Breast Cancer Classification in Digital Mammograms using Deep Learning Algorithm

Abstract

Cancer is an unpredictable and uncertain disease that can create heightened vulnerability for many individuals. Breast cancer has emerged as the most common cancer in women and the most common cause of cancer death in women. In India, the incidence of breast cancer has steadily increased over the years with 100,000 new cases being diagnosed every year. At a given time, there are as many as one million patients live with breast cancer in India. The life-time risk of developing breast cancer is found to be 1: 30 in urban India and newline1:65 in rural India as compared to 1 in 8 in the USA. Data obtained from Tata Memorial Hospital, a tertiary cancer referral centre in Mumbai, on the women undergoing treatment for cancer revealed that about 60% of them have early breast cancer, 35% with advanced stage and 5% have the disease spread to other organs. However, the survival rate of breast cancer has increased in recent times thanks to the advanced technology available for early detection, eand#64256;ective treatment and medical care delivery. It enables the victims to live longer and enhances their quality of life. newlineVarious imaging modalities are available for detecting the breast cancer. Computer aided diagnosis scheme is awfully useful for radiologist in detection and identifying irregularity in advance and more rapidly. The computer aided diagnosis is a second opinion for radiologist before suggesting a biopsy test. Many Computer Aided Diagnosis (CAD) systems were developed to detect breast cancer in its early stage using mammogram images. The CAD systems mostly focus on identifying and detecting the breast nodules. Staging the breast cancer at its detection need to be focused as the treatment is based on the stage of the cancer. The major drawbacks of existing CAD systems are the accuracy in segmenting the nodule and staging the breast cancer. newline newline