Computer-Aided Identification of the Pectoral Muscle in Mammograms

Due to drastic growth in mammography, a huge number of high quality and diverse images are available for analysis. At this juncture, usage of computer vision techniques, which includes artificial systems to analyze these medical images, is indispensable. However, the usage of artificial systems for mammogram analysis is not new to this field. Though Computer-Aided Detection (CAD) for breast cancer is available in the market, studies demonstrate that further development is required in this field to produce more effective CAD. In CAD, removal or suppression of the pectoral muscle in screening mammograms is one of the preprocessing steps as its presence within a mammogram may influence the breast cancer detection. Through this research, we have attempted to obtain efficient automatic methods to identify the pectoral muscle, which appears as a homogeneous region, in mediolateral oblique view mammograms using a proposed segmentation method, the graph cut based merging.