Classification of mammograms using multi layer neural network
Canan Oral, Hatice Sezgın · Electrical, Electronics and Computer Engineering (ELECO), 2010 National Conference on · 2010
Breast cancer is the most common cancer among women and the leading cause of cancer deaths in women. Mammography plays a major role in the early detection of breast cancer. In this study computer aided detection (CAD) system is designed to classify mammographic abnormalities. CAD system used computerized algorithms in order to detect breast abnormalities. Within this work, breast images from MIAS database are considered. Designed CAD system includes preprocessing, feature extraction and classification stages. Multiscale top-hat transform is used to enhance mammograms and to remove noise. First and second textural features are extracted from enhanced mammograms. Classification is performed using multi layer perceptron. The accuracy of classification is % 89,3.