A cost-sensitive cascaded method for automatic mass detection

Mass detection in mammograms is a challenging problem. In this paper, we propose a cost-sensitive cascaded method for automatic mass detection, which employs machine learning techniques to detect region of interests (ROI). In detail, we divide the original mammograms into overlapped squared sub-images. For each sub-image, intensity features based on gray histogram, texture features based on spatial gray-level co-occurrence matrix (SGLDM) and texture features based on local binary patterns (LBP) are extracted and input to a cost-sensitive cascaded classifier. Simple threshold segmentation and neural network are used to further reduce false positives. Experimental results show that the proposed method is effective in mass detection.