Computer-aided diagnosis system for mammogram density measure and classification

This paper presents a computer-aided diagnosis (CAD) system for breast density classification in digital mammogram images. Mammographic density is considered as a strong indicator for developing breast cancer. This proposed method consists of four steps: (i) breast region is segmented from the mammogram images by removing the background and pectoral muscle (ii) segmentation of fatty and dense tissue (iii) percentage of the fatty and dense tissue area is calculated (iv) Classification of breast density. Results of the proposed method evaluated on the Mammographic Image Analysis Society (MIAS) database. The experimental results show that the proposed CAD system can well characterize the breast tissue types in mammogram images.