Biomedical images processing and analysis

Biomedical images processing and analysisBiomedical images processing and analysis

Group members

Massimo De LucaMassimo De Luca (2003-) Fellowship – PhD student

Marco ForacchiaMarco Foracchia (-2003) PhD student

Alfredo GianiAlfredo Giani (2003-) Post doc

Enrico GrisanEnrico Grisan PhD student – Post doc

Lorenzo MarafattoLorenzo Marafatto (2005-) Fellowship

Alfredo RuggeriAlfredo Ruggeri Associate professor

Biomedical images processing and analysis

Cooperations

J. JaroszewskiJ. Jaroszewski - Cornea Bank Berlin, Clinic of Ophthalmology, University School of Medicine, Berlin, Germany

A. NeubauerA. Neubauer - Dept. of Ophthalmology, Ludwig Maximilians University, Munich, Germany

S. PiermarocchiS. Piermarocchi – Dept. of Ophthalmology, University of Padova

D. PonzinD. Ponzin - Veneto Eye Bank Foundation, Venice, Italy

A. PocobelliA. Pocobelli - Eye Bank, S. Giovanni-Addolorata Hospital, Rome, Italy

P. GainP. Gain - Ophthalmology Department, Bellevue Hospital, Saint-Etienne, France

A. BezerianosA. Bezerianos - Dept. of Medical Physics, University of Patras, Greece

G. BarbaroG. Barbaro - Nidek Technologies, Padova, Italy

P. FavaroP. Favaro - Siemens Corporate Research, Princeton (NJ), USA

Biomedical images processing and analysis

Publications

Biomedical images processing and analysis

0

1

2

3

4

5

6

7

8

2001 2002 2003 2004 2005

International Journals

Conference Papers

Conference Abstracts

Funding

University of Padova: € 60.000 (shared)

University of Padova: € 15.000

Ministry of University: € 20.000

Nidek Technologies: € 25.000

CARIPARO Bank Foundation: € 40.000

Biomedical images processing and analysis

Biomedical images processing and analysis

1.Cell contour recognition for in-vivo microscopy of corneal endothelium

Statistical Correction

Band-Pass Filtering

ROI extraction

Skeletonization

Contour completion

Correction

Perimeter extraction

ANN contour extraction

Hole removal and Erosion

Cell contour recognition

Statistical Correction

Band-Pass Filtering

ROI extraction

Skeletonization

Contour completion

Correction

Perimeter extraction

ANN contour extraction

Hole removal and Erosion

Cell contour recognition

Statistical Correction

Band-Pass Filtering

ROI extraction

Skeletonization

Contour completion

Correction

Perimeter extraction

ANN contour extraction

Hole removal and Erosion

Cell contour recognition

Statistical Correction

Band-Pass Filtering

ROI extraction

Skeletonization

Contour completion

Correction

Perimeter extraction

ANN contour extraction

Hole removal and Erosion

Cell contour recognition

Statistical Correction

Band-Pass Filtering

ROI extraction

Skeletonization

Contour completion

Correction

Perimeter extraction

ANN contour extraction

Hole removal and Erosion

Cell contour recognition

Statistical Correction

Band-Pass Filtering

ROI extraction

Skeletonization

Contour completion

Correction

Perimeter extraction

ANN contour extraction

Hole removal and Erosion

Cell contour recognition

Statistical Correction

Band-Pass Filtering

ROI extraction

Skeletonization

Contour completion

Correction

Perimeter extraction

ANN contour extraction

Hole removal and Erosion

Cell contour recognition

Statistical Correction

Band-Pass Filtering

ROI extraction

Skeletonization

Contour completion

Correction

Perimeter extraction

ANN contour extraction

Hole removal and Erosion

Cell contour recognition

Statistical Correction

Band-Pass Filtering

ROI extraction

Skeletonization

Contour completion

Correction

Perimeter extraction

ANN contour extraction

Hole removal and Erosion

Cell contour recognition

• The ENDO software is a module of the system for ophthalmology.

Nidek Technologies NAVIS-ENDO system

A glimpse of tomorrow …

Biomedical images processing and analysis

2.Fourier analysis for the estimation of cell density on eye bank images of donor corneas

AIM:• to develop a fully automatic technique for cell density

estimation (no user intervention).

2250 cell/mm2

Fully automatic density estimation

• It must be without cell contour detection.

A repetitive pattern of cell borders is clearly visible.

Spatial frequency of this pattern is proportional to cell density.

Frequency information is available through Fourier analysis.

Information from Fourier analysis can provide an estimation of cell density.

Frequency-based density estimation

A circular band indicates that the endothelium image contains a repetitive pattern at a specific frequency.

Spatial frequency is the radius of the bandSpatial frequency is the radius of the band

Gray-scale image of 2D-DFT log-magnitude.

Radius of circular band can be used to estimate cell density.

Frequency-based density estimation

Position of second peak provides estimated frequency f of cell borders.

Frequency-based density estimation

1500

2000

2500

3000

3500

1500 2000 2500 3000 3500

Manual density (cell/mm2)

Auto

matic d

ensity (cell/

mm

2)

Frequency-based density estimation

(Ruggeri et al., Br J Ophthalmol, Mar 05)

• The EyeBank software is a module of the

system for ophthalmology.

Nidek Technologies NAVIS-EyeBank system

3. Tracking techniques for vessel-like structure

Biomedical images processing and analysis

Applications to:

• vessels in retina

• nerves in cornea

Clinical outcomes:• length• tortuosity• bifurcations• caliber course• optic disc detection

Tracking techniques in retina

Tracking techniques in retina

Tracking techniques in cornea

Biomedical images processing and analysis

4.Methodologies in eye fundus analysis for the diagnosis of retinopathy

Diabetic retinopathy characterized by fundus lesions

Automatic and objective tools:• wide screening • disease assessment &

monitoring in time• (new) drugs efficacy

Three steps:

1. Detection

2. Classification & measurement

3. Clinical assessment

Eye fundus analysis

Biomedical images processing and analysis

5.Design and realization of an adaptive optics fundus camera

Flashpath

Wavefrontsensor

RetinalImaging

Eye

Image Processing

Biomedical images processing and analysis

5.Design and realization of an adaptive optics fundus camera

Imageacquisition Coma Defocus Astigmatism

Imagecorrected

Image Analysis

Mirrorupdate

Biomedical images processing and analysis

6.Bio-inspired omni-directional vision

Omnidirectional mirror

Space variant sensorproviding with a foveated vision

Development ofbiomimeticalgorithmsfor vision