Breast cancer detection based on mixture membership function with MFSVM-FKNN ensemble classifier

Micro-calcification cluster is an important sign of early breast cancer. However, computer-aided micro-calcification clusters detection is often hampered due to the diversified features of the lesions. In this paper, we propose a mixture membership function based on linear distance membership and tight density membership. Specifically, different fuzzy factors are defined for different training samples based on mixture membership. Furthermore, a MFSVM-FKNN ensemble classifier for breast cancer detection algorithm based on mixture membership is proposed. The experimental results in X-ray mammography demonstrate that the proposed algorithm achieves the best performance compared with other state of art classifiers for micro-calcification detection.