پديد آورنده :
هاشمي عمروآبادي، مسعود
عنوان :
طراحي سيستم بازشناسي اتوماتيك تومورهاي سرطاني از روي تصاوير ماموگرام
مقطع تحصيلي :
كارشناسي ارشد
محل تحصيل :
اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر
صفحه شمار :
ده، 151، [II]ص.: مصور، جدول، نمودار
يادداشت :
ص. ع. به فارسي و انگليسي
استاد راهنما :
محمدرضا احمدزاده
استاد مشاور :
علي حكمت نيا
توصيفگر ها :
سرطان سينه , ماموگرافي ديجيتال﴿FFDM) , ماهيچه پكتورال
تاريخ نمايه سازي :
05/06/87
استاد داور :
سعيد صدري ، رسول امير فتاحي
تاريخ ورود اطلاعات :
1396/03/06
رشته تحصيلي :
برق و كامپيوتر
دانشكده :
مهندسي برق و كامپيوتر
چكيده فارسي :
به فارسي و انگليسي: قابل رؤيت در نسخه ديجيتال
چكيده انگليسي :
Abstract Breast cancer is one of the leading causes of deaths among women Mammography iscurrently the best method for early detection Using low dose x ray in mammography thebreast tissue type and different kinds of lesions make the detection of lesions inmammograms very ambiguous and tedious work Early detection is the most effective wayto reduce the mortality rate Our main aim in this thesis is detection and recognition oftumors in mammograms Mammograms usually have large size so the processing of theentire mammogram takes a lot of time To reduce the size and therefore the processingtime and also decreasing FPR a two step algorithm is used At the first step someunimportant regions such as background and pectoral muscle are eliminated and at thesecond step an ROI detection algorithm is proposed which extracts the most likely regionsto tumors To recognize the tumors in detected regions some features are extracted fromeach region To find the most effective features for tumor detection several data mining features extraction and feature selection methods are used and compared At the end a veryeffective method is proposed by mixing the data extracted from co occurrence matrix andPCA To increase the performance and reduce the number of features a GAs basedalgorithm is proposed SVM is used as our final classifier because it has the best results incomparison with other tools in our application Finally an approach is suggested torecognize if the tumor is benign or malignant which is based on finding the border oftumor opening the border around its center of gravity and extracting some features such asfractal dimension The reached area under ROC curve using proposed co occurrencefeatures PCA and feature selection based on GAs is 0 97 The TPR using SVM is 97 3 and FPR is 16 65 Experimental results show that the performance of proposed methodsis better than other methods
استاد راهنما :
محمدرضا احمدزاده
استاد مشاور :
علي حكمت نيا
استاد داور :
سعيد صدري ، رسول امير فتاحي
