LEUKO: LEUKO: Computer Decision Computer Decision Support System for Support System for Leukemia Diagnosis Leukemia Diagnosis Daniela M. Ushizima
LEUKO:LEUKO:Computer Decision Computer Decision Support System for Support System for Leukemia DiagnosisLeukemia Diagnosis
Daniela M. Ushizima
2/4130-May-07 Computer Vision in Leukemia Diagnosis
MotivationMotivation• Leukemia = 30% cancer.
• Pattern recognition: low-cost alternative solution;
• Human visual analysis: • 79.3% to 92.3% correct (lymphocytes);
• 150 cells >> 10 minutes for an hematologist;
• Why lymphoproliferative diseases?
• Software for cell analysis and classification: • computer-aided automation;
• educational purposes;
3/4130-May-07 Computer Vision in Leukemia Diagnosis
SynopsisSynopsis1. Human blood cells2. Pattern recognition3. Feature selection4. Results5. Latest developments
5/4130-May-07 Computer Vision in Leukemia Diagnosis
1.1. 1.1. WhereWhere leukocytesleukocytes come come fromfrom??
6/4130-May-07 Computer Vision in Leukemia Diagnosis
LymphocyteMonocyte
Eosinophil Neutrophil Basophil
1.2. Normal leukocytes1.2. Normal leukocytes
7/4130-May-07 Computer Vision in Leukemia Diagnosis
Prolymphocyte
CLLHairy-cell
1.3. Malignant cells1.3. Malignant cells
2.1. Steps in PR design2.1. Steps in PR design
Segmentation
Pre processing
Featureextraction
Classification
Classes
Classes compare
Criteriumfunction
Humanexpertise
Examples
DigitalImage
Feature selection
f={ff={f00,f,f11,…,f,…,fnn--11}}
10/4130-May-07 Computer Vision in Leukemia Diagnosis
2.2. Segmentation2.2. Segmentation
segmentsegment
• Regions of interest: nucleus, cytoplasm, red blood cells and background
11/4130-May-07 Computer Vision in Leukemia Diagnosis
2.2.1. Methods2.2.1. Methods
• G channel thresholding: where is the nucleus?
• Color segmentation: where are the leukocyte and RBCs?
12/4130-May-07 Computer Vision in Leukemia Diagnosis
Green levels
Abs
olut
e fr
eque
ncy
180 200 220 100 98 90 95 95 180 230 221 160 82 95 93 90 230 200 220 100 99 85 82 96
10 200 220 100 50 30 35 25 10 230 221 160 32 35 23 10 20 200 220 100 50 30 35 25
10 200 22 100 50 30 35 25 230 22 160 32 35 23 10 13 100 120 200 15 0 35 25 0
2.2.2. 2.2.2. ThresholdingThresholding
13/4130-May-07 Computer Vision in Leukemia Diagnosis
14/4130-May-07 Computer Vision in Leukemia Diagnosis
Katz (2000)
15/4130-May-07 Computer Vision in Leukemia Diagnosis
Sabino et al (2003)
16/4130-May-07 Computer Vision in Leukemia Diagnosis
2.2.3. Color segmentation2.2.3. Color segmentation
trainr
g
b
modelµ,σ
r
g
b
18/4130-May-07 Computer Vision in Leukemia Diagnosis
• Image properties;• Nucleus and cytoplasm attributes;• Shape;• Size;• Color;• Texture.
2.3. Feature extraction2.3. Feature extraction
Traditional measures
Subjective descriptions
Shape and sizeShape and size
TextureTexture
ColorColor
20/4130-May-07 Computer Vision in Leukemia Diagnosis
2.3.1. Shape and size2.3.1. Shape and size
• Nucleus-cytoplasm ratio (NC):• NC=Anuc/(Anuc+Areacit)
• Factor form=compactness measure (C):• C=P2/A
• Curvature (k):• Concave and convexity points;• Bending Energy (B): 2
1
1 ( )P
tB k t
P == ∑
21/4130-May-07 Computer Vision in Leukemia Diagnosis
2.3.2. Fractal dimension2.3.2. Fractal dimension•• CostaCosta: multiscale fractal dimension (2D) curve and
its peak (FDmax) for complexity description of neurons;
22/4130-May-07 Computer Vision in Leukemia Diagnosis
23/4130-May-07 Computer Vision in Leukemia Diagnosis
2.3.2. 2.3.2. FDFDmaxmax -- the methodthe method
Radius
Cum
mV
f1
ln(Radius)
l n( C
umm
V)
f2=ln(f1)
ln(Radius)
Fra
cD
i m
Peak of max fractality Scale of max fractality Width of max fractality
Multiscale fractal dimension
ln(Radius)
Fra
cD
i m
ln(Radius)
Fra
cD
i m
ln(Radius)
Fra
cD
i m
f3=3-d(f2)dr
24/4130-May-07 Computer Vision in Leukemia Diagnosis
2.3.2. Gray Level 2.3.2. Gray Level CoocurrenceCoocurrence MatrixMatrix
• Joint probability distribution of 2 pixels given a displacement (direction+distance) and a window;
• Spatial distribution and spatial dependence.
0 0 1 1 10 0 1 1 10 2 2 2 22 2 3 3 3
d = (1,0) & w = m x n2 0 0 02 4 0 01 0 4 0 0 0 1 2
I(m,n) = gray levels GLCM(i,j) = gray level transitions ratenumber of transitions
ji
nm
25/4130-May-07 Computer Vision in Leukemia Diagnosis
2.3.2. GLCM2.3.2. GLCM
2
1 1( , )( )
g gN N
i jInertia p i j i j
= =
= −∑∑
1 1
( , ) log( ( , ))g gN N
i j
Entropy p i j p i j= =
= −∑∑
21 1
1 ( , )1 ( )
g gN N
i j
Homogeneity p i ji j= =
=+ −∑∑
Haralick (1976)
2
1 1
( , )g gN N
i j
Energy p i j= =
=∑∑
26/4130-May-07 Computer Vision in Leukemia Diagnosis
2.3.3. Color2.3.3. Color
Pratt (1991), Song et al (1997)
b
N(b)
27/4130-May-07 Computer Vision in Leukemia Diagnosis
2.4. 2.4. LeukoLeuko classificationclassification
• Learning: supervised;• Decision rule: maximum likelihood;• Pdf estimation: parametric;• Pdf: Gaussian;• Error estimation methods regarded:
• Resubstituion, holdout, cross-validation,leave-one-out.
28/4130-May-07 Computer Vision in Leukemia Diagnosis
29/4130-May-07 Computer Vision in Leukemia Diagnosis
31/4130-May-07 Computer Vision in Leukemia Diagnosis
3. Feature selection3. Feature selection
• Problems of dealing with many features:• Overfitting (decision surface = many details)• Overtraining (decision surface = few details)• Curse of dimensionality (lacking samples);• Peaking phenomena.
• ∴ Define feature subsets using strategies:• Exaustive;• Heuristics;• Random;
32/4130-May-07 Computer Vision in Leukemia Diagnosis
3. Feature selection3. Feature selection
33/4130-May-07 Computer Vision in Leukemia Diagnosis
35/4130-May-07 Computer Vision in Leukemia Diagnosis
4. Results4. Results• Differentiation among 6 types
of leukocytes, including the CLL (the most common leukemia in adults from Western);
• Project and development of pattern recognition and feature selection tools.
37/4130-May-07 Computer Vision in Leukemia Diagnosis
5.1. 5.1. LeukoLeuko + SVM+ SVM
•• SVM extension to SVM extension to multiclassmulticlasstask, applying treetask, applying tree--based based strategy;strategy;
• SVM and minimum spanning tree:• Adapted version of Kruskal
algorithm• Generates a tree in a bottom-up
iterative way• Polynomial complexity
• Including weight assignment• Allows the automatic determination
of the multiclass tree.
1
2 5
3 4
1
0
23
45
6
7
8
9
Graph G
1
2
3 4
1
0
4 5
MST T
2
38/4130-May-07 Computer Vision in Leukemia Diagnosis
5.1. 5.1. LeukoLeuko accuracyaccuracyCNPq
39/4130-May-07 Computer Vision in Leukemia Diagnosis
• γ(t) = boundary of the nucleus in Ф(x,t=0)• Фt + F| Ф| = 0
F 1 1 G I
5.2. Level set5.2. Level set
40/4130-May-07 Computer Vision in Leukemia Diagnosis
• Given C, the set of points of the nucleus contour and p∈ C: DC(p) = min(d(p,q))
• If 0
41/4130-May-07 Computer Vision in Leukemia Diagnosis
42/4130-May-07 Computer Vision in Leukemia Diagnosis
UshizimaUshizima et al., Leukocyte detection using nucleus contour et al., Leukocyte detection using nucleus contour propagation, LNCS 4091:389propagation, LNCS 4091:389--396, 2006.396, 2006.
43/41
HematlasHematlas
44/41Leukocyte detection using nucleus contour propagation
Acknowledgments:Acknowledgments:• Unisantos: Profa. Marta Rosatelli, Daniella, Rodrigo, Aline, Rafael• NIH: Dr. Edgar Rizzatti e Dr. Rodrigo Calado• Instituto Fleury: Dr. Sérgio Martins• Universidade de Sao Paulo: Prof. André Carvalho e Ana• Universidade Federal de Santa Maria: Prof Marcos e Luciana• Universidade Federal do Ceará: Profa Fátima Medeiros
Contact:Contact:
45/4130-May-07 Computer Vision in Leukemia Diagnosis
46/4130-May-07 Computer Vision in Leukemia Diagnosis