The algorithm for automatic segmentation of breast and pectoral muscle regions from mammograms

摘要

Proper segmentation of breast and pectoral muscle regions is often the first step in systems for automatic analysis of mammographic images. This paper proposes a method for extraction of the breast region using adaptive gamma correction algorithm for image contrast enhancement and k-means algorithm for thresholding the image in order to extract background and the breast region. To extract the pectoral muscle we find the region of interest, enhance its contrast, and find the region of muscle using k-means algorithm. To estimate the curve representing the edge of the pectoral muscle we use cubic polynomial fitting. The efficiency of the proposed method is tested on mammograms from miniMIAS database.