Automatic mammogram analysis using wavelet-fourier transforms and entropy-based feature selection

Abstract

Breast cancer is the second leading cause of cancer-related death after lung cancer in women. Early detection of breast cancer in X-ray mammography is believed to have effectively reduced the mortality rate since 1989. However, a relatively high false positive rate and a low specificity in mammography technology still exist. A computer-aided automatic mammogram analysis system in this research is proposed to improve the detection performances. In designing this analysis system, the discrete wavelet transforms (Daubechies 2, Daubechies 4, and Biorthogonal 6.8) and the Fourier cosine transform were first used to parse the mammogram images and extract statistical features. Then, an entropy-based feature selection method was implemented to reduce the number of features. Finally, different pattern recognition methods (including the Back-propagation Network, the Linear Discriminate Analysis, and the Naïve Bayes Classifier) and a voting classification scheme were employed. The performance of each classification strategy was evaluated for sensitivity, specificity, and accuracy and for general performance using the Receiver Operating Curve. The experiment demonstrated that the proposed automatic mammogram analysis system could effectively improve the classification performances, especially using the voting classification scheme based on the selected optimal features.