AN AUTOMATIC COMPUTER-AIDED WOMEN BREAST CANCER DIAGNOSIS SYSTEM FROM 2-D DIGITAL MAMMOGRAPHIC IMAGES

Breast cancer is the second leading cause of cancer death in women. Accurate early detection can effectively reduce the mortality rate and ensure long survival of the patients. Diagnosis of breast cancer can be made from clinical examination based on the symptoms produced or based on the imaging analysis of digital medical images to identify abnormality in the to test for cancer tissue or not. The automatic prediction model can be a non-image based risk model based on genetic susceptibility factors or image-based prediction model based on Mammography, MRI, Ultrasound images. Mammography is most preferred as it uses a low dosage of x-rays and takes 20 second scan and suitable for fatty and dense breasts. The abnormalities in mammograms include micro-calcifications (MCs), masses, architectural distortion and bilateral asymmetry. The current automatic CAD systems suffer from false diagnosis which is resolved by the proposed system with improved accuracy helps the expert effectively and reduces their examination time.