Classification of Breast Masses Based on Multi-View Information Fusion Using Multi-Agent Method

Mammography is an important detection method of breast cancer, and classification of mammographic masses plays an important role in Computer-aided diagnosis (CAD) for breast cancer. In this paper, one novel multi-view information fusion algorithm based on Multi-Agent (MA) method is proposed to improve the accuracy of classification of masses. 128 ROIs (regions of interest) from DDSM database composed by 64 pairs of cranio-caudal (CC) view and medio-lateral oblique (MLO) view were chosen for the experiments, which demonstrated the proposed algorithm improved the accuracy and reduced the false positive rates rather than the other methods.