Thesis (M.Sc.) - Cairo University - Faculty of Engineering - Department of Systems and Biomedical Engineering

Digital mammography has emerged as the most popular screening technique for early detection of breast cancer and other abnormalities in human breast tissue and it continues to be the standard screening tool for breast cancer detection. In this study, we developed computer-aided detection (CADe) and computer-aided diagnosis (CADx) systems and we tested and experimentally verified these systems using the publicly available MIAS and DDSM mammographic databases, respectively. We first applied preprocessing technique to enhance the breast peripheral regions, then we extracted a set of 543 different textural features from the regions of interest, and after that the most relevant features were selected using four selection methods. The selected features are then used as input to different classifiers to differentiate between normal and abnormal breast masses in CADe system, and to distinguish between normal, benign and malignant breast tissues in CADx system. All cases were correctly detected in the proposed CADe system, while CADx system achieved 98.67% overall accuracy

Issued also as CD