6543

6108

كارشناسي ارشد

الكترونيك

اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر

1390

ده، 117ص.: مصور، جدول، نمودار

ص.ع. به فارسي و انگليسي

سعيد صدري، رسول امير فتاحي

مژگان مختاري

14/1/90

محمد علي خسروي فرد، بهزاد نظري

1396/10/10

كتابنامه

برق و كامپيوتر

مهندسي برق و كامپيوتر

ID6108

به فارسي و اگليسي: قابل رويت در نسخه ديجيتالي

Detection of Collagenous Colitis Based On Histopathology Image Segmentation of Colon Vahid Malekian V malekian@ec iut ac ir Date of submission 2011 9 12 Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language FarsiSupervisors Saeed Sadri sadri@cc iut ac irRasoul Amirfattahi fattahi@cc iut ac irAbstractIn recent years digestive colon diseases have increased dramatically A category of common digestivediseases are Colitis In medicine Colitis refers to inflammation of the colon Collagenous Colitis is a type ofmicroscopic colitis which is characterized by chronic and intense diarrhea While this change is normal inmacroscopic view of the colon tissue it is abnormal in the microscopic view Routine tests like blood testsand parasite tests cannot be used for diagnosis The only method of diagnosis is sampling of the colon duringcolonoscopy and measuring the thickness of collagen band by Pathologist which is obtained throughmicroscope images Thickness of collagen band in the colon tissue of a patient is more than 10 micrometers This change of collagen thickness in sub epithelial may occur anywhere in colon tissue so pathologists needto sample several areas of colon tissue and measure the thickness of the collagen band Now this procedure isdone manually which leads to fatigue and loss of accuracy of pathologists In this thesis we take highresolution images from tissue samples in order to develop the algorithm which can extract collagen bandfrom colon tissue and measure the thickness of the collagen band accurately The proposed algorithm wasdesigned in a way to make it resistant to the changes of environmental conditions and acceptably flexible tosegment colon tissue images Due to the fact that the image segmentation of colon tissues needs to have highlevel quality the first step is preprocessing Then the color and texture features must be extracted from theimage After that the optimum features which perform better in the separation of target and nontarget imagesamples are selected through the Adaboost feature selector In the next step accurate optimized classifier isused to separate collagen band from the colon tissue Through several different methods in this research MLP neural network is obtained as the most efficient way In the last step after completing segmentation byusing appropriate algorithms the thickness of collagen band is measured along the axis passing through itsarea Performance of the proposed algorithm and accuracy of the results have been confirmed by apathologist Keywords Collagenous colitis Image segmentation Feature extraction Classification MLP Neural network

سعيد صدري، رسول امير فتاحي

مژگان مختاري

محمد علي خسروي فرد، بهزاد نظري