A second opinion system for microcalcification diagnosis

An important early sign of breast cancer is the presence of microcalcification clusters in mammograms. To assist radiologists in the diagnosis of mammographic clusters a Computer Aided System for breast cancer diagnosis is presented. In particular, the procedure first detects microcalcifications having a cluster pattern and then classifies the abnormalities as benign or malignant clusters. A Support Vector Machine is implemented for cluster classification which is trained adopting the Sequential Minimal Optimization technique. The classifier considers one cluster at a time and evaluates several parameters, so that each cluster is fully represented by its own features. The performance of the implemented system is evaluated taking into account the accuracy and the sensitivity in classifying clusters. Obtained results make this method able to operate as a "second opinion" helping radiologists during the routine clinical practice.