Automatic Cancer Detection in Mammographic Images

Abstract: Breast cancer is the major health problem in women that has increased over years. Early detection is necessary as to treat breast cancer with success and reduce mortality. Towards this, mammography is the main diagnostic test for screening of breast tumors wherein high quality images with low dose x-rays are used to image the breast(s). Due to the immense danger that this disease presents it becomes necessary to develop a Computer-aided diagnosis (CAD) systems to improve radiologist�s diagnosis. This paper has implemented such a system. The developed method proceeds in four steps: pre-processing mammograms for enhancement, segmentation to detect breast abnormalities, then texture feature(s) are extracted and finally image is classified.

Keywords: Breast Cancer, Mammography, image pre-processing, segmentation, feature extraction, image classification.