Development of an intelligent system for breast cancer diagnosis

Abstract

Breast cancer is the most common cancer affecting Singapore women. Every year, 700 - 1000 new cases of breast cancer are diagnosed and about 250 women die from the disease. High-quality mammography, an X-ray technique that vi-sualizes the internal structure of the breast, is the most effective early detection technology currently available. It is sensitive to screening and diagnosis. Un-fortunately, it results in a high false-positive rate, i.e. only a small portion of masses found on mammograms are malignant. Recent studies found that only 20-30% mammographically suspicious nonpalpable breast masses were malig-nant. The National Cancer Institute of America also reported that 80% of American women who undergo surgical breast biopsies do not have cancers. Considering the cost of biopsy and the patient's emotional disturbance, it is crucial to develop high-performance computer-aided diagnosis (CAD) systems to assist radiologists in the classification of breast cancers in order to reduce unnecessary biopsies.