Feature selection in computer aided diagnostic system for microcalcification detection in digital mammograms

In this paper an approach is proposed to develop a computer-aided diagnosis (CAD) system that can be very helpful for radiologist in diagnosing microcalcifications' patterns in digitized mammograms earlier and faster than typical screening programs and showed the efficiency of feature selection on the CAD system. The proposed method has been implemented in four stages: (a) the region of interest (ROI) selection of 32times32 pixels size which identifies clusters of microcalcifications, (b) the feature extraction stage is based on the wavelet decomposition of locally processed image (region of interest) to compute the important features of each cluster, (c) the feature selection stage, which select the most significant features to be used in next stage, and (d) the classification stage, which classify between normal and microcalcifications' patterns and then classify between benign and malignant microcalcifications. In classification stage, two methods were used, the voting K-nearest neighbor classifier, and support vector machine classifier. The proposed method was evaluated using the Mammographic Image Analysis Society (MIAS) mammographic databases. The proposed system was shown to have the large potential for microcalcifications detection in digital mammograms.