DETECTION AND ANALYSIS OF BREAST CANCER USING MAMMOGRAM IMAGING

Abstract

Breast cancer is the second most common cancer in women after skin cancer. Early discovery and determination is the best methodology to control the tumor movement. Mammograms can detect breast cancer early, possibly before it has spread. Mammogram pictures are observed to be hard to decipher so a CAD is turning into an undeniable essential device to help radiologists in the mammographic lesion interpretation. In this dissertation we explore an automated technique for mammogram segmentation. From comparing different Digitization Noise Removal techniques in light of parameters, for example, PSNR, MSE and SNR, comparing different direct and indirect image enhancement techniques, Background Separation, Edge Detection and finally Segmentation of Breast ROI all are analyzed. Therefore the dissertation leaves us with the best techniques which make tumor detection easy for radiologists.