that the localisation is of

more accuracy and the detection rate is now 100% when fringe noise is present, in

comparison to the studies previously conducted in the literature.

There are also times when the whole image is too dark or too light. In such

cases, the detection of features become more difficult as the boundaries would be

less defined. To improve the detection precision in these circumstances, the image

intensity has to be adjusted by enhancing the image contrast. More details are

provided in the next section.

5.7 Contrast Enhancement

The previous section considered the effect of a localized variation in contrast and

how to overcome this problem using trimming regions. The overall results were

promising and the precision of the localization of ROI was improved.

However, the variation in contrast is not always confined to a specific region

of the image. The whole image may appear to be brighter or darker than the set

specification of the system and as a result the accuracy of detection is reduced for

the localization of ROI. In such cases another approach has to be taken.

Moreover, the flexibility of the automatic detection process is critical in iden-

tifying the ROI. There are occasions where the ROI detection has been affected

by the variation in contrast of the obtained images. In such cases, the proposed

system should still be able to proceed and perform its function successfully.

In majority of the studies performed previously, the grey scale image or the

green band of the coloured image was chosen for further processing. Similarly,

107


initially for this study, the green band was chosen to detect the features of interest.

However, there were times where the ROI detection proved to be inaccurate or

unresponsive. Visually revisiting and studying these images indicated that the

variation in contrast, might have been the cause.

Illumination in fundus retinal images is uneven and so the images may appear

to be brighter or darker. The variation in the lighting is dependent on the image

capturing system or the response of the retina itself. The non-uniform illumina-

tion adversely affects the ROI localisation precision and may even result in mis-

detection. In such cases it is essential to consider various contrast enhancement

techniques for re-adjusting the image colours. Once this stage is complete, the

remaining detection processes may be re-implemented and results obtained. Con-

trast enhancement is crucial in medical field as it can reveal information which

might have been otherwise missed or hidden from view.

There are two widely used approaches in contrast enhancement, the linear con-

trast stretching 1 or the histogram equalization 2. In the linear contrast stretching,

the dynamic range of the image is adjusted, while in the histogram equalization,

form the integral of the image histogram, the input and output relation is ob-

tained [154]. In this study, the most common approach in field of medicine is

chosen for further investigation which is the histogram equalization method.

From the available histogram equalization techniques, the Adaptive Histogram

Equalization (AHE) and the Adaptive Contrast Enhancement (ACE) are the most

popular [154].

The AHE algorithm uses the local histograms obtained from the gray values

of pixels. The image is separated into blocks. A particular pixel is enhanced by

interpolating its mapping function with its neighbouring four blocks [154].

The ACE method uses the unsharp masking technique in which the image is

separated into two masks using the low frequency filter. The high frequency mask

is obtained by subtracting the low frequency mask from the image. The amplified

1Linear contrast enhancement or linear contrast stretching is when the original values areexpanded into a wider range. As a result the subtle changes in variation become more apparent.

2Histogram Equalization is when both shape and distribution is taken under consideration.Each level in the displayed image has to have approximately equal number of pixels. This isachieved by stretching the regions with more pixels more than those with few pixels in thehistogram.

108


high frequency mask is then added to the original image in order to enhance the

image contrast [154].

Since in the histogram has been already obtained, the AHE technique which

uses the information obtained from a local histogram to map the gray values of

the pixels has been chosen and implemented.

Depending on the feature of interest, the approach undertaken for contrast

enhancement may vary. Therefore in the study a few different histogram equaliza-

tion methods have been implemented as the interest regions varied significantly in

characteristics.

5.7.1 New Necessary Step

To overcome the uneven illumination, the contrast of each of the images is to be

modified. For each of the contrast enhancement methods, the histogram of the

original image is changed and adjusted to form a new histogram known as the

Desired Histogram (DH).

5.7.1.1 Intensity Adjusted

The first approach has been to modify the intensity variance of the image, such

that 1% of the low and high intensities of the gray scaled image is saturated.

(a) Original Histogram (b) Intensity Adjusted

Figure 5.13: Example of the effect of Intensity Adjustment

109


Figure 5.13 illustrated an example of the changes which occur to the histogram

when its intensity is adjusted. This may be useful, in particular when the original

image is quite dark and so the affect will increase the contrast of the overall image.

However, when noise is present in either of the low or high intensity bands, this

method may not be reliable as it magnifies the error.

5.7.1.2 Histogram Equalization

The second approach is the Histogram Equalization (HE) method [144, 155]. It

basically involves modifying and equalizing the intensity of each image so that the

illumination effects have been minimized. An example of the effect of HE method

on a histogram can be viewed in Figure 5.14.

(a) Original Histogram (b) HE

Figure 5.14: Example of the effect of Histogram Equalization

In this section, a flat DH is formed and applied to the image [144]. It is as

follow:

Desired Histogram =ones(1, n) ∗ Pdt(Size(A))

n(5.16)

Where Pdt is the product of array element in A.

The DH ensures that the grey scale transformation T is minimised by:

|c1(T (k))− c0(k)| (5.17)

110


In the Equation 5.17 the c0 is the cumulative histogram of A and the c1 is the

cumulative sum of DH for all intensities of k.

It should be noted that this equation is constrained such that T must be

monotonic. Moreover, c1 (T (a)) should not overshoot c0 (a) by more than half

the distance between the histogram counts at a.

To map the grey level into their new values, the DH uses the b = T (a) trans-

formation.

5.7.1.3 Adaptive Histogram Equalization

The final approach which is in most cases a more effective method than the HE,

is the Adaptive Histogram Equalization (AHE) method. It is more commonly

known as the Contrast Limited Adaptive Histogram Equalization (CLAHE) as it

concentrates on a small region of the image. It follows the work performed by

Zuiderveld [156].

Figure 5.15 shows the effect of CLAHE when it is applied on a sample his-

togram.

(a) Original Histogram (b) CLAHE

Figure 5.15: Example of the effect of Contrast Limited Adaptive Histogram Equal-ization

CLAHE separates the image into smaller regions and works in enhancing the

contrast in each of those sections, therefore the histogram output approximately

111


is the same as the specified DH. In order to remove the boundaries formed by each

region, the bilinear interpolation can then be applied to smooth out the output

image.

This technique is quite useful as it minimizes the amplification of the noise

present. This is due to the fact that the image is separated into smaller regions

and each section is analyzed separately, reducing the effect of the noise to the

surrounding regions. However, due to computational difficulties, this process may

also take longer.

5.7.2 Results and Discussion

In this section, the effect of each of the different contrast enhancement methods

discussed above is visualised. A sample image has been selected to represent the

effect of each method and how enhancing the contrast of the image may help in

accurate localisation of the ROI.

The outcome is clearly depicted in Table 5.8. As it can be seen, previously

while detecting the OD as the ROI using the green band of the image; the result

was inaccurate. However, after implementation of the three approaches, the OD

was correctly localised.

The variation in contrast and the effect of each of the techniques is apparent

in the image. As mentioned earlier, depending on the area of the interest, the im-

plemented methodology can then be chosen. For example for the OD localisation,

it is better if the image is not too bright since the OD is the brightest region in

the retinal image. If the image is too bright, there is a possibility of misdetec-

tion. However vasculatures are best visible in high contrast and bright images.

Therefore depending on the feature of interest, the chosen methodology to adjust

contrast could vary.

For the purpose of this study, the discussed methodologies proved to be ad-

equate and the implemented approaches tend to provide sufficient information.

For different applications, one or two of the methodologies have been useful. For

example, in vasculature detection the HE method proved to reveal more intricate

details, while the AHE method was used primarily for OD localisation.

112


Table 5.8: OD localization for contrast enhanced images.

Image OD localisation

Green Channel of

Image

Intensity adjusted

image

Histogram

equalised image

Adaptive histogram

equalised image

113


5.8 Summary

In this chapter the pre-processing stage of image processing was applied, so that the

overall accuracy of feature detection could be enhanced for automated processes

with minimal user input.

The common processes including the conversion of the images from colour to

grey scaled and green band images, masking, filtering and image sharpening were

implemented.

Based on the previous literature, the coloured images are best to be converted

into the grey scaled images or to their primary components. This enhances the

processing time, while preserving the image details. The study agreed with the

literature that green channel of the image provided the best level of details for the

purpose of this research and was selected to be used for the consecutive steps of

the image processing process.

To define the ROI, a new thresholding procedure was suggested to mask the

images. This new procedure automatically locates the location of the first major

minimum in the image, separating the ROI from the black background. The

obtained results are promising, demonstrating rapid but exact localisation of the

ROI for masking the retinal images. The accuracy is very similar to the Otsu

method; however, it is computationally less complicated and faster.d

The use of 2D FFT filter was suggested also suggested in this study as a

software filter in order to improve the processing time in the consecutive stages of

the image processing. Using the 2D FFT in conjunction with a kernel was then

used to sharpen the image so that the key features of interest in the fundus image

could be enhanced. The smaller kernel size proved to provide more details about

the image while the larger kernel size displayed the overall outlay of the features.

This characteristic has been used in the coming chapters for localisation of vessels

in the retinal images.

Furthermore, two main factors which may lead to imprecise localization or

misdetection of ROI were considered, including the presence of fringe noise or

localization of a desired feature in low contrast retinal images.

The fringe noise mainly occurs during the capturing where the ambient light

affects the image when the patients’ eye is not placed directly in front of the device.

114


The presence of this bright spot may result in misdetection of the ROI, in particular

when localizing the OD. To eliminate this error, the use of new trimming regions

was suggested so that depending on the shape of the fundus image, the illuminated

noise could be removed automatically. The results for both circular and elliptical

trimming regions proved to be promising, with improvements in overall rate of OD

detection to 100% in comparison to the previously conducted studies.

The other factor which was considered in this chapter was to implement con-

trast enhancement methodologies, so that the ROI could be more easily distin-

guished and localised. Majority of the researches tend to not perform this step

and only use the grey scaled or green band of the colours image in the analysis.

However, for an automated system, it was observed that enhancing the image con-

trast can play a significant role in localisation of the feature. Different histogram

equalization approaches were considered and implemented, including the Intensity

Adjustment, Histogram Equalization and Adaptive Histogram Equalization. The

precision for feature detection has improved as a result, especially when Histogram

Equalization was used in vascular detection and Adaptive Histogram Equalization

was used for OD localisation.

In conclusion of the chapter it can be said that the pre-processing stage im-

proved the outcome of the detection process and increased its success rate. It also

reduced the amount of manual user input needed for feature localization system

of retinal images.

115

CHAPTER 6

IRIS AND PUPIL LOCALISATION AND EXTRACTION




—Iris

— Pupil

Feature Extraction:

— Center

— Area

Figure 6.1: Chapter Six Outline of Image Processing Stages

6.1 Overview

The next main step in image processing after image acquisition and pre-processing

is feature localisation and extraction. In the literature review chapter, some of the

key features of the eye have been identified to be important in many applications

of ophthalmology and biometrics. In this chapter, Iris and Pupil of the eye have

been considered as the features of interest.

Recent studies and applications of biometrics authentication which relates to

the human characterisation and identification, suggests that uniqueness of individ-

ual Iris pattern can be used to separate and distinguish people with extremely high

116

6. IRIS AND PUPIL LOCALISATION AND EXTRACTION

accuracy. Hence, many methodologies have been introduced and implemented in

order to localise the Iris.

Accurate detection of the Pupil boundary can also play a significant role in

the field of ophthalmology as well as biometrics. Accurate detection of the Pupil

and Iris boundary specify the exact Iris region which can then be used for exact

pattern extraction as well as disease diagnosis, treatment and monitoring stages.

For example, during a treatment procedure, such as the case of cataract surgery,

detection of the marginal variations of the size of Pupil boundary may minimise the

occurrences of complications to a great extent. Hence it is important to accurately

detect the Pupil boundary and its changes.

Based on the above factors, new methodologies for fast localisation of the Iris

and Pupil have been proposed in this chapter. Moreover, approaches have been

suggested to automatically detect and measure the center and area of the features

so that medical practitioners could use this information to identify changes due to

disease or complication.

The two essential steps in image processing, the feature localisation and feature

extraction for Pupil and Iris are considered in detail and different approaches are

suggested and applied for the betterment of the final outcomes.

6.2 New Technique for Iris/Pupil Localisation

Exact boundary detection of the Iris and Pupil restricts the affected area and fur-

ther analysis may provide the ophthalmologist with more insight to the severity of

the disease. The information may aid ophthalmologists with all level of experience

to better diagnose and treat the patients.

As discussed in section 3.2.2.1, many different approaches have been considering

Iris and Pupil detection, each having their own advantages and disadvantages.

Amalgamates process has been suggested to be used in this section. This is to

ensure that the actual desired region is selected and more accurately detected. In

order to do so, the results of two different techniques have been fused together,

creating a single mask which segments the ROI, which is then applied to the

original data to define the ROI. In this case the Iris and Pupil have been detected

using this methodology.

117


Figure 6.2 illustrates the flowchart of the overall procedure of the proposed

technique by the author for detection of Iris and Pupil [9, 12].

EyeImage

Acquisition

Image

Pre-Processing

Iris/Pupil

Localisation

Method 1 Method 2

Mask1 Mask2

Overall Mask

(Mask1 + Mask2)

Matching

(with previous data)

Interpretation

(Feature Extraction)Display

Complication?

Alarming System

Revise

Procedure

Continue

NoYes

Figure 6.2: Proposed steps for Iris and Pupil localisation.

Normally any single approach may have its own advantages and disadvantages,

affecting the overall outcome. To check the validity of the result and verifying that

the detected region is in fact the desired ROI, it is best to double check the outcome

with another methodology as well.

From the studied literature, two methodologies have been chosen and imple-

mented to investigate and prove this concept. The thresholding approach sug-

gested by Masek [107] and the active contouring procedure introduced by Rit-

ter [108] have been implemented following the suggested. Detailed explanation of

the two processes and their advantages were included in Section 3.2.2.1.

Figure 6.3 is an example of the possible results which might be obtained from

two different techniques. The results for Iris localisation from technique one is in

green and the technique two is in red. It can be seen that each of the techniques are

not ideal and have missed some critical information. To overcome this problem

and ensure that none of the required information is removed, the best possible

solution would be to define the ROI as the combination of the regions by both

techniques.

118


Figure 6.3: Example of the possible inaccurate results obtained from two differentIris localisation techniques. Results from approach one and two are outlined ingreen and red respectively.

Usually the undertaken approaches are similar in outcome, with minor varia-

tions. Therefore creating an overall mask, combining the two approaches reduces

the detection error and localizes the region with more precision.

Moreover, with an increase number of different approaches, the computational

time also increases, therefore in this study the results from two approaches have

been chosen to be combined. In cases where time is not of an essence, the results

from multiple techniques maybe combined for higher precision.

Another point to consider is that this procedure should be designed such that it

could be applied in the treatment stages of ophthalmology. At this stage, since the

chosen images were from open source databases the main objective has been the

localisation and extraction in a timely manner. Therefore, there is an assumption

that no eyelashes and eyelids can be viewed in the images and so their removal has

not been taken under consideration. This agrees with the treatment procedures

were the eyes are clamed open. As a result of this assumption the computational

complexity has been reduced significantly as the unwanted noise is not present

Additionally, the images for the investigation have been chosen such that they

were clear and not blurred as a result of the slight movements of the eye and the

head. Therefore filtering for deblurring was not considered further in the study.

Furthermore, an exact localisation of Iris and Pupil boundary is of interest in

this case and so no assumptions have been made in regards to their shape being

circular or elliptical. Therefore, the two chosen methodologies from the literature

would need to exactly detect the boundaries without approximating them.

119


It should be noted that Iris and Pupil are similar in shape, so the same method-

ology with different parameters may be used to detect these features. This reduces

the complication of the implemented algorithm and so is more feasible to be used

in an automated system.

6.3 Implementation

In this section, the proposed methodology has been implemented and the results

are observed. An example, using the original image shown in Figure 6.4, has been

used for better representation of the possible outcomes.

Figure 6.4: Original image used for localisation of Iris and Pupil

The results are promising and the feature of interest has been accurately located

in comparison to the results of each of the techniques separately. Similar results

have been observed when detecting the Pupil. Example of the result obtianed

when localising the Iris and Pupil using the proposed methodology can be viewed

in Figure 6.5.

(a) Localised Iris (b) Localised Pupil

Figure 6.5: Result obtained when localising the iris and pupil outer boundariesusing the proposed new algorithm

120


Moreover, the step by step results for Iris localisation using the proposed

methodology has been shown in Table 6.1.

Table 6.1: Example of Iris Localisation Results

Method 1 Method 2

Detection

Noise Removal

Mask

Feature Localisation

It should also be noted that majority of the pre-processing steps are the same

for different procedures, hence it is only the last stage of Iris and Pupil localisation

which may vary between the procedures. As a result the overall computational

time varies mainly due to localisation stage.

Since the two methodologies are being performed concurrently, the processing

time is also reduced in comparison to if the procedures were to be performed

separately and that is a desirable outcome for an automated process. For the

chosen methodologies the overall processing time was about 2-5 seconds.

The suggested process has been performed on over twenty different eye images.

Six samples of the obtained results for Iris localisation are displayed below in

Table 6.2.

121


Table 6.2: Iris localisation for different images.

Original Image Overall Mask Iris Localisation

Image 1

Image 2

Image 3

Image 4

Image 5

Image 6

The results are consistent and show reasonable robustness for detection of

the Iris boundary. In cases where the pigmentation of the Iris is lighter some

misdetection is observed, such as the case in the bottom left hand corner of Image

2 in Table 6.2. This is mainly due to the error in thresholding approach where there

is less contrast between the Iris and Sclera. To overcome this problem, it is best

122


to enhance the contrast using the suggested approach in Section 5.7. This ensures

that the contrast between the two regions are maximised and so the accuracy of

detection is improved.

6.4 Iris and Pupil Extraction

Once the Iris and Pupil have been detected and the boundaries have been localised,

the next step is to extract the feature information. The general information needed

are the center location and the area of the ROI. As a result in this section some

approaches have been suggested to obtain this information.

6.4.1 Center Decection

A simple approach has been used to estimate the location of the center of the Iris

and Macula based on the detected boundary of the localised region. To do so, the

following steps have to be undertaken:

1. Mask the ROI, so that the desired region is represented by ”1” and all sur-

rounding region are set as background and have ”0” pixel value.

2. First non-zero pixel is determined. This pixel would not be black and so

is part of the estimated Iris or Macula. It would represent the most left

non-zero pixel in the image.

3. Last non-zero pixel is then determined. This would be the last pixel of the

ROI and is located on the right hand side of the image.

4. In order to estimate the center of ROI, the horizontal and vertical pixel

locations of the first and last non-zero pixels are used to calculate the middle

point which may be considered as a preliminary location of the Iris and or

Pupil center.

5. To improve the accuracy of center estimation, the horizontal middle value

found in the previous step can then be used to determine the first and last

non-zero values in vertical directions. These points would represent the fur-

thest top and bottom points where the pixel values are still non-zero.

123


6. Similarly using the vertical middle value found in step 4, the first and last

non-zero values in horizontal directions can be determined.

7. Once the points have been determined, their average values are taken, re-

sulting in the re-calculated center location of the Iris and Pupil. An example

of the possible results from this process, will be shown in the OD localisation

Section 8.4.1, Figure 8.6. The final center point of the ROI can be seen as

blue (+) sign on the image.

6.4.2 Area Calculation

Once the center has been localized, the next step is to calculate the area of the

ROI, in this case the Iris and Pupil. Three suggested approaches are as follow:

The first approach could be to approximate the ROI as being circular, and

use the radius (R) to detect the area (A). The radius can be calculated using the

distance between the estimated center and the four non-zero pixels found in the

suggested center localisation approach.

Once the radius has been defined, the area can be calculated using:

A = πR2 (6.1)

The second approach could be to use the perimeter (P) of the ROI to determine

its area. The perimeter can be found more accurately by considering the ROI

pixels. In a binary image of the ROI, the pixels are considered to be part of the

desired region, if they are non-zero and are connected to at least one other non-zero

pixel.

Once the perimeter is calculated, the area of the ROI can then be estimated,

since:

P = 2πR (6.2)

Therefore:

R =P

2π

124


Substitute R back into Equation 6.2:

A = π

(P

2π

)2

=πP 2

4π2

=P 2

4π(6.3)

Using the Equation 6.3 the area of the ROI can be calculated.

Another approach used to determine the area of the ROI is to determine the

total number of the non-zero pixels. This value represents the area of the ROI

since the value of the desired region is set to ”1”, while its surrounding has ”0”

pixel value.

6.5 Summary

Iris and Pupil of the eye have been localised and their key information such as

center and area have been detected. Due to similarities in shape of both Iris and

Pupil, the proposed procedures to localise and extract these features were the

same.

In this study, the exact boundary detection, simplicity of the procedure and

the speed of detection were of interest, hence the proposed approach and the

methodologies were chosen accordingly.

Since each procedure has its own advantage and disadvantage, a new procedure

was proposed which was to obtain results from two different approaches and then

combine the outcomes to create a single mask covering both regions. The mask

could then be used to detect the ROI which in this case were the Iris and Pupil.

In this case, the thresholding and active contouring methods were selected and

their results were combined to create the mask for the ROI. Moreover, since both

methodologies were performed at the same time, the overall processing time is not

increased significantly. The obtained results for Iris and Pupil localisation proved

to be more precise, with less loss of critical information and with a reasonable

125


computational timing.

Once the Iris and Pupil were detected, their center, radius and area were then

calculated. The location of the center was approximated by finding the middle

value in horizontal and vertical direction within the detected boundary. The ra-

dius was then calculated by measuring the distance between the center and the

boundary. Using the equation for the area of the center, the area of Iris and

Pupil were approximately calculated. For a more accurate area, the equation for

perimeter of the circle was used to calculate the area.

The outcomes have been beneficial for the fields of biometrics and optometry

as the Iris and Pupil were successfully detected and their important information

extracted.

126

CHAPTER 7

RETINAL VESSELS LOCALISATION AND

EXTRACTION


Image Acquisition Image Pre-ProcessingFeature Localisation:

—Retinal Vessels

Feature Extraction:

— End Point

Figure 7.1: Chapter Seven Outline of Image Processing Stages

7.1 Overview

Many ophthalmological disorders influence the structure of the retinal vessels and

therefore Vasculature detection has always been one of the key areas for oph-

thalmological research. Many researchers have considered and studied the retinal

vasculature and its detection. Several of these approaches have been considered

and reviewed in Section 3.2.2.1.

Detection of exact location of vessels of the retinal image can enormously aid

medical experts in disease diagnosis and treatment. Diseases such as the ROP,

which affect the normal growth of vessels in the eye can easily be detected and

127

7. RETINAL VESSELS LOCALISATION AND EXTRACTION

treated if the vessels are localized correctly and precisely. The areas which show

signs of insufficient growth can be treated, resulting in reduction of severe cases of

lifelong blindness by ROP.

Therefore, the main objectives of this study have been to locate the vascu-

lature edges and determine their end-points. The proposed methodology should

have been fast, reliable and simple. Furthermore, to reduce the computational

complication and time, the use of previously performed steps have also been con-

sidered.

7.2 Proposed Localisation Technique

Variety of different methodologies for vessel detection has been performed by re-

searchers in this field. Vessels are the most studied feature of interest in the retina

and their localisation have been covered in depth in recent years. The objective

of this research was to suggest a faster, simpler solution, so that a reasonable

outcome could be achieved as majority of the previously proposed approaches are

computationally complicated and times consuming.

To achieve this objective, the 2D FFT filtered images from Section 5.4.1 have

been chosen as the input images. Two different size kernels of several widely used

edge detector filters were then convolved with the images. The two kernels were

10×5 and 3×2 windows.

The edge detector filters, included the Sobel filter, Canny filter, Laplacian filter,

Prewitt filter, Circular Average filter, Average filter, Median filter, Weiner filter

and Gaussian filter.

Figure 7.2 depicts the flowchart of the overall procedure of the proposed tech-

nique for detection of retinal vasculature.

EyeImage

Acquisition

Image

Pre-Processing

Vessels

Localisation

2D FFT ∗ Edge Filter

Interpretation

(Feature Extraction)

End-point

Display

Figure 7.2: Proposed steps for retinal vessel localisation.

128


Canny Filter

Canny filters detect the local maxima of the gradient using the derivative of a

Gaussian filter. The strong and weak edges are found using two different thresh-

olds. Using this, it tracks the intensity discontinuities.

Sobel Filter

Sobel filters emphasize on the high spatial frequency by approximating the

absolute gradient magnitude at each point. It consists of two matrices for edge

detection in horizontal and vertical directions. The two results are then added

together to find the overall magnitude. They are:

Sobel − horizontal =

1 2 1

0 0 0

−1 −2 −1

Sobel − vertical =

−1 0 1

−2 0 2

−1 0 1

Prewitt Filter

Similar to the Sobel Filter, the following is the Prewitt filter which emphasizes

on the edges using the approximation of gradient, therefore it can be considered

as a discrete differential operator. The Prewitt filter consists of two 3×3 matrices

which are convoluted to the original image. The magnitude of the overall results

can be found by adding the outcomes from the two matrices. The two matrices

for detection of edges in horizontal and vertical direction are:

Prewitt− horizontal =

1 1 1

0 0 0

−1 −1 −1

Prewitt− vertical =

1 0 −1

1 0 −1

1 0 −1

129


Laplacian Filter

Laplacian is a second order differential operator, considering the divergence of

the gradients. The Sobel and Prewitt operator only consider the first derivative

while the Laplacian filter calculated the second derivative. In the two dimensions,

Laplacian filter is given by:

∆f =δ2f

δx2+δ2f

δy2

∇2 =4

α + 1

α4

1−α4

α4

1−α4−1 1−α

4α4

1−α4

α4

Where x and y are the Cartesian coordinates and ∇ is the divergent function.

Circular Average Filter

The Circular Average Filter is a smoothing filter which is convolved with the

image. It is capable of detecting edges using a square matrix size of 2×(radius+1),

where radius is the proposed size of the expected artefacts.

Average Filter

Another smoothing filter is the rectangular averaging linear filter commonly

known as the Average filter. In this case the value for each pixel is replaced by

the mean values of its neighbouring pixels. The process is very similar to the

convolution process. In this case a 3×3 kernel was used.

Median Filter

Median filter is a non-linear operator similar to the Average filter. In this case,

the pixel value is replaced with the median value of its neighbouring pixels using

the designated kernel size.

Weiner Filter

Weiner is a linear time-invariant filter. It minimises the mean square error

between the estimated random processes with the desired process. It is a useful

noise removal filtering approach.

Gaussian Filter

The Gaussian filter is a symmetrical low pass filter whose impulse response is

130

7. RETINALVESSELSLOCALISATIONANDEXTRACTION

approximatelyaGaussianfunction.ItisdescribedbytheEquation:

hg(n1,n2)=en2

1+n22

2σ2

TheoverallGaussianfilteroftheimageisfoundusing:

h(n1,n2)=hg(n1,n2)

n1 n2

hg

wheren1andn2arethedistanceinthehorizontalandverticalaxisrespectively.

TheσisthestandarddeviationoftheGaussiandistribution.

Thesuggestedprocedureusingtheabovefiltershasbeenimplementedandthe

resultscanbeviewedinthefollowingsection.

7.3 Implementation

Theproposedprocedureforlocalisingtheretinalvesselshavebeenimplemented

andtheresultsareillustratedinTable7.1.

Table7.1: Modelingandimplementationofdifferentfiltersforvesseldetection

Filter 10×5kernel 3×2kernel

SobelFilter

CannyFilter

131


Table 7.1: Modeling and implementation of different filters for vessel detection

Filter 10 × 5 kernel 3 × 2 kernel

Laplacian Filter

Prewitt Filter


Average Filter

Median Filter

132


Table 7.1: Modeling and implementation of different filters for vessel detection


Weiner Filter

Gaussian Filter

The results obtained from Canny filters appear to be more noisy than the

desired results. This is mainly due to the chosen thresholds. Since each image

would require its own specific threshold values, this method may not be feasible

and desirable for the purpose of this study.

Results from Sobel, Prewitt and Laplacian filters appear to be very similar.

The techniques consider variation in gradient and since the background gradient

is considered in the process, the results do not have the required clarity. The

remaining processes provided similar responses, much clearer than the Sobel, Pre-

witt, Canny and the Laplacian operations.

The results from the Circular Average filter and Average filter was very similar

due to the similarities in the process. However, under similar conditions the Av-

erage filter provided more vasculature details. Comparing the Average filter with

Median filter revealed that median values may result in more noise detection.

Based on observations, it can be said that the Average filter, Median filter,

Weiner filter and Gaussian filter revealed more details and clarity for vascular

detection.

To improve the results even further, several combinations of these filters were

133


also examined and the results have been displayed in Table 7.2.

Table 7.2: Combining results of different filters


Laplacian of Gaussian Filter

Addition of Weiner and Me-

dian Filter

Average Filter of Weiner Fil-

tered image

Weiner Filter of Median Fil-

tered image

Gaussian Filter of the

Weiner Filtered image

134


The results indicate that larger size kernel windows reveal more detail but

have more noise and unwanted error as well. In these cases the accuracy of the

procedures reduces, while the processing time increases. Therefore, for a general

overview of the vessels smaller size windows are preferred in this case.

Moreover, by combining and implementing multiple filters, the results appear

to have improved the clarity of the vasculature detection. This is quite apparent

in three cases of when an Average filter or Gaussian filter was applied to a Weiner

filtered image or when the Weiner filter was applied to the Median filtered image.

All the three cases revealed similar results, however in the case of applying Weiner

filter to the Median filtered image; it appears that some more minor details can

be viewed.

This is due to more emphasis of the locations of the vessels. In the original

results from Table 7.1, the best results for vessels localisation was found by imple-

menting a single filter to sharpen or blur the images. In this case, the emphasised

vessels are further highlighted by combining the filters and noise removal. In the

preliminary analysis, Median filter revealed more detailed structure of the vessels

while Weiner filter which is commonly used for noise removal highlighted the ves-

sels more clearly. Therefore, applying the Weiner filter to the obtained results

of the Median filter would have removed the unwanted noise and revealed more

vasculature structures. This agrees with the observations and the findings of this

study.

For confirmation of the observation, this process has been implemented on

over twenty different images. The average processing time for the retinal vessel

localisation was about 12-15 seconds. The results for five of the images has been

displayed in the following Tables 7.3 to 7.7.

135


Results for Image 1:

Table 7.3: Vessel localisation for Image 1


Original Image - 2D FFT

Filtered Image

Sobel Filter

Canny Filter

Laplacian Filter

Prewitt Horizontal Edge

Emphasizing Filter

136




Average Filter

Median Filter

Weiner Filter

Gaussian Filter

137





dian Filter


tered image


tered image



138






Filtered Image

Sobel Filter

Canny Filter

Laplacian Filter


Emphasizing Filter

139




Average Filter

Median Filter

Weiner Filter

Gaussian Filter

140





dian Filter


tered image


tered image



141






Filtered Image

Sobel Filter

Canny Filter

Laplacian Filter


Emphasizing Filter

142




Average Filter

Median Filter

Weiner Filter

Gaussian Filter

143





dian Filter


tered image


tered image



144






Filtered Image

Sobel Filter

Canny Filter

Laplacian Filter


Emphasizing Filter

145




Average Filter

Median Filter

Weiner Filter

Gaussian Filter

146





dian Filter


tered image


tered image



147






Filtered Image

Sobel Filter

Canny Filter

Laplacian Filter


Emphasizing Filter

148




Average Filter

Median Filter

Weiner Filter

Gaussian Filter

149





dian Filter


tered image


tered image



Studying the results, suggest that the preliminary observations were correct.

Once again the results indicated that the smaller kernel size reduced the noise,

150


while the larger kernel size showed more details. Since the noise would cause

confusion and may lead to misjudgement, the results for smaller kernel size are

preferred.

From the applied filters, the Average filter, Median filter, Weiner filter and

Gaussian filter revealed more information and displayed a better and clearer results

in comparison to the other applied filters.

Similarly, the combination of the filters once again showed that the best local-

isation of the vessels were obtained for the cases were the noise filtering Weiner

filter was applied to the Median filtered images.

7.4 Retinal Vasculature Extraction

Several key features of the vessels including its turosity and variation in diameter

have been considered in details in the literature. However, the disease which was

considered in this case was the ROP. As mentioned in Section 2.4 , ROP occurs in

premature infants and the main distinguishable feature of this disease is that the

vessels are affected as they are not well developed. The only cure for an irreversible

blindness in these infants is to apply laser treatment to the end point of affected

vessels. Therefore, in this case detecting end-point of vessels was investigated

further.

As a result, in this section, an approach has been suggested for localising the

end point of the vessels.

7.4.1 Localisation of the End Point of Vessels

In this section a method has been suggested in order to localise the end point of

the vessels.

1. Localise the retinal vessels from the fundus image.

2. Mask the vessels, so that they have the pixel value of ”1” and the remaining

background areas of the retina have the ”0” pixel value.

3. Trace the location of the vessels. If necessary burst or shrink the vessels to

the desired thickness.

151


4. Using template matching, the end point of the vessels can then be calculated.

By considering a window of 3×3, where the desired non-zero pixel is located

at the center of it, the end point can then be determined, if the middle pixel

is only surrounded by one other non-zero pixel. Else, the desired pixel may

have been located in the middle of the vessel. Figure 7.3 shows an example

of a vessels end point.

Figure 7.3: Some of the possible vessels end point using template matching

7.5 Summary

One of the most important key features of retina is the vasculature. The aim of

this chapter was to introduce a new method to localise the retinal vessels and

determine their end-points.

To reduce the processing time of the localisation procedure, the edges of the

vessels have been detected by applying multiple different filters to the 2D FFT

image which was prepared in Chapter 5. From the studied edge detection filters,

the Average and Gaussian filters applied to Weiner filter and the Weiner filter

applied to the Median filter provided the best possible vessel detection. The vessels

in these cases were clearly visible and more easily distinguishable in comparison

to the other filters and the original images. However, the best visible result was

for the case were the Weiner filter was applied to the Median filtered image.

The extracted feature of the vessels was detecting their end-points. This may

be useful in studying the vasculature growth throughout the retina and diagnosing

diseases such as ROP. Furthermore, it may also aid the ophthalmologists in treating

such diseases as the areas at risk would be highlighted. To achieve this, template

matching was applied to locate the last non-zero pixels. These pixels would only

152


have one other neighbouring non-zero-pixel and hence can be defined as the end

point of the vessels.

Successful, localisation and extraction of the vessels and their end-point were

the outcomes of this research. The short processing time of only a few seconds,

allow this process to be used in many diagnostic tools and a guide for ophthalmol-

ogists.

153

CHAPTER 8

OPTIC DISK AND MACULA LOCALISATION AND

EXTRACTION




—Optic Disk

— Macula

Feature Extraction:

— Center and Radius

— Area

— Cup to Disk ratio

Figure 8.1: Chapter Eight Outline of Image Processing Stages

8.1 Overview

In the literature review chapter, some of the key features of the eye have been

identified to be important in many applications of ophthalmology, including the

OD and Macula of the eye.

Diseases such as Glaucoma are detected using the OD, which is the brightest

region in the retinal image. Glaucoma is the second leading cause of irreversible

visual loss and blindness. Hence, to minimise vision loss in patients, early detection

and treatment of Glaucoma is crucial.

154

8. OPTIC DISK AND MACULA LOCALISATION AND EXTRACTION

Ophthalmologists diagnose Glaucoma by observing the visible changes which

occur at the OD. The diameter of the OD can be used as the preliminary in-

dication of the susceptibility of the patient to Glaucoma. As a result, the OD

localisation and measurement of its area are other key features of interest in the

field of ophthalmology.

Another main feature in retinal images is the macula, which is approximately a

dark circular region in the images. Macula may also help experts in their prognosis

and so its detection is important.

8.2 New Technique for Optic Disk Localisation

Over the past years, many methods have been suggested for detection of OD, each

having their own benefits and restrictions. Some of these approaches resulted in

localising OD center while others estimating its boundaries. One of such methods

has been the thresholding technique.

Thresholding technique has been widely used in the past to detect different

features of a retinal image. In this study, the thresholding approach has been used

to approximate the location of the OD. The reason being is that this approach

would provide an exact boundary of the OD in comparison to majority of the

other available techniques which assume OD to have a circular or an elliptical

shape.

EyeImage

Acquisition

Image

Pre-Processing

Optic Disk

Localisation

Histogram of ROI

Apply Threshold

/Brightest Pixels

Define OD Region

Mask OD Region

Interpretation

(Feature Extraction)

Center

Radius

Area

Cup to Disk Ratio

Display

Figure 8.2: Proposed steps for Optic Disk localisation.

155


As mentioned previously, OD appears as a circular bright spot on the fundus

retinal image. Using this characteristic, the adaptive thresholding technique has

been implemented to detect the brightest pixels of the image. Figure 8.2 depicts

the flowchart of the overall procedure of the proposed technique for detection of

Optic Disk.

In the first step, the bright pixels have been detected and the outcome has

then been displayed as a binary image. This has been achieved using automated

adaptive thresholding for each individual image. Figure 8.3, displays a sample

histogram of this process and the set threshold.

The result is somewhat noisy; therefore filters have been applied to remove this

noise. Noise removal of the result by median filtering has proven to be successful.

Figure 8.3: The gradient plot histogram used to set the threshold for the ODlocalisation.

As demonstrated in Figures 8.3 and 8.4, the OD region is defined by determin-

ing the pixels with the higher intensity values. Since not all the images have the

same intensity and brightness, the threshold has to be set individually. Defining

the threshold is easier in cases like Figures 8.4a and 8.4b as the majority of the

bright pixels are bundled together and easier distinguishable in the Gradient Plot.

However, there are times where defining this region would be more difficult such

as the case in Figure 8.4c. In such cases, the threshold has been set as the first

156


occasion where a few closely located pixels have intensity values greater than 200

gray levels.

(a) Sample 1

(b) Sample 2

(c) Sample 3

Figure 8.4: Example gradient plot histograms and set thresholds for OD localisa-tion for different images.

At this point, a reasonable outline of the OD region has become apparent

and therefore using the remaining white pixels, the center of the OD region has

been detected and an approximated boundary has been set. Depending on the

size of the OD in relation to the overall retinal image size and capturing device

157


specifications, this boundary might vary and therefore has to be set accordingly.

In this case the given boundary has a radius of 70 pixels.

Using the centre location and plotting an approximate circle a mask has been

created to locate the OD region.

Implementing the mask on to the original image has provided a more specific

region of interest. Since consecutive application of a process would enhance the

accuracy and speed of detection, at this stage the thresholding has once again been

applied. The result for the overall process has been displayed in the next section.

8.3 Implementation

In this section, the proposed consecutive adaptive thresholding technique for de-

tection of the OD has been implemented and the results have been displayed in

Table 8.1. It should be noted that for clearer visibility of the results, the images

were zoomed in.

The Adaptive thresholding method has been performed twice on the desired

image in order to accurately detect its brightest regions or in other words OD.

Table 8.1a is an example of a possible desired retinal image which has been

pre-processed according to the procedure covered in Chapter 5 and has been used

in this section for OD localisation.

Table 8.1b represents the detected brightest regions of the original image which

have the pixel values greater than 200 gray levels and are considered as the upper

region of the image histogram. It also outlays the regions which are most likely to

be the OD.

The next two rows, Table 8.1c and 8.1d represent the regions which are having

the pixel values greater than the calculated mean value and the minimum value of

the upper region respectively.

Combining the findings would result in detection of the possible center of the

OD region and is shown in Table 8.1e.

Once the center has been localised, a boundary is set and plotted to the region

which is most likely to be the location of the OD. This has been displayed in

Table 8.1f.

158


Table 8.1: Step by step results for OD detection, applying the proposed consecutiveadaptive thresholding method.

STAGE 1

(a) Original image

(b)Detected lighter region with pixel values greater

than 200 gray level

(c)

Detected lighter region using pixels with values

greater than the mean value from the upper region

of the histogram

(d)

Detected lighter region using the pixels with val-

ues greater than the minimum value from the up-

per region of the histogram

(e)Detected center of OD region using results from

part(d)

(f) Outline of the OD region

STAGE 2

(g)Cropped OD region using results from the first

cycle

159


Interested Region Outcome

(h)Detected lighter region with pixel values greater

than 200 gray level outlined in blue

(i)

Detected OD using the pixels with values greater

than the minimum value from the upper region of

the histogram outlined in green

(j)

Detected OD using the pixels with values greater

than the mean value from the middle Region of

the histogram outlined in red

(k)Detected OD by illustrating results from sections

(h), (i) and (j).

The possible OD region has now been determined. In order to segment the OD

region in the original retinal image, a mask has been created and implemented and

the outcome is shown in Table 8.1g. At this point a second round of the adaptive

thresholding procedure has been applied.

Similar to the previous round, the Table 8.1h, 8.1i and 8.1j represent the de-

tected lighter regions with pixel values greater than 200 gray levels, minimum value

of the upper region and mean value of the middle region accordingly.

Combing the results and plotting boundaries around the detected regions, out-

lines the possible location of the OD. The final result is illustrated in Table 8.1k.

This automated process has proven to be successful in localising the exact

boundary of the brightest region of the retinal image, which is considered as the

OD. It has been implemented on more than twenty different images. The re-

sults obtained using this exact OD detection methodology appears to be of higher

precision in comparison to the other available procedures, with an average com-

putational time of 20-25 seconds.

160


Table 8.2: OD localisation for different images.

Original

Image

Pixels > min-

imum value of

upper region

Pixels >

mean value of

middle region

OD

Image 1

Image 2

Image 3

Image 4

Image 5

Table 8.2 is the results of five different images from the studies database, illus-

trating the OD localisation using the proposed Consecutive Adaptive Thresholding

technique. The results show that the OD localisation has been successful for all

cases and the OD boundaries have been exactly detected.

161


8.4 Optic Disk Extraction

Once the OD has been localized, the next step is to extract the necessary needed

information from the detected ROI.

During disease diagnosis and its progression, the ophthalmologists look at the

shape of the OD and its variation in diameter. Therefore, estimation of the OD

center is the first necessary step in extracting the information. This is then followed

by calculation of its area and later on determing the cup to disk ratio.

8.4.1 Center of the Optic Disk

Two approaches have been suggested by the author, in order to estimate the

location of the center of the OD.

The first method is to estimate the location of the center of the OD based

on the detected boundary of the localised OD. This is similar to the previously

suggested center calculation for Iris and Pupil in Section 6.4.1 of this chapter.

The second method is to determine the location of the center based on the

originating of the vessels within the OD. In this case the use of Template Matching

has been suggested.

1. Extract the OD from the retinal image.

2. Localize the vessels within the OD using the methodology suggested in sec-

tion 7.1 of this chapter.

3. Mask the vessels, so that the vessels have the pixel value of 1 and the re-

maining areas of the OD have the 0 pixel value.

4. Trace the location of the vessels. If necessary burst or shrink the vessels to

the desired thickness.

5. Calculate the point of intersection by implementing template matching con-

cept, determining whether the surrounding pixels of a middle value pixel in

a 3×3 window is zero or one. If the middle pixel in red is our desired pixel

and it is surrounded with at least three other non-zero pixels as shown in

162


Figure 8.5, it can be said that intersection has occurred at the desired pixel.

Otherwise, it can be the middle or an end point in the vessel.

Figure 8.5: Some possible templates for determining vessels intersection

6. The point of intersection, represents the origination of the vessels and so the

center of the OD.

Example of the result obtained implementing the suggested methodologies to

detect the center of the OD can be viewed in Figure 8.6.

(a) Detected OD center

;(b) Zoomed in image

;

Figure 8.6: Center localisation of the OD, method 1 is represented as a blue (+)sign and method 2 as red (+) sign

Comparing the two methodologies, the results are approximately similar. In

majority of the cases, the first methodology is sufficient, unless otherwise the

location of the origination of the vasculature is also on importance in disease

detection and prognosis. The overall processing time is about 1-2 seconds and this

is due to simplicity of the process and reduction in the size of the ROI by confining

it to the OD region.

163


8.4.2 Area of the Optic Disk

Area of the OD can be calculated following the same procedure which was used

previously in Section 6.4.2 for determining the area of the Iris and Pupil.

8.4.3 Cup to Disk Ratio

For diagnosis of diseases such as Glaucoma, ophthalmologists would consider the

area and variation in the shape of the OD, as well as the cup to disk ratio [46, 157,

158, 159]. In the previous sections, the area and the overall shape of the OD has

been detected and analysed. In this section, a suggestion has been made to detect

the Optic Cup (OC) so that it could be used to determine the cup to disk ratio.

Detection of the OC which outlines the borders of the Optic Nerve Head (ONH)

is quite difficult in comparison to the OD localisation as it may not clearly be visible

in the fundus image. On the coloured retinal images, it usually appears as a pink

colour or change in contour from rim to the cup [160].

Although, it may not be possible to accurately detect the OC in all the images

as it may not be visible, in this study it has been suggested to detect the OC using

the similar approach as the suggested consecutive adaptive thresholding which was

used for OD localisation. The overall procedure would be similar but performed

on contrast enhanced images. Since the contrast of the images has changed, the

automatically detected threshold value would also defer, resulting in detection of

the OC. Enhancing the contrast would help in distinguishing and detection of the

cup boundary. More details on how to enhance the contrast of retinal images is to

be covered in Chapter 5.7.

Figure 8.7: Detection of the OC (green) and OD (red)

164


Figure 8.7 represents a sample result which have been obtained when imple-

menting the procedure to detect the OC and OD. As it can be seen, the OC has

been detected and the boundary is shown in green, while the detected OD has

been shown in red.

Once the cup has been localized, similar feature extraction procedures as those

for OD can be performed in order to determine the radius and area of the cup.

Using the obtained area, the ratio between the OD and OC can then be calculated

and used by ophthalmologists for determining the rate of progression of diseases.

The common approach is to visually examine the symmetrical and shape of the OD

and OC under the slit lap biomicroscopy. In the case of Glaucoma, based on the

study performed by Nicolela [160], the cup to disk ratio asymmetry of 0.2 or greater

between the fellow eyes of the patient can be suggestive of this disease.. Therefore,

with the aid of the suggested approach it is possible to help ophthalmologists with

their diagnosis.

8.5 Macula Localisation - Proposed Technique

In order to detect the Macula, its visual characteristics have to be defined. Based

on the definition mentioned in section 2.1.2, Macula is a darkly pigmented circular

region near the center of the fundus retinal images and its structures are responsible

for high acuity vision.

(a) (b) (c) (d)

Figure 8.8: Different positions of macula in retinal images, in images (a) and (d)macula is located in the center while in images (b) and (c) no macula is present.The macula has been manually defined and can be viewed in the images.

165


From observing a number of fundus images, it can be seen that macula may or

may not be present in the image of interest, as shown in Figure 8.8. In Figures 8.8b

and 8.8c, no Macula is visible because of the angle of the image. It can also be

seen that depending on the location of the OD, macula may approximately be

localized as well.

Therefore in this study, prior to localisation of macula, it has been suggested

to initially locate the OD. This is then followed by defining whether Macula is

expected to be present or not. In cases where the Macula is not expected to be

present, further processing is not necessary. However, in cases where the Macula

is expected to be present, process proceeds and macula is localised using Neural

Network (NN) concept.

Figure 8.9 illustrates the flowchart of the overall procedure of the proposed

technique by the author for detection of Macula.

EyeImage

Acquisition

Image

Pre-Processing

Macula

Localisation

OD Coordinates

Is Macula Present?

Complement Image

Adaptive Thresholding

No Further Analysis

Interpretation

(Feature Extraction)Display

Center

Radius

AreaNoYes

Figure 8.9: Proposed steps for Macula localisation.

Neural Networks has been widely used in different areas. In ophthalmology, it

has mainly been used in detection of vessels in retinal images [161]. However in

this study, the concept of NN has been used to determine whether Macula is or

is not present in the given retinal image. If it is present, the Macula can then be

localised.

166


To do so, the fundus image has been segmented in to blocks. 9 blocks in this

case. The number of blocks depends on the ratio and the size of OD in relation

to the size of the retinal image. Based on the observation, for the set of analysed

image in this case, 9 blocks have been sufficient and resulted in accurate macula

localisation. In other cases, in which the image or the capturing instrumentation

specification may vary, the number of blocks may also vary. Figure 8.10 illustrates

a sample of retinal image being separated into the desired number of blocks.

Figure 8.10: The retinal image has been deperated into blocks.

Using the simple feed-forward concept of the NN depicted in Figure 8.11, each

block is considered as the input. The inputs are then checked for the presence

of the OD with them. If OD is present, the output would be set as 1, otherwise

it would be set to 0. It should be noted that the weight for each input block is

the same since OD may be present in any of the blocks. Once the block in which

contains the OD is determined, the blocks which are most likely to contain the

Macula are then investigated further.

167


Input Layer Hidden Layer Output Layer

Input 1

Input 2

Input 3

Input 4

Input 5

Input 6

Input 7

Input 8

Input 9

OD

No OD Ouput

Figure 8.11: Neural network model determining the OD block.

Based on observations, the OD is normally located in the centre, sides or diag-

onals of the images. Depending on the number of blocks and the location of the

OD, it is then possible to estimate the location of the Macula.

Moreover, on average Macula is approximately located 3 mm temporal to the

168


OD [162]. Therefore, on images where OD is located on the right or left hand

side, Macula is most likely located in the center of the image. However, this is still

dependant on the magnification and the angle in which the image is taken from.

If the instrument or possible output of the retinal fundus image is unknown,

it is best to implement Macula detection process to all the blocks expect those

of the background and the OD. This would ensure that the macula is detected

irrespective of the possible estimated ROI.

OD has been previously detected in Section 8.1. To detect Macula, it is impor-

tant to determine in which of the created blocks the Macula is more likely to be

present. For example in Figure 8.10, since the OD is located on the left hand side

in block (4), the Macula is most likely be present in center of the image in Block

(5) or with a lower probability on the right hand side in block (6). Therefore, the

localisation process may only be applied to these two blocks.

There are also possible cases where the OD is not present. In such cases the

Macula localisation may proceed throughout all the blocks.

In other cases where the OD is present in the middle block (block 5), the Macula

may or may not be apparent in the image and therefore the Macula localisation

procedure has to be implemented to all the blocks. However, there is a possibility

that the Macula is covered by the OD and may not be visible.

Once the possible blocks for which the Macula is most likely to be presented in

has been defined, the processing steps similar to those previously used for OD lo-

calisation can be implemented. However, there is a slight alteration to the method-

ology.

Since the Macula is a dark circular region of the retina, the darkest pixels

have to be located instead of the brightest pixels which have been previously

selected in the case of the OD. Another option which was implemented in this

study would be to obtain the complementary image, in which the brightest pixels

correspond to the darkest pixels of the original image or vice versa. An example of

the complementary image can be viewed in Figure 8.12. Once the complementary

image is obtained, the localisation process would be exactly as it was for the case

of the OD.

169


(a) Image (b) Complement

Figure 8.12: Complementary image. (a) Original Image, (b) Complement Image.

Advantages of using the proposed technique are that the error in localisation

of the Macula is reduced significantly. The error is reduced as the first step is to

deter ermine the presence of the macula. If this step is not included the macula

may be located wrongly. Moreover, since the desired ROI is reduced in size the

overall processing time has also reduced. Detection of both Macula and OD may

also be helpful in more accurate formation of fundus maps, which was discussed

in chapter 3, as these features can also be used as markers similar to the vessels

locations.

8.6 Implementation

The proposed methodology for Macula localisation has been performed and the

outcome can be viewed in Figure 8.13. The results are promising and the approx-

imate detection of the Macula has been a success.

(a) Image (b) Detected Macula

Figure 8.13: Localisation of Macula using the proposed technique.

170


Table 8.3: Macula localisation for different images. For cases where the Maculacannot be seen the process is stopped, such as the case for Image 6.

Image Complement Macula Region Macula

Image 1

Image 2

Image 3

Image 4

Image 5

Image 6Macula not vis-

ible

Macula not vis-

ible

171


Observing the results suggests that Macula detection using the proposed tech-

nique has been successful. This process has been implemented on over twenty

images from the used databases with an average processing time of about 3-5

seconds, some of the results have been illustrated in Table 8.3.

8.7 Macula Extraction

Macula is considered to be circular in shape, similar to the OD. Therefore, the

important information which may need to be extracted from the Macula is the

center and the radius. As a result, the approaches undertaken to estimate these

information are the same as what was previously suggested for OD extraction.

Since in this case, the origination of the blood vessels were not of interest and

so the chosen process for locating the center of macula was similar to the one

suggested in Section 6.4.1.

The approach for calculating the area of the macula was also similar to the

suggested method in Section 6.4.2.

The approximate processing time for detection of the center and area of the

macula was less than 1 second, which suggests a very fast processing time due to

simplicity of the suggested procedures.

8.8 Summary

Localisation and extraction of OD and Macula has significant impact in ophthal-

mology as some of the widely affecting diseases such as Glaucoma affects these

features. Therefore variation in shape of OD and Macula can be useful in an early

detection of these diseases.

This chapter looked into the possibility of extracting information from these

features via their accurate localisation. A new method of Consecutive Adaptive

Thresholding technique has been introduced for finding the brightest pixels in

the image in order to exactly outline the OD boundary with a high accuracy.

Possibility of detecting OC has also been suggested at this section, as knowing

the ration between the OD and OC is used to determine the possibility of the

172


occurrence of a disease.

Similarly Macula has also been localised using the same technique. However,

since Macula is the darker region of the retina, the process was altered to some

extent. The Consecutive Adaptive Thresholding approach in this case was used to

detect the darker region of the retina on the complement image. Moreover, there

are times where Macula is not visible in the image as it is over shadowed by the

OD. Hence, prior to the implementation of the technique, Neural Network concept

was applied to determine whether Macula was present or not. If it was present,

then the procedure was performed.

To extract information from the localised OD and Macula, their center was

initially detected. This was then followed by radius and area of the two regions.

In the case of the OD, the ration of the OD to OC was also determined as the

determining factor of occurrence of diseases such as Glaucoma.

The proposed new approach was able to accurately locate the OD and Macula.

The exact boundary detection instead of circular assumption was performed in

order to enhance the accuracy of the extracted information further. The extracted

features were also calculated in order to help ophthalmologists in their diagnosis.

173

CHAPTER 9

CONCLUSIONS


Figure 9.1: Chapter Nine Outline

9.1 Overall Research Program

Ophthalmology has been a growing field in the recent years. With the aid of

the new medical instrumentations and Telemedical devices, ophthalmologists have

been able to diagnose, treat and monitor patients.

The most important stage for treatment of any condition is its early detection.

To aid the ophthalmologists in the diagnosis stage, this study concentrated on

some of the most widely affecting disease such as Cataract, Glaucoma, and ROP.

For each of their key descriptors and features; Iris and Pupil, OD and Macula and

retinal vessels; image processing techniques were suggested for their localisation

and examination. Furthermore, the study was designed such that it could be

used as part of a Telediagnostic tool, which could also be used in rural areas and

developing regions where the availability of resources and expertise are limited.

To achieve this objective, improvements and modifications for all stages of

174

9. CONCLUSIONS

image processing, including image acquisition, pre-processing, feature localisation

and extraction were suggested. The considerations for the proposed techniques

were the simplicity, robustness, fast processing time and high accuracy, with min-

imal user input. The processes were designed such that all the obtained results

could be stored onsite or transferred offsite to be used by ophthalmologists for

their prognosis.

9.2 Research Findings, Perceived Contributions

In this study, each chapter has concentrated on a specific stage of image processing

and some modifications were suggested for each stage. The proposed techniques

were fast, reliable, non-invasive and with a reasonable accuracy.

In order to examine and study a problem, data is required. Therefore, the

first step of image processing is image acquisition. For the purpose of this study,

open source data bases were chosen so that the compatibility of the procedures on

different input data could be monitored and examined. Several different databases

were considered including STARE, DRIVE, MESSIDOR, REVIEW, ROC, CMIF

and UPOL. To study the Iris and Pupil, the images from UPOL database were

chosen. For the cases were retinal fundus images were required, the STARE and

DRIVE data bases were chosen because they are the most widely used databases

by researchers in this field were chosen. All the consecutive steps in this study

were performed on over twenty different images from these databases.

Due to limitations, accessibility and cost of instrumentations in remote loca-

tions, majority of developing nations may only have access to minimal resources.

As a result, to create a wider view on the retina, the use of multiple markers and

images was suggested in order to create a fundus map using normal view angle

cameras. Ophthalmologists can then use this map to diagnose and treat diseases.

The suggested methodology for creating the fundus map used geometric charac-

teristics of the images and included overlapping regions with more markers. As a

result, significant amount of unwanted duplicate noise was removed.

The next a crucial step in image processing is image pre-processing. Different

stages including the colour separation, segmentation and masking of the ROI, noise

175

9. CONCLUSIONS

removal of the images using 2D FFT filters and sharpening them were considered

and examined. These steps were performed in order to prepare the images for the

consecutive stages, their main objective is to remove all the unwanted information

and as a result reduce the overall processing time.

Moreover, studying the results indicated that in some special cases further

image pre-processing stages may be required. Two of such circumstances were

studied as part of this research.

Observing the results indicated that there were times where the bright fringe

noises affected the detection precision, especially in the case of OD localisation.

As a result, circular and elliptical trimming was suggested to be implemented

prior to feature localisation, in the pre-processing stage. After this application,

the precision of results performed was greatly improved to 100% success rate in

comparison to the other previously suggested procedure in the literature.

In other cases, the accuracy of the results was affected due to the contrast

of the images. This specially became apparent when thresholding technique was

considered. In such cases, the contrasts of the images were enhanced using the

Intensity Adjusted, Histogram Equalization and Adaptive Histogram Equalization.

The next two main stages of image processing included the feature localisation

and extraction. As mentioned previously, the main key features considered in this

study for diagnosing Cataract, ROP and Glaucoma were the Iris and Pupil, retinal

vessels, OD and Macula respectively.

For detection of the Iris and Pupil boundaries, which is beneficial for Cataract

diagnosis and Biometrics application, an amalgamates procedure was suggested to

incorporate and combine the results from two or more different processes in order to

create a single outlay to mask and segment the ROI. By combining two different

techniques of Thresholding and Active Contouring, the suggested methodology

has improved the accuracy of the detection in about 2-5 seconds. Since the two

procedures occur simultaneously the processing time is not increased significantly

while the results are of higher precision. To quantize the chosen region approaches

were suggested to approximately determine the center of the Iris and Pupil and

then calculate their areas.

Using fundus images, the retinal vasculatures were examined and localised for

diagnosis of diseases such as ROP, where the complication affects the vascular for-

176

9. CONCLUSIONS

mation and shape. To do so, two different size kernels of several filters were applied

to the readily available 2D FFT filtered images from the pre-processing stage. The

applied filters included the Sobel, Canny, Laplacian, Prewitt, Circular Average,

Average, Median, Weiner and Gaussian filters. The observed results suggest that

larger size kernels revealed more information, but had more unwanted noise as

well. From the implemented sample filters, four revealed more details. The filters

were the Average filter, Median filter, Weiner filter and Gaussian filter. However,

there was still noise present in the outcomes; hence a combination of them was

studied. Three of the results showed very clear vasculature edges, including the

application of Average filter or Gaussian filter on the Weiner filtered image and

Wiener filter when it was applied to the Median filtered image. There were some

slight variation between the three best results but by observation, it could be said

that when Weiner filter was applied on a median filtered image, some more details

could be viewed in the output. To analyse the findings it was suggested to de-

termine the end-point of the vessels using template matching. The simplicity and

the reasonable processing time of about 12-15 seconds for the suggested vascular

localisation process makes it a suitable preliminary telemedicine tool for determin-

ing the high risked patients who might suffer from retinal vascular disorders such

as ROP.

Lastly, OD and Macula are used to diagnose and monitor the progression of

Glaucoma. To localise the boundary of OD, a new iterative thresholding method-

ology was suggested. On the contrary to the majority of the available OD approx-

imation localisation techniques, this method determines the exact OD location

and shape. The variations and changes to the OD shape were also examined by

obtaining its center, area and cup to disk ratio. The overall processing time for

OD localisation was about 20-25 seconds.

Macula was examined using a similar approach as to the OD. Firstly, the

retinal image is checked for the visibility of the Macula using the Neural Network

concept. If the Macula was visible, the thresholding approach was applied to the

complement of the image, localising the Macula in 3-5 seconds. Center and area

of the Macula were also calculated.

This study indicated that if need be all the main key features for critical wide

spread diseases may be localised and monitored in under a minute. The simplicity

177

9. CONCLUSIONS

and robustness of the chosen approach also ensured that it could be used as part

of a Telediagnositc tool.

9.3 Proposals for Future Research

Research is an ongoing field and with advancements in technology, current available

approaches may further improve. In this section, a few suggestions have been given

by the author as the possible future work.

• Larger databases

– The databases used in this study were limited to the online available

open source links. However, by creating a larger database not only

the accuracy of detection for a specific disease increases but also wider

range of ailments could be detected using disease maching.

• Considering other diseases

– There are times when irreversible damage may be caused when critical

information is missed by the medical practitioner. This may be due to

the limited expertise of the ophthalmologists, rareness of a disease or

patient suffering from several medical conditions. In such cases, looking

into a larger database, covering many other diseases can be of great

assistance. To do so, many other studies on different diseases should

be performed so that the overlapping information and features of the

ailments could be defined and a larger database formed. Using this

database, then the medical practitioner could pinpoint and determine

what the main cause of the condition.

– One of the diseases which affect a wide population is Primary Angle

Closure Glaucoma (PACG). PACG causes development of angle closure.

The narrow angle is treated using the laser periphery iridotomy, if de-

tected early. Currently the Ultrasound Bio-Microscopy (UBM) is used

to detect the narrow angles, but since the procedure involves immersion

178

9. CONCLUSIONS

of the eye into fluid, it is time consuming, inadequate and inconvenient

as a routine test. To improve the testing procedure, a study can be per-

formed incorporating results from the Optical Coherence Tomography

(OCT) and the Ultrasound Bio-Microscopy (UBM). Since both OCT

and UBM are capable of obtaining cross sectional images of the Ante-

rior Chamber (AC), they may provide a better potential information in

detection of patients who might be at risk of angle closure.

• Considering other features

– In the image acquisition stage of the study, the effect of light and its

refraction was considered when passing through the eye and creating the

retinal images. The results suggested that there is a significant different

between the incident and refractive light rays which is usually ignored

and is not considered when analysing results. In order to consider this

effect, further calculation in consecutive steps of processing is needed

for determining the exact locations of the key features of the eye.

– Localization of other features and conditions can further help in cre-

ating a broader database. An example could be including results from

detection of microaneurysm [163].

– As mentioned previously, main feature for detection of the occurrence

of the complication during cataract surgery is variation in colour of

the eye. Using the colour index and its variation can therefore help in

detection of such complications.

– For the case of ROP, since the outgrowths of vessels are of great impor-

tance, the use of fractal approach can help in estimating the angiogene-

sis growth. This information can be included and used by the surgeons

to oversee the progression of the disease.

179

9. CONCLUSIONS

• Combining other results

– Patients Records

∗ The obtained results may also benefit if other information from the

patient such as ocular pressure could be available. For example if

variation of ocular pressure could be constantly monitored during

the cataract surgery, any changes in pressure may assist the pro-

posed monitoring system and alert the surgeons of the possibility

of complication.

– Results from other devices

∗ In this study, image processing methodologies were of main inter-

est. Incorporating the information and results from other medical

devices such as the OCT [164], fluorescence angiograms, use of in-

frared lighting with the results obtained from this study can aid

the ophthalmologists to make a more valid and reliable decision in

their disease prognosis.

∗ Real time feedback from the OCT can also aid the cataract surgery

significantly as the thickness of the posterior capsule can be con-

tinuously measured intra-operatively. Any changes in the thickness

can then alert the surgeon. This may also help in creating the 3D

view of the eye during the surgery as the location of the device, the

depth of the eye and all its features can be calculated and defined.

∗ Including results obtained from Confocal Scanning Laser Tomogra-

phy (CSLT) which is widely used for three dimensional scanning of

the ONH would provide a better insight into the extent of progres-

sion of Glaucoma. However, further statistical examination of the

progression of the structural glaucomatous damage as well as im-

provements on the repeatability of the images obtained using this

technique is required.

To do so, a Statistic Image Mapping (SIM) can be performed which

may benefit the field of neuro-imaging. The active changes of the

ONH can be visualised by applying the pixel by pixel analysis of

180

9. CONCLUSIONS

the topographic height over time. The flagged change map and

the intensity variation can be used to determine active changes

of the ONH and determine the progression of the disease. The

repeatability of the images can be tested by comparing the findings

with the results obtained from the Topographic Change Analysis

(TCA) system.

• Improvements of devices

– Hardware improvements - For instance in the cataract surgery case,

placing sensors on the head of the phacoemulsification handheld device,

in order to measure the input and output flow can help in constant

monitoring of the intraocular pressure and so automatically stoping the

surgery if any irregularity is seen.

– Improvements on portable handheld capturing devices - With increase

in technology and its availability in remote locations, image processing

can further enhance. Capturing high quality retinal images using mo-

bile phones are the next step in disease classification. Despite several

studies being recently conducted in this field, it may still acquire im-

plementation of several new filtering systems and image enhancement

mechanisms.

– Improvements of OCT -

∗ Create a real time, high speed anterior segment OCT system which

can quantitatively analyse the angle parameters. The designed

OCT should use the 1.3µm light source instead of the 0.8µm light

source which would provide better visualisation of the features and

enhance the speed of processing significantly faster than the current

available segment OCT systems. This is due to the lower scattering

of light at this wavelength as well as about 90% reduction of light

incident reaching the retina as it is absorbed by the water in the

ocular media. This system may be applied to analyse the angle

parameters, which can then be used for narrow angle detection and

diagnosing diseases such as PACG.

181

9. CONCLUSIONS

∗ Incorporation of the ultra-board spectral bandwidth light sources

in order to reduce the cost and enhance the axial resolution of

OCT production. The OCT technology may further benefit from

combining the outputs of other available technologies such as the

Retinal Thickness Analysis (RTA), Heidelberg Retinal Tomograph

(HRT) and Scanning Laser Polarimetry which are also capable of

determining the retinal thickness and the Retinal Nerve Fiber Layer

(RNFL) thickness. The combination and advancements in this area

may benefit the data acquisition and abnormality detection for dis-

ease diagnosis. There are many challenges involved in progression

of this technology and therefore further detailed examination is re-

quired.

These were a few possible further improvements on the current available tech-

niques. This suggests that there are many other aspects in ophthalmology which

need further attention and research. The use of biomedical applications can cer-

tainly meet these needs in conjunction with advancements in technology.

182

REFERENCES

[1] W. H. Organisation. (2011, May) Visual impairment and blindness. [Online].

Available: http://www.who.int/mediacentre/factsheets/fs282/en/

[2] J. Bewes and et.al., “Automated cell colony counting and analysis using the

circular hough image transform algorithm (chita),” Physics in Medicine and

Biology, vol. 52, p. 59916008, 2008.

[3] J. Suri, Y. Ng, and R. A. U, Image Modeling of the Human Eye. Norwood:

Artech House, 2008, pp. 1–36.

[4] R. Warwick, Eugene Wolffs Anatomy of the Eye and Orbit - 7th ed. Philadel-

phia: PA: W.B. Saunders,, 1976.

[5] J. Flammer and et al, “The impact of ocular blood flow in glaucoma,” Prog.

Retinal Eye Res., vol. 21, no. 4, p. 359393, 2002.

[6] S. A. U. and E. K. Ng, Computational Analydid of the Human Eye with

Applications. Singapore: World Scientific Publishing Company, 2011, pp.

1–39.

[7] C. Willoughby, D. Ponzin, S. Ferrari, A. Lobo, K. Landau, and Y. Omidi,

“Anatomy and physiology of the human eye: effects of mucopolysacchari-

doses disease on structure and function a review,” JClinical and Experi-

mental Ophthalmology, vol. 38, pp. 2–11, 2010.

183

http://www.who.int/mediacentre/factsheets/fs282/en/

REFERENCES

[8] M. Hughes, “Anatomy of the anterior eye for ocularists,” Journal of Oph-

thalmic Prosthetics, p. 2535, 2005.

[9] A. Ektesabi and A. Kapoor, “Complication prevention of posterior capsu-

lar rupture using image processing techniques,” Proceedings of the World

Congress on Engineering 2012, pp. 603–607, July 2012.

[10] S. R. Snell and A. M. Lemp, Clinical Anatomy of the Eye - 2nd ed. Norwood:

Blackwell Science, 1998.

[11] X. Zhu, R. Rangayyan, and A. Ells, Digital Image Processing for Ophthal-

mology: Detection of the Optic Nerve Head. USA: Morgan and Claypool

Publishers, 2011, pp. 1–10.

[12] A. Ektesabi and A. Kapoor, “Exact pupil and iris boundary detection,”

2nd International Conference on Control, Instrumentation and Automation

(ICCIA), pp. 1217–1221, 2011.

[13] T. W. Bank. (2013) Population, total. [Online]. Available: http:

//data.worldbank.org/indicator/SP.POP.TOTL?cid=GPD 1

[14] H. Scholl, R. Massof, S. West, and A. Singh, Ophthalmology and the Ageing

Society. USA: Springer Heidelberg New York Dordrecht London, 2013, pp.

1–10.

[15] M. Reddy, “Complications of cataract surgery,” Ophthalmology Practice,

vol. 43, no. 4, pp. 201–209, 1995.

[16] G. Kanthan, Mitchell, Burlutsky, and Wang, “Alcohol consumption and

long-term incidence of cataract and cataract surgery: The blue mountains

eye study,” American Journal of Ophthalmology, vol. 150, no. 3, pp. 434–440,

2010.

[17] B. Lorenz, Pediatric Ophthalmology, Neuro-Ophthalmology, Genetics. New

York: Spronger-Verlag Berlin and Heidelberg Gmbh & Co.Kg, 2006, pp.

63–80.

184

http://data.worldbank.org/indicator/SP.POP.TOTL?cid=GPD_1

http://data.worldbank.org/indicator/SP.POP.TOTL?cid=GPD_1

REFERENCES

[18] N. Ashton, “Oxygen and the growth and development of retinal vessels. in

vivo and in vitro studies. the xx francis i. proctor lecture.” American Journal

of Ophthalmology, vol. 62, pp. 412–435, 1966.

[19] R. Foos and S. Kopelow, “Development of retinal vasculature in prinatal

infants.” Survey of Ophthalmology, vol. 18, pp. 117–127, 1973.

[20] J. Flynn, “Retinopathy of prematurity,” Pediatric Clinics of North America,

vol. 34, pp. 1487–1516, 1987.

[21] C. S. H. Tan, “Cost effectiveness of phacoemulsification in developing coun-

tries,” Eye, vol. 22, pp. 1827–1828,, 2010.

[22] R. Khanna and et al, “Cataract surgery in developing countries,” Current

Opinion in Ophthalmology, vol. 22, pp. 10–14, 2011.

[23] E. L. Lamoureux and et al, “The impact of cataract surgery on quality of

life,” Current Opinion in Ophthalmology, vol. 22, pp. 19–27, 2011.

[24] D. Friedman, M. Wilson, J. Liebmann, R. Fechtner, and R. Weinreb, “An

evidence-based assessment of risk factors for the progression of ocular hy-

pertension and glaucoma,” Americal Journal of Ophthalmology, vol. 138, p.

S19S31, 2004.

[25] P. Khaw, P. Shah, and A. Elkington, “Glaucoma-1: diagnosis,” BMJ, vol.

328, p. 9799, 2004.

[26] F. F. III, S. Fine, and L. Hyman, “Age-related macular degeneration and

blindness due to neovascular maculopathy,” Arch Ophthalmol., vol. 102, pp.

1640–1642, 1984.

[27] A. Sola, S. Golombek, M. M. Bueno, L. Lemus-Varela, C. Zuluaga,

F. Dominguez, H. Baquero, A. Sarmiento, D. Natta, J. Perez, R. Deulofeut,

A. Quiroga, G. Flores, M. Morgues, A. Perez, B.Van-Overmeire, and F. van

Bel, “Safe oxygen saturation targeting and monitoring in preterm infants:

can we avoid hypoxia and hyperoxia?” Acta Paediatrica, vol. 103, pp. 1009–

1018, 2014.

185

REFERENCES

[28] H. Taylor, J. Keeffe, H. Vu, J. Wang, E. Rochtchina, P. Mitchell, and M. Pez-

zullo, “Vision loss in australia,” Medical Journal, vol. 182, pp. 565–568, 2005.

[29] W. Huang, K. Chan, H. Li, J. Lim, J. Liu, and T. Wong, “A computer

assisted method for nuclear cataract grading from slit-lamp images using

ranking,” IEEE Transactions on Medical Imagingl, vol. 30, no. 1, pp. 94–

107, 2011.

[30] B. Henderson, R. Pineda, C. Ament, S. Chen, and J. Kim, Essentials of

Cataract Surgery. NJ: SLACK: Thorofare, 2007.

[31] H. Crabtree, A. Hildreth, J. O’Connell, and et al, “Measuring visual symp-

toms in british cataract patients: The cataract symptom scale.” British Jour-

nal of Ophthalmology, vol. 83, pp. 519–523, 1999.

[32] E. Lamoureux, E. Rehnwick, K. Pesudovs, and D. Tan, “The impact of

cataract surgery on quality of life,” Current Opinion in Ophthalmology,

vol. 22, pp. 19–27, 2011.

[33] E. Monestam and L. Wachtmeister, “Change of subjective visual function in

first-eye cataract patients when the rate of surgery increases in a population,”

Medical Care, vol. 40, no. 11, pp. 1080–1089, 2002.

[34] R. R. adn S. Pommier, L. Roux, and et al, “Magnitude and strategies of

cataract management in the world,” Med Trop, vol. 67, pp. 644–650, 2007.

[35] A. Agarwal and D. Kumar, “Cost-effectiveness of cataract surgery,” Current

Opinion in Ophthalmology, vol. 22, pp. 15–18, 2011.

[36] J. Javitt, M. Kendix, J. Tielsch, D. Steinwachs, O. Schein, M. Kolb, and

E. Steinberg, “Geographic variation in utilization of cataract surgery,” Med-

ical Care, vol. 33, no. 1, pp. 90–105, 1995.

[37] A. Coleman and J. Morrison, Management of Cataracts and Glaucoma.

U.K.: Taylor Francis: Oxfordshire, 2005.

186

REFERENCES

[38] B. Klein, R. Klein, K. Linton, Y. Magli, and M. Neider, “Assessment of

cataracts from photographs in the beaver dam eye study,” International

Journal of Ophthalmology, vol. 97, no. 11, pp. 1428–1433, 1990.

[39] J. Sparrow, A. Born, N. Brown, W. Ayliffe, and A. Hill, “The oxford clinical

cataract classification and grading system,” International Journal of Oph-

thalmology, vol. 9, no. 4, pp. 207–225, 1986.

[40] B. Thylefors, L. Chylack, K. Konyanma, K. Sasaki, R. Sperduto, H. Taylor,

and S. West, “A simplified cataract grading system,” Ophthalmic Epidemiol,

vol. 9, no. 2, pp. 83–95, 2002.

[41] L. Chylack, J. Wolfe, D. Singer, M. Leske, M. Bullimore, I. Bailey, J. Friend,

D. McCarthy, and S. Wu, “The lens opacities classification system ii,”

Archive of Ophthalmology, vol. 111, no. 6, pp. 831–836, 1993.

[42] N. Ferrier, “Automated identification of the anatomical features in slit lamp

photographs of the lens,” Invest. Ophthalmol. Visc. Sci., vol. 43, p. 435,

2002.

[43] R. Baltussen, M. Sylla, and S. Mariotti, “Cost-effectiveness analysis of

cataract surgery: A global and regional analysis,” Bull World HEalth Organ,

vol. 82, pp. 338–345, 2004.

[44] A. Coombs and D. Garty, Cataract Surgery. London: BMJ Books - Ebrary

Inc., 2003.

[45] J. Alio and Y. Sanz, Minimizing Incisions and Maximizing Outcomes in

Cataract Surgery. Dordrecht: Springer, 2010.

[46] S. Johnson, Cataract Surgery in the Glaucoma Patient. Dordrecht: Springer,

2009.

[47] M. Kwitko, The History of Modern Cataract Surgery. The Hague: Kugler,

1998.

187

REFERENCES

[48] Frompo. Intracapsular cataract extraction (icce). [Online].

Available: http://www.covidien.com/imageServer.aspx?contentID=

11904&contenttype=image/jpeg

[49] S. Basti, A. Vasavada, R. Thomas, and P. Padhmanabhan, “Extracapsular

cataract extraction: Surgical techniques,” Ophthalmology Practice, vol. 41,

pp. 195–210, 1993.

[50] B. Hamasalh. (2015) Ophthalmology diseases of the

lens. [Online]. Available: http://www.slideshare.net/AbbasTelakoe/

ophthalmologydiseases-of-the-lensdrbaxtyar

[51] S. Pershing and A. Kumar, “Phacoemulsification versus extracapsular

cataract extraction: where do we stand?” Current Opinion in Ophthal-

mology, vol. 22, pp. 37–42, 2011.

[52] S. Ruit and et al, “A prospective randomized clinical trial of phacoemulsifi-

cation vs manual sutureless small-incision extracapsular cataract surgery in

nepal,” American Journal of Ophthalmology, vol. 143, pp. 143–144, 2007.

[53] D. Bhattacharya, “Nuclear management in manual small incision cataract

surgery by snare technique,” Indian Journal of Ophthalmology, vol. 57, pp.

27–29, 2009.

[54] H. Courtecuisse, J. Allard, C. Dureiz, and S. Cotin, “Preconditioner-

based contact response and application to cataract surgery,” MICCAI

2011, vol. 6891, pp. 315–322, 2011. [Online]. Available: http:

//codrt.fr/allardj/pub/2011/CADC11

[55] A. Hennig, S. Singh, I. Winter, and D. Yorston, “Responce to cost effective-

ness of phacoemulsification in developing countries,” Eye, vol. 24, p. 1828,

2010.

[56] M. Zare, M. Javadi, B. Einollahi, A. Baradaran-Rafii, S. Feizi, and V. Ki-

avash, “Risk factors for posterior capsule rupture and vitreous loss during

phacoemulsification,” Journal of Ophthalic and Vision Research, vol. 4, no. 4,

pp. 208–212, 2009.

188

http://www.covidien.com/imageServer.aspx?contentID=11904&contenttype=image/jpeg

http://www.covidien.com/imageServer.aspx?contentID=11904&contenttype=image/jpeg

http://www.slideshare.net/AbbasTelakoe/ophthalmologydiseases-of-the-lensdrbaxtyar

http://www.slideshare.net/AbbasTelakoe/ophthalmologydiseases-of-the-lensdrbaxtyar

http://codrt.fr/allardj/pub/2011/CADC11

http://codrt.fr/allardj/pub/2011/CADC11

REFERENCES

[57] D. Colvard, D. Chang, M. Packer, I. Fine, and R. Hoffman, Phaco Tech-

niques. New York: Spronger-Verlag Berlin and Heidelberg Gmbh & Co.Kg,

2006, pp. 33–52.

[58] C. Kelman, “Phacoemulsification and aspiration,” American Journal of Oph-

thalmology, vol. 67, pp. 464–477, 1969.

[59] M. Schafer and L. Arbisser, “Quantification of acoustic exposure during

cataract surgery,” IEEE International Ultrasonics, Ferroelectrics, and Fre-

quency Control Joint 50th Anniversary Conference, pp. 1828–1831, 2004.

[60] K.Yao, P. Ye, X. Tang, P. Chen, and X. Shen-Tu, “Clinical evaluation using

custom control software technology in coaxial phacoemulsification,” Clinical

and Experimental Ophthalmology, vol. 34, pp. 861–865, 2006.

[61] H. Sin. (2007) Cataract surgery and intraocular lens technology.

[Online]. Available: http://bme240.eng.uci.edu/students/07s/hsin/IOL%

20Implantation.html

[62] U. Devgan, “Surgical techniques in phacoemulsification,” Current Opinion

in Ophthalmology, vol. 18, pp. 19–22, 2007.

[63] C. H. Boston. (2007) Can blindness be prevented through diet? [Online].

Available: http://www.sciencedaily.com/releases/2007/06/070624141851.

htm

[64] T. Terry, “Extreme prematurity and fibroblasatic overgrowth of persistent

vascular sheath behind each crystalline lens. ii. report of cases,” American

Journal of Ophthalmology, vol. 29, pp. 36–53, 1943.

[65] R. R. Ober and et al., Retinopathy of Prematurity, in Handbook of Pediatric

Retinal Disease. New York: Springer-Verlag New Youk Inc Dordrecht, 2007,

pp. 284–349.

[66] M. Avery and E. Oppenheimer, “Recent advances in mortality from hyaline

membrane disease.” Journal of Pediatrics, vol. 57, pp. 553–559, 1960.

189

http://bme240.eng.uci.edu/students/07s/hsin/IOL%20Implantation.html

http://bme240.eng.uci.edu/students/07s/hsin/IOL%20Implantation.html

http://www.sciencedaily.com/releases/2007/06/070624141851.htm

http://www.sciencedaily.com/releases/2007/06/070624141851.htm

REFERENCES

[67] A. D. McDonald, “Cerebral palsy in children of very low birth weight.”

Archives of Disease in Childhood, vol. 38, pp. 579–588, 1963.

[68] V. E. Kinsey and et al., “Pao2 levels and retrolental fibroblasia: a report of

the coorporative study,” Journal of Pediatrics, vol. 60, pp. 655–668, 1977.

[69] D. Phelps, “Retinopathy of prematurity: an estimate of visual loss in the

united states: 1979,” Journal of Pediatrics, vol. 67, pp. 924–926, 1981.

[70] L. Smith, Retinopathy of Prematurity: Molecular Mechanism of Disease, in

Pediatric Ophthalmology, Neuro-Ophthalmology, Genetics. Spronger-Verlag

Berlin and Heidelberg Gmbh & Co.Kg, 2006, pp. 51–62.

[71] J. Flynn, “Acute proliferative retrolental fribroblasia: multivariate risk anal-

ysis.” Transactions of the American Ophthalmological Society, vol. 81, pp.

549–591, 1983.

[72] W. Silverman, Retrolental fibroplasia: a modern parable. New York: Grune

& Statton, 1980, pp. 191–204.

[73] B. Darlow, J. Hutchinson, D. Henderson-Smart, D. Donoghue, J. Simpson,

and N. E. NJ, “Australian and new zealand neonatal network. prenatal risk

factors for severe retinopathy of prematurity among very preterm infants of

the australian and new zealand neonatal network,” Pediatrics, vol. 115, pp.

990–996, 2005.

[74] T.Butler and et al., “Anatomical and visual outcome of retinal detachment

surgery in children.” British Journal of Ophthalmology, vol. 85, pp. 1437–

1439, 2001.

[75] A. Poulson and M. Snead, Childhood Retinal Detachment, in Pediatric Oph-

thalmology, Neuro-Ophthalmology, Genetics. Spronger-Verlag Berlin and

Heidelberg Gmbh & Co.Kg, 2006, pp. 191–204.

[76] N. E. Institute. (2013) Facts about retinopathy of prematurity (rop).

[Online]. Available: http://www.nei.nih.gov/health/rop/rop.asp

190

http://www.nei.nih.gov/health/rop/rop.asp

REFERENCES

[77] L. Wu and et al. (2013) Tractional retinal detachment. [Online]. Available:

http://emedicine.medscape.com/article/1224891-overview

[78] J. McNamara and et al., “Laser photocoagulation for stage 3+ retinopathy

of prematurity.” Ophthalmology, vol. 98, pp. 576–580, 1991.

[79] L. R. S. Group, “Laser therapy for retinopathy of prematurity.” Archives of

Ophthalmology, vol. 112, pp. 154–156, 1994.

[80] D. Iverson and et al., “Laser photocoagulation for threshold retinopathy of

prematurity.” Archives of Ophthalmology, vol. 109, pp. 1342–1343, 1991.

[81] D. Hunter and M. Repka, “Diode laser photocoagulation for threshold

retinopathy of prematurity. a randomized study.” Ophthalmology, vol. 100,

pp. 234–244, 1993.

[82] M. O’Keefe and et al., “Longer term visual outcome of eyes with retinopathy

of prematurity treated with cryotherapy or diode laser.” British Journal of

Ophthalmology, vol. 82, pp. 1246–1248, 1998.

[83] J. White and M. Repka, “Randomized comparison of diode laser photocoag-

ulation versus cryotherpy for threshold retinopathy of prematurity: 3-year

outcome.” Journal of Pediatric Ophthalmology and Strabismus, vol. 34, pp.

83–87, 1997.

[84] I. Pearce and et al., “Three year visual outcome for treated stage 3 retinopa-

thy of prematurity: cryotherpay versus laser.” British Journal of Ophthal-

mology, vol. 82, pp. 1254–1259, 1998.

[85] T. Realini, “A history of glaucoma pharmacology,” Optometry and Vision

Science, vol. 88, pp. 36–38, 2011.

[86] G. Michelson, S. Wrntges, J. Hornegger, and B. Lausen, “The papilla as

screening parameter for early diagnosis of glaucoma,” Deutsches Aerzteblatt

Int., vol. 105, pp. 34–35, 2008.

[87] I. Toprak, C. Yildirim, and V. Yaylal, “Optic disc topographic analysis in

diabetic patients,” Int Ophthalmology, vol. 32, pp. 559–564, 2012.

191

http://emedicine.medscape.com/article/1224891-overview

REFERENCES

[88] N. Gupta and R. Weinreb, “New definitions of glaucoma,” Curr Opin Oph-

thalmol., vol. 8, pp. 38–41, 1997.

[89] H. Quigley, “Neuronal death in glaucom,” Prog Retin Eye Res, vol. 18, pp.

39–57, 1999.

[90] Y. Pan and R. Varma, “Natural history of glaucoma,” Indian Journal of

Ophthalmology, vol. 59, pp. S19–S23, 2011.

[91] A. Tuulonen and P. Airaksinen, “Initial glaucomatous optic disk and retinal

nerve fiber layer abnormalities and their progression.” Am J Ophthalmol.,

vol. 111, p. 485, 1991.

[92] M. Ishikawa, Y. Sawada, N. Sato, and T. Yoshitomi, “Risk factors for pri-

mary open-angle glaucoma in japanese subjects attending community health

screenings,” Clinical Ophthalmolgy, vol. 5, pp. 1531–1537, 2011.

[93] J. Daugman, “High confidence visual recognition of persons by a test of sta-

tistical independence,” IEEE Transactions on Pattern Analysis and Machine

Intelligence, vol. 5, pp. 1148–1161, 1993.

[94] A. Basit, M. Javed, and S. Masood, “Non-circular pupil localization in iris

images,” 2008 International Conference on Emerging Technologies, 2008.

[95] K. Nishino and S. Nayar, “Eyes for relighting,” ACM Transactions Graph,

vol. 23, pp. 704–711, 2004.

[96] A. Ferreira, A. Kiurenco, B. Pinto, and J. Tendeiro, “Modifications and

improvements on iris recognition,” Proc INSTICC International Conf. on

Bio-inspired Systems and Signal Processing - Biosignals, vol. 1, pp. 72–79,

2009.

[97] R. Wildes, “Iris recognition: An emerging biometric technology,” Proceedings

of IEEE, vol. 85, pp. 1348–1363, 1997.

[98] J. Cui, Y. Wang, T. Tan, L. Ma, and Z. Sun, “A fast and robust iris locali-

sation method based on texture segmentation,” SPIE Defense and Security

Symposium, vol. 5404, pp. 401–408, 2004.

192

REFERENCES

[99] C. Daouk, L. El-Esber, F. Kammoun, and M. Al-Alaoui, “Iris recognition,”

IEEE ISSPIT, pp. 558–562, 2002.

[100] T. Moravik, E. Bubenikova, and L. Muzikarova, “Detection of determined

eye features in digital image,” International Journal of Engineering, pp.

155–160, 2011.

[101] Y. Shen, M. Zhang, J. Yue, and Y.H.M, “A new iris locating algorithm,”

International Conference on Artificial Reality and Telexistence Workshops

(UCAT’06), pp. 438–441, 2006.

[102] Q. Haq, M. Javed, and Q. Haq, “Efficient and robust approach of iris recog-

nition through fisher linear discriminant analysis method and principal com-

ponent analysis method,” Proceedings of the 12th IEEE International Mul-

titopic Conference, pp. 218–225, 2008.

[103] B. Bonney, R. Ives, D. Etter, and Y. Du, “Iris pattern extraction using bit

planes and standard deviations,” IEEE, pp. 582–586, 2010.

[104] H. Mehrabian and P. Hashemi-Tari, “Pupil boundary detection for iris recog-

nition using graph cuts,” Proceedings of Image and Vision Computing, pp.

77–82, 2007.

[105] A. Basit and M. Javed, “Localization of iris in gray scale images using in-

tensity gradient,” Optics and Lasers in Engineering, vol. 45, pp. 1107–1114,

2007.

[106] N.Barzegar and M. Moin, “A new approach for iris localization in iris recog-

nition systems,” IEEE, pp. 516–523, 2008.

[107] L. Masek, “Recognition of human iris patterns for biometric identification,”

The University of Western Australia, Tech. Rep., 2003.

[108] N. Ritter, “Location of the pupil-iris border in slit-lamp images of the

cornea,” Proceedings of the International Conference on Image Analysis and

Processing, 1999.

193

REFERENCES

[109] T. Chanwimaluang and G. Fan, “An efficient blood vessel detection algo-

rithm for retinal images using local entropy thresholding,” Proceedings of

the 2003 International Symposium on Circuits and Systems, vol. 5, pp. 21–

24, 2003.

[110] J. Rahebi and F. Hardalac, “Combination of matched filter and gabor filter

for retinal vessel extraction,” Life Science Journal, vol. 10, pp. 483–486,

2013.

[111] B. Zhang, L. Zhang, L. Zhang, and F. Karray, “Retinal vessel extraction by

matched filter with first-order derivative of gaussian,” Compu. Biol. Med.,

vol. 40, no. 4, pp. 438–45, 2010.

[112] A. Banumathi, R. Devi, Raju, and V. Kumar, “Performance analysis of

matched filter techniques for automated detection of blood vessels in retinal

images,” Conference on Convergent Technologies for the Asia-Pacific Region

(TENCON), vol. 2, pp. 543 – 546, 2003.

[113] D. Fiorin and A. Ruggeri, “Computerized analysis of narrow-field rop images

for the assessment of vessel caliber and tortuosity,” 33rd Annual Interna-

tional Conference of the IEEE EMBS, pp. 2622–2625, 2011.

[114] M. Zhang and J. Liu, “Directional local contrast based blood vessel detection

in retinal images,” ICIP, pp. 317–320, 2007.

[115] P. Siddalingaswamy and K. Prabhu, “Automatic detection of multiple ori-

ented blood vessels in retinal images,” Journal of Biomedical Science and

Engineering, vol. 3, pp. 101–107, 2010.

[116] P. Bankhead, C. Scholfield, J. G. McGeown, and T. Curtis, “Fast retinal ves-

sel detection and measurement using wavelets and edge location refinement,”

PLoS One, vol. 7, 2012.

[117] D. Selvathi and N. Balagopal, “Detection of retinal blood vessels using

curvelet transform,” International Conference on Devices, Circuits and Sys-

tems (ICDCS), pp. 325 – 329, 2012.

194

REFERENCES

[118] L. Xu and S. Luo, “A novel method for blood vessel detection from retinal

images,” Biomedical Engineering Online, vol. 9, no. 14, 2010.

[119] A. Dehghani, H. Abrishami-Moghaddam, and M. Moin, “Optic disc local-

ization in retinal images using histogram matching,” Journal on Image and

Video Processing, vol. 19, 2012.

[120] G. Sekar and P. Nagarajan, “Localisation of optic disc in fundus images

by using clustering and histogram techniques,” International Conference on

Computing, Electronics and Electrical Technologies, pp. 584–589, 2012.

[121] A. Youssif, A. Ghalwash, and A. Ghoneim, “Optic disc detection from nor-

malized digital fundus images by means of a vessels’ direction matched filter,”

IEEE Trans Med Imag, vol. 27, pp. 11–18, 2008.

[122] A. Mendonca, A. Sousa, L. Mendonca, and A. Campilho, “Automatic local-

ization of the optic disc by combining vascular and intensity information,”

Computerized Medical Imaging and Graphics, 2013.

[123] X. Zhu, R. Rangayyan, and A. Ells, “Detection of the optic nerve head in

fundus images of the retina using the hough transform for circles,” Journal

of Digital Imaging, vol. 23, pp. 438–453, 2010.

[124] R. Rangayyan, X. Zhu, and F. Ayres, “Detection of the optic nerve head in

fundus images of the retina with gabor filters and phase portrait analysis,”

Journal of Digital Imaging, vol. 23, pp. 438–453, 2010.

[125] D. Welfer, J. Scharcanski, C. Kitamura, M. D. Pizzol, L. Ludwig, and

D. Marinho, “Segmentation of the optic disk in color eye fundus images

using an adaptive morphological approach,” Comput. Biol. Med, vol. 40, pp.

124–137, 2010.

[126] H. Yu, E. Barriga, C. Agurto, S. Echegaray, M. S. Pattichis, W. Bauman, and

P. Soliz, “Fast localization and segmentation of optic disk in retinal images

using directional matched filtering and level sets,” IEEE Transactions on

Information Technology in Biomedicine, vol. 16, pp. 644–657, 2012.

195

REFERENCES

[127] G. Joshi, J. Sivaswamy, and S. R. Krishnadas, “Optic disk and cup segmen-

tation from monocular color retinal images for glaucoma assessment,” IEEE

Transactions on Medical Imaging, vol. 30, pp. 1192–1205, 2011.

[128] Y. Tang, X. Li, A. Von-Freyberg, and G. Goch, “Automatic segmentation of

the papilla in a fundus image based on the c-v model and a shape restraint,”

International Conference on Pattern Recognition(ICPR), pp. 183–186, 2006.

[129] M. Esmaeili, H. Rabbani, and A. M. Dehnavi, “Automatic optic disk bound-

ary extraction by the use of curvelet transform and deformable variational

level set model,” Pattern Recognition, vol. 45, pp. 2832–2842, 2012.

[130] D. Wong, J. Liu, N. Tan, F. Yin, X. Cheng, G. Cheung, M. Bhargava, and

T. Wong, “Automatic localization of the macula in a supervised graph-based

approach with contextual superpixel features,” 21st International Confer-

ence on Pattern Recognition(ICPR), pp. 2063 – 2066, 2012.

[131] J. Kaur and H. Sinha, “Automated localisation of optic disc and macula from

fundus images,” International Journal of Advanced Research in Computer

Science and Software Engineering, vol. 2, pp. 242–249, 2012.

[132] P. West, “A roadmap for building a machine vision system,” Automated

Vision Systems, Inc. in www.pulnix.com.

[133] D. Industry. (2014) Frame grabbers. [Online]. Available: http://www.

directindustry.com/industrial-manufacturer/frame-grabber-78230.html

[134] T.-V. Project. (2014) Methods to evaluate segmentation and indexing

techniques in the field of retinal ophthalmology. [Online]. Available:

http://messidor.crihan.fr/index-en.php

[135] U. of Lincoln. (2010) Review: retinal vessel image set for estimation of

widths. [Online]. Available: http://reviewdb.lincoln.ac.uk/

[136] T. U. of Iowa, B. v. G. the ROC organizers (Michael D. Abramoff, and

M. Niemeijer). (2007) Retinopathy online challenge. [Online]. Available:

http://webeye.ophth.uiowa.edu/ROC/var.1/www/

196

http://www.directindustry.com/industrial-manufacturer/frame-grabber-78230.html

http://www.directindustry.com/industrial-manufacturer/frame-grabber-78230.html

http://messidor.crihan.fr/index-en.php

http://reviewdb.lincoln.ac.uk/

http://webeye.ophth.uiowa.edu/ROC/var.1/www/

REFERENCES

[137] T. U. o. B. School of Computer Science. Collection of multispectral images

of the fundus. [Online]. Available: http://www.cs.bham.ac.uk/research/

projects/fundus-multispectral/

[138] M. Dobes and L. Machala. (2004) Upol iris image database. [Online].

Available: http://phoenix.inf.upol.cz/iris/

[139] J. Staal, M. Abramoff, M. Niemeijer, M. Viergever, and B. V. Ginneken,

“Ridge based vessel segmentation in color images of the retina,” IEEE Trans-

actions on Medical Imaging, vol. 23, pp. 501–509, 2004.

[140] A. Hoover, V. Kouznetsova, and M. Goldbaum, “Locating blood vessels in

retinal images by piece-wise threhsold probing of a matched filter response,”

IEEE Transactions on Medical Imaging, vol. 19, no. 3, pp. 203–210, 2000.

[141] A. Hoover and M. Goldbaum, “Locating the optic nerve in a retinal image

using the fuzzy convergence of the blood vessels,” IEEE Transactions on

Medical Imaging, vol. 22, no. 8, pp. 951–958, 2003.

[142] P. Saine and M. Tyler, Ophthalmic Photography: Retinal Photography, An-

giography, and Electronic Imaging, 2nd ed. USA: Butterworth-Heinemann

Medical, 2001.

[143] Hecht and Eugene, Optics, 2nd ed. Addison Wesley, 1987.

[144] R. W. R.C. Gonzalez, Digital Image Processing. New Jersey: Pearson

Prentice Hall, 2008.

[145] M. Sonka, V. Hlavac, and R. Boyle, Image Processing, Analysis, and Machine

Vision. USA: Thomson, 2008.

[146] M. Zhang and J. Liu, “Directional local contrast based blood vessel detec-

tion in retinal images,” IEEE International Conference on Image Processing

(ICIP), pp. IV–317 – IV–320, 2007.

[147] M. Al-Rawi, M. Qutaishat, and M. Arrar, “An improved matched filter for

blood vessel detection for digital retinal images,” Computers in Biology and

Medicine, vol. 37, pp. 262–267, 2007.

197

http://www.cs.bham.ac.uk/research/projects/fundus-multispectral/

http://www.cs.bham.ac.uk/research/projects/fundus-multispectral/

http://phoenix.inf.upol.cz/iris/

REFERENCES

[148] N. OTSU, “A threshold selection method from gray-level histograms,” IEEE

Trans. Syst. Man Cybern, vol. 9, pp. 62–66, 1979.

[149] H. Ng, “Automatic thresholding for defect detection.” Pattern Recognition

Lett., vol. 27, p. 16441649, 2006.

[150] P. Richard, “Iris recognition: an engineering biometric,” Proceeding of the

IEEE, pp. 1354–1356, 1997.

[151] M. Brewer, “A modelling approach for bandwidth selection in kernel density

estimation,” COMPSTAT, pp. 203–208, 1998.

[152] Z.Zhang, F.S.Yin, J.Liu, W.K.Wong, N.M.Tan, B.H.Lee, J.Cheng, and

T.Y.Wong, “Origa-light : An online retinal fundus image database for glau-

coma analysis and research.” 32 nd Annual International Conference of the

IEEE EMBS, pp. 3065–3068, 2010.

[153] I. Kasa, “A curve fitting procedure and its error analysis.” IEEE Trans. Inst.

Meas., vol. 25, pp. 8–14, 1976.

[154] D. Chang and W. Wu, “Image contrast enhancement based on a histogram

transformation of local standard deviation,” IEEE Transactions on Medical

Imaging, vol. 17, no. 4, pp. 518–531, 1998.

[155] M. Aarthy and et al, “International journal of computer science and mobile

applications,” IEEE Transactions on Medical Imaging, vol. 2, no. 3, pp.

25–34, 2014.

[156] Zuiderveld and Karel, Contrast Limited Adaptive Histograph Equalization.

Graphic Gems IV. San Diego: Academic Press Professional, 1994.

[157] D. Grigera, “Clinical estimation of opric disc size,” Glaucoma Now, pp. 10–

11, 2011.

[158] S. Zeki, J. Dudgeon, and G. Dutton, “Reaooraisal of ratio of disc to mac-

ula/disc diameter in optic nerve hypoplasia,” Br J Ophthalmol, vol. 75, pp.

538–541, 1991.

198

REFERENCES

[159] J. Jonas, G. Gusek, and G. Noumann, “Optic disc, cup and neuroretinal rim

size, configuration and correlations in normal eyes,” Investigative Ophthal-

mology and Visual Science, vol. 29, no. 7, 1988.

[160] M. Nicolela, “Optic nerve: Clinical examination,” in Pearls of Glaucoma

Management, J. Giaconi, Ed. Berlin Heidelberg: Springer-Verlag, 2010.

[161] S. Manoj, Muralidharan, and P. M. Sandeep, “Neural network based classi-

fier for retinal blood vessel segmentation,” International Journal of Recent

Trends in Electrical and Electronics Engineering, vol. 3, pp. 44–53, 2013.

[162] K. Rohrschneider, “Determination of the location of the fovea on the fun-

dus,” Investigative Ophthalmology and Visual Science, vol. 45, no. 9, pp.

3257–3258, 2004.

[163] G. Rajput, P. Patil, and R. Chavan, Automatic detection of microaneurysms

from fundus images using morphological operations. Springer, 2013.

[164] D. Koozekanani, K. Boyer, and C. Roberts, “Retinal thickness measurements

from optical coherence tomography using markov boundary model,” IEEE

Transactions on Medical Imaging, vol. 20, no. 9, 2001.

199

APPENDIX A

Table ?? was used to plot the Figure 4.9. It was calculated using the Equation 4.12

indicating the relation between the index value of the angle of incidence and re-

fraction when light passes through two different materials.

n1sin(θ1) = n2sin(θ2) (1)

Table 1: Angle of light as it enters the eye (Incident Ray), passes through differentinterfaces within the eye and reaches the back of the eye (Refractive Ray).

Incident

Ray

(Degrees)

First

Interface

(Radians)

Second

Interface

(Radians)

Third

Interface

(Radians)

Fourth

Interface

(Radians)

Refractive

Ray

(Degrees)

0 0.00 0.00 0.00 0.00 0.00

5 0.07 0.06 0.06 0.07 3.74

10 0.13 0.13 0.12 0.13 7.46

15 0.19 0.19 0.18 0.19 11.16

20 0.26 0.25 0.24 0.26 14.82

25 0.32 0.30 0.30 0.32 18.43

30 0.37 0.36 0.36 0.37 21.96

35 0.43 0.41 0.41 0.43 25.40

40 0.48 0.46 0.46 0.48 28.74

45 0.53 0.51 0.50 0.53 31.93

50 0.57 0.55 0.54 0.57 34.96

200

. APPENDIX A

Incident

Ray

(Degrees)

First

Interface

(Radians)

Second

Interface

(Radians)

Third

Interface

(Radians)

Fourth

Interface

(Radians)

Refractive

Ray

(Degrees)

55 0.61 0.59 0.58 0.61 37.78

60 0.65 0.62 0.62 0.65 40.37

65 0.68 0.65 0.64 0.68 42.68

70 0.70 0.68 0.67 0.70 44.66

75 0.72 0.70 0.69 0.72 46.26

80 0.74 0.71 0.70 0.74 47.44

85 0.75 0.72 0.71 0.75 48.17

90 0.75 0.72 0.71 0.75 48.41

95 0.75 0.72 0.71 0.75 131.83

100 0.74 0.71 0.70 0.74 132.56

105 0.72 0.70 0.69 0.72 133.74

110 0.70 0.68 0.67 0.70 135.34

115 0.68 0.65 0.64 0.68 137.32

120 0.65 0.62 0.62 0.65 139.63

125 0.61 0.59 0.58 0.61 142.22

130 0.57 0.55 0.54 0.57 145.04

135 0.53 0.51 0.50 0.53 148.07

140 0.48 0.46 0.46 0.48 151.26

145 0.43 0.41 0.41 0.43 154.60

150 0.37 0.36 0.36 0.37 158.04

155 0.32 0.30 0.30 0.32 161.57

160 0.26 0.25 0.24 0.26 165.18

165 0.19 0.19 0.18 0.19 168.84

170 0.13 0.13 0.12 0.13 172.54

175 0.07 0.06 0.06 0.07 176.26

180 0.00 0.00 0.00 0.00 180.00

201

APPENDIX B

Following are the results obtained from conversion of the coloured images to their

corresponding gray scaled and indexed images.

Table 2: Gray Scaled and colour component separation of coloured images

Image Original Gray Scaled Red Band Green Band Blue Band

1

2

3

4

202

. APPENDIX B


5

6

7

8

9

10

11

12

203

. APPENDIX B


13

14

15

16

17

18

19

20

204

APPENDIX C

Following are the results obtained for the suggested approach in creating individual

masks for different images using the thresholding technique.

Table 3: Masks created for different images using Thresholding technique

ImageCreated

Mask

Masked Im-

ageImage

Created

Mask

Masked Im-

age

1 2

3 4

5 6

7 8

205

. APPENDIX C

ImageCreated

Mask

Masked Im-

ageImage

Created

Mask

Masked Im-

age

9 10

11 12

13 14

15 16

17 18

19 20

206

APPENDIX D

Following are the results obtained by implementing the 2D FFT filter.

Table 4: 2D FFT filtered images.

Image Gray Scaled Magnitude and Phase Plot Filtered

1

2

3

4

207

. APPENDIX D


5

6

7

8

9

10

11

12

208

. APPENDIX D


13

14

15

16

17

18

19

20

209

APPENDIX E

Following are the results obtained for sharpening the retinal images.

Table 5: Sharpening the retinal images using 2D FFT filtered images.

Image Gray Scaled FilteredSharpened-

10×5 kernel

Sharpened-

3×2 kernel

1

2

3

4

210

. APPENDIX E


10×5 kernel

Sharpened-

3×2 kernel

5

6

7

8

9

10

11

211

. APPENDIX E


10×5 kernel

Sharpened-

3×2 kernel

12

13

14

15

16

17

18

212

. APPENDIX E


10×5 kernel

Sharpened-

3×2 kernel

19

20

213

PLEASE NOTE

The following materials cannot be reproduced online and have been extracted: Ektesabi, A & Kapoor, A 2011, 'Exact pupil and iris boundary detection,' Control, Instrumentation and Automation (ICCIA), 2011 2nd International Conference on, 1217-1221. DOI: 10.1109/ICCIAutom.2011.6356835 Ektesabi, A & Kapoor, A 2012, 'Complication prevention of posterior capsular rupture using image processing techniques,' Proceedings of the World Congress on Engineering, 603-607. www.iaeng.org/publication/WCE2012/WCE2012_pp603-607.pdf Ektesabi, A & Kapoor, A 2014, 'Removal of Circular Edge Noise of Retinal Fundus Images,' Proceedings of the International Conference on Image Processing, Computer Vision, and Pattern Recognition (IPCV). http://world-comp.org/preproc2014/IPC3384.pdf

http://doi.org/10.1109/ICCIAutom.2011.6356835

http://www.iaeng.org/publication/WCE2012/WCE2012_pp603-607.pdf

http://world-comp.org/preproc2014/IPC3384.pdf

Image processing for detection of Cataract, Retinopathy of ...€¦ · After image acquisition, the rst image processing stage is the image pre-processing. The general processes such

Documents