A New Mammogram Preprocessing Method for Computer-Aided Diagnosis Systems

Mammography is currently the most powerful technique for early detection of breast cancer. To better interpret mammogram images and assist radiologists in their decision, CAD systems have been proposed. This paper gives a comparative analysis of the existing preprocessing methods and proposes a technique for preprocessing mammography that will be implemented afterwards in a CAD system. The proposed preprocessing technique consists of four phases: The first involves suppressing noise from mammogram images using two denoising filters. The second comprises the contrast enhancement using the CLAHE. The third phase describes labels removal, and finally, pectoral muscle segmentation method is performed. The proposed method is applied on images from MIAS and INbreast databases resulting in complete pectoral muscle suppression in most of the images.