Identification of Masses in Digital Mammogram Using an Optimal Set of Features

Recently, Digital mammogram has become one of the most effective techniques for early breast cancer detection. The aim of this study is to develop an automated system for digital mammogram analysis. In the proposed system, the regions of interest (ROIs) in the mammogram are firstly segmented by a topographic representation method called the isocontour map. Subsequently, the textural, intensity and shape features are extracted from the ROIs. Then an optimal feature selection method (Correlation-based Feature Selection, CFS) is used to select some important features to classify the ROIs as either masses or non-masses. Finally, we use these selected features to train the cost-sensitive BP neural network. The experimental results show that the proposed method can produce better identification performance than some other algorithms.