Automatic Mammographic Mass Segmentation based on Region Growing Technique

Breast cancer is one of the leading cancers in woman worldwide both in developed and developing nations as per the records from World Health Organization (WHO). American Society identified that by the end of 2012, about 2,26,000 cases were diagnosed and 40,000 resulted in death. Physician uses mammography as one method for breast cancer detection and interpretation. Mass segmentation plays an important step for the cancer detection. Notable researches were done and still moving towards the effective detection of masses in mammograms. In most of the segmentation techniques, the region of interest is chosen manually. To overcome this, a fully automatic mass segmentation scheme is proposed. The proposed method includes automatic seed selection by extracting the statistical features and the region growing technique is employed. The difference in the mean of the manual markup by an expert and the proposed segmentation obtained is 0.356. Keywords— Mammography, Mass, Region Growing, Segmentation.