K9. Automatic Segmentation of Digital Mammograms to Detect Masses

Mammography is a well-known method for detection of breast tumors. Early detection and removal of the primary tumor is an essential and effective method to enhance survival rate and reduce mortality. Breast tumor segmentation is needed for monitoring and quantifying breast cancer. However, automated tumor segmentation in mammograms poses many challenges considering the characteristics of images. In this paper, we propose a fully automatic algorithm for segmentation of breast masses, using two types of image segmentation; normalized graph cuts to delineate pectoral muscle, and then optimal thresholding based on the two-dimensional entropy for mass detection.