segmentation evaluatation

gets label matrix of a tissue in segmented and ground truth and returns similarity indices

Description

[Jaccard,Dice,rfp,rfn]=sevaluate(m,o)
gets label matrix for one tissue in segmented and ground truth
and returns the similarity indices
m is a tissue in gold truth
o is the same tissue in segmented image
rfp false pasitive ratio
rfn false negative ratio

• MATLAB release: MATLAB 7.4 (R2007a)

[Arjun]

I=imread('cancer1.jpg');
J = rgb2gray(I);
A=imread('cancer2.jpg');
B = rgb2gray(A);
m = bwlabeln(J)
o = bwlabeln(A);
m=m(:);
o=o(:);
common=sum(m & o);
union=sum(m | o);
cm=sum(m); % the number of voxels in m
co=sum(o); % the number of voxels in o
Jaccard=common/union;
Dice=(2*common)/(cm+co);
rfp=(co-common)/cm;
rfn=(cm-common)/cm;

Error in ==> eval at 9
common=sum(m & o);

[rekoba]

first thanks for ur code, second , i'm working on project in medical image segmentation , using fuzzy c mean, my question is how to use segmentation evaluation image, i must use same algorithm in gold truth image and on segmented image and then evaluate i work on brainweb image and segment it into GM,WM,CSF