To develop a computer-aided diagnosis (CAD) system for full field digital mammography (FFDM) using advanced computer vision techniques and to evaluate the effects of CAD on interpretation of digital mammograms (DMs). This system will assist radiologists with the four most important areas in mammographic interpretation: (1) detection of masses, (2) classification of masses, (3) detection of microcalcifications, (4) classification of microcalcifications. The proposed approach is distinctly different from previous approaches in that image information from two-view and bilateral mammograms will be fused with that from the single-view mammogram to improve lesion detection and characterization.
