An Automatic Mass Detection System
Today in the whole world in many areas, Breast cancer is a leading cause of cancer particularly in woman in
which most common breast abnormalities are masses and calcifications. Early detection of diagnosis is the key to breast
cancer controls that increase the success of treatment, save lives and reduce cost. It is difficult for the radiologist to recognize
the masses on a mammogram because they are surrounded by complicated tissues, for these reasons many CADe systems
have been developed to aid the radiologist in detecting mammographic lesions that may indicate the presence of breast
cancer. In this paper, we present an overview and a complete automatic classification system for the detection of masses in
digitized mammographic images. As in general view, a CADe system consists of four stages like Preprocessing,
segmentation, feature extraction & selection and classification. It also refers a method for the feature extraction of
mammograms using gray level co-occurrence matrix for suspicious areas of a breast to identify the tumor. Thus the
radiologists are able to segment masses on the mammogram. This system is trained and tested by 358 mammography
(DDSM). The results prove that this system achieves satisfactory detection performance.
Keywords - DDSM, CADe, Mammography, Diagnosis.