Segmentation of the Breast Region with Pectoral Muscle Removal in Mammograms

Breast region segmentation is an essential prerequisite in computerised analysis of mammograms. It aims at separating the breast tissue from the background of the mammogram and it includes two independent segmentations. The first segments the background region which usually contains annotations, labels and frames from the whole breast region, while the second removes the pectoral muscle portion (present in MedioLateral Oblique (MLO) views) from the rest of the breast tissue. In this paper we propose a fully automated breast region segmentation method based on histogram thresholding, edge detection in scale space, contour growing and polynomial fitting. Subsequently, pectoral muscle removal using region growing is presented. To demonstrate the validity of our segmentation algorithm, it is extensively tested using over 240 mammographic images from the EPIC database. The qualitative evaluation of experimental results indicates that the method can accurately segment the breast region in a large range of digitised mammograms, covering all density classes.