Computer Aided Detection of Masses in Mammogram Using K-Means Clustering

Breast cancer is a serious public health problem in several countries. Computer Aided Detection/Diagnosis systems have been used with relative success aiding health care professionals. The aim of the system is to accurately detecting the abnormal area in mammogram. This study concerns the development of a CAD system to detect malignant masses. We use the term “mass” for the group of malignant masses, architectural distortions, and focal asymmetries. CAD systems use a three-stage approach for classification of breast masses as malignant or benign. First, the preprocessing stage, image is segmented from the background tissue, Breast Tissue and the pectoral muscle. This work presents a methodology for masses detection on digitized mammograms using the K-means algorithm for image segmentation in the next stage of the CAD masses and non-masses this is the final stage of CAD.