سال انتشار: ۱۳۹۰

محل انتشار: هفتمین کنفرانس ماشین بینایی و پردازش تصویر

تعداد صفحات: ۵

نویسنده(ها):

Vahid Malekian – Digital Signal Processing Research Lab., Department of Electrical and Computer Engineering, Isfahan University ofTechnology Isfahan, 84156-83111, Iran
Mojgan Mokhtari – School of Medicine, Isfahan University of Medical Sciences Isfahan, 73461-8174, Iran.
Saeid Sadri – Digital Signal Processing Research Lab., Department of Electrical and Computer Engineering, Isfahan University ofTechnology Isfahan, 84156-83111, Iran
Rasoul Amirfattahi – Digital Signal Processing Research Lab., Department of Electrical and Computer Engineering, Isfahan University ofTechnology Isfahan, 84156-83111, Iran

چکیده:

Collagenous colitis is prevalent among pathologicaldiseases. Because of normal radiological and endoscopicappearances, the microscopic image of colon tissue isnecessary and important material for investigation of thisdisease. In this paper, a computerized system is developed forcollagenous colitis diagnosis. First, colon tissues are coloredwith Mason trichrome to make sub-epithelial collagen bandto be appeared in blue. Second, preprocessing is done on themicroscopic image of colon tissue, and then Color histogramfeatures in HSV color space and Haar Wavelet energy indetail coefficients of sub-band images are implemented tocharacterize the histological structure representation fortissue classification. KNN Classifier is selected for thisclassification, which segments the sub-epithelial collagenband from the image, and finally, thickness of sub-epithelialcollagen band is determined by morphological operations.Abnormal case will be recognized if the thickness of subepithelialcollagen band be more than 10 μm. Fifty clinicalimage samples were employed in the training and testingprocedures for the evaluation of system performance.Through the applied classification it was revealed thatcollagenous colitis can be diagnosed accurately.