Mammography mass detection: a multi-stage hybrid approach
Nima Sahba, Vahid Tavakoli, Alireza Ahmadian, Masoumeh Giti · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2009
Here in this paper a combined method of pixel based and region based mass detection is proposed. In the first step, the background and pectoral muscle are filtered from mammography images and the image contrast is enhanced using an adaptive density weighted approach. Then, in a coarse level, suspected regions are extracted based on mathematical morphology and adaptive thresholding methods. Finally, to reduce the false positives produced in the coarse stage, a useful feature vector based on ranklet transform is obtained and fed into a support vector machine classifier to detect masses. MIAS (Mammographic Image Analysis Society) and Imam Hospital databases were used to evaluate the performance of the algorithm. The sensitivity and specificity of the proposed method are 74% and 91% respectively. The proposed algorithm shows a high degree of robustness in detecting masses of different shapes.