Skip to Main Content
Breast cancer is the most common cancer among women in the western world and in Malaysia, other than skin cancer. It is the second leading cause of cancer death in women, after lung cancer. Screening mammography is currently the most effective tool for early detection of breast cancer. For every thousand cases analyzed by a radiologist, only 3 to 4 are cancerous and the rest could be overlooked. The challenges basically come from the (1) A large variability in the appearance of abnormalities (masses) within digital mammogram made very difficult in image analysis (2) Presence of high dense breast tissues for fibroglandular tissue predominance such as mammogram of young woman which makes the distinction between normal glandular tissues and malignant disease is difficult, So it is very hard to detect the masses with an opaque uniform background and (3) hard to obtain data in an unstructured knowledge of previous screening history. In this paper, we have proposed an algorithm by CBR (Case Based Reasoning Classification) based computerized mammogram mass detection for improving the accuracy rate of detection; the main aim of the paper is to show the evaluation results of CBR classification and make a comparative analysis with existing ANN classification method.