Improving detection of clustered microcalcifications using morphological connected operators

Breast cancer is one of the major causes of death among all cancers for middle-aged and older women, mainly in developed countries, and its incidence is rising. Since the origin of this disease is not yet known, early detection is the best way to reduce the breast cancer mortality. Today, early detection is achieved by means of mammography. Radiologists look for certain signs and characteristics indicative of cancer when evaluating a mammogram. Among these signs is the presence of clustered microcalcifications. A microcalcification is a tiny calcium deposit that has accumulated in tissue in the breast, and it appears as a small bright spot on the mammogram. Due to the large amount of mammograms a radiologist must examine, there are many people developing computer-based systems to aid in the detection of the disease. This paper presents a method to improve automatic detection of clusters of microcalcifications in mammograms