Iterative Fuzzy Clustering Regions of Interest in Skin Lesions

13
Iterative Fuzzy Clustering Regions of Interest in Skin Lesions By R. Cucchiara, C. Grana, M. Piccardi Presented by Mohammed Jirari October 23 rd , 2002 Image Processing Lab

description

Iterative Fuzzy Clustering Regions of Interest in Skin Lesions. By R. Cucchiara, C. Grana, M. Piccardi Presented by Mohammed Jirari October 23 rd , 2002 Image Processing Lab. Introduction. Definition of Skin Melanoma Systems used for Melanoma diagnosis Recent research. - PowerPoint PPT Presentation

Transcript of Iterative Fuzzy Clustering Regions of Interest in Skin Lesions

Page 1: Iterative Fuzzy Clustering Regions of Interest in Skin Lesions

Iterative Fuzzy Clustering Regions of Interest in Skin Lesions

By R. Cucchiara, C. Grana, M. Piccardi

Presented by Mohammed Jirari October 23rd, 2002

Image Processing Lab

Page 2: Iterative Fuzzy Clustering Regions of Interest in Skin Lesions

Introduction Definition of Skin Melanoma Systems used for Melanoma

diagnosis Recent research

Page 3: Iterative Fuzzy Clustering Regions of Interest in Skin Lesions

Method used in paper Preprocessing Karhunen-Loeve transform Fuzzy c-means clustering Topological tree

Page 4: Iterative Fuzzy Clustering Regions of Interest in Skin Lesions

Preprocessing Convolve the image with a

Gaussian kernel with standard deviation of one pixel.

Transform images from original RGB into CIE L*a*b* color coordinates.

Page 5: Iterative Fuzzy Clustering Regions of Interest in Skin Lesions

Karhunen-Loeve transform Projection of the vectors to be

reduced on the eigenvectors of their covariance matrix using the following:

M

k

Txx

Tkkx

M

kkx

mmxxM

C

xM

m

1

1

1

1

Page 6: Iterative Fuzzy Clustering Regions of Interest in Skin Lesions

Karhunen-Loeve transform (cont.) The Karhunen-Loeve transform of

vector x is defined by:

xmxAy

Page 7: Iterative Fuzzy Clustering Regions of Interest in Skin Lesions
Page 8: Iterative Fuzzy Clustering Regions of Interest in Skin Lesions

Fuzzy c-means clustering Use the following 2 recurrent

equations:

M

k

mik

M

kk

mik

i

mc

ijj

jk

ikik

U

xUv

vx

vxU

1

1

1

1

1

12

2

1

Page 9: Iterative Fuzzy Clustering Regions of Interest in Skin Lesions

Topological tree Bright clusterHealthy skin Dark cluster Lesion

Page 10: Iterative Fuzzy Clustering Regions of Interest in Skin Lesions

Topological tree (cont.) Def1:Skin region of Interest(Skin ROI)

a set of pixels of the skin image exhibiting 3 properties: uniform color, connected pixels and significant area.

Def2:Topological Tree(TT)a tree whose nodes are skin ROIs and the arcs topological inclusion relationships between skin ROIs

Page 11: Iterative Fuzzy Clustering Regions of Interest in Skin Lesions

Pseudo-code of the algorithmAnalyzeRegion (region R, node N){if(not StopCondition (R)){

[C1,C2]=FCM(R);

[Cint,Cext]=VerifyInclusion([C1,C2]);

if(exists([Cint,Cext])){

Cres=R-Cint-Cext;

Nnew=AddNodeToTree(Cext,N);

for each C in ConnectedComponents(Cint)

AnalyzeRegion(C+Cres,Nnew);}else {

Analyzeregion(R-C1,N);

AnalyzeRegion(R-C2,N);}}

else AddNodeToTree(R,N);}

Page 12: Iterative Fuzzy Clustering Regions of Interest in Skin Lesions
Page 13: Iterative Fuzzy Clustering Regions of Interest in Skin Lesions