A textural approach for recognizing architectural distortion in mammograms

Breast cancer is considered as the most important cause of death among women. Architectural distortions are very important signs of breast cancer and early detection of them is a rewarding work. In this paper we propose a method to recognize architectural distortion from normal parenchyma. In our proposed method, appropriate features are extracted by the analysis of oriented textures with the application of orientation component of recent the state-of-the-art local texture descriptor called Monogenic Binary Coding (MBC). In addition, we transform Region of Interests (ROIs) to polar coordinates in order to highlight some specific patterns in mammograms. Various classifiers are used over a set of mammograms from Digital Database for Screening Mammography (DDSM). The results show that proposed method is very encouraging. The best performance achieved is 91.25% in terms of the average accuracy using the Nearest Neighbor classifier.