Analysis of mammographie microcalcifications using gray-level image structure features

At present, mammography associated with clinical breast examination and breast self-examination is the only effective and viable method for mass breast screening. The presence of microcalcifications is one of the primary signs of breast cancer. It is, difficult however, to distinguish between benign and malignant microcalcifications associated with breast cancer. Most of the techniques used in the computerized analysis of mammographie microcalcifications use shape features on the segmented regions of microcalcifications extracted from the digitized mammograms. Since mammographie images usually suffer from poorly defined microcalcification features, the extraction of shape features based on a segmentation process may not accurately represent microcalcifications. The intensity variations and texture information in the area of interest provide important diagnostic information about the underlying biological process for the benign or malignant tissue and therefore should be included in the analysis. In this paper, we define a set of image structure features for classification of malignancy. Two categories of correlated gray-level image structure features are denned for classification of difficult-to-diagnose cases. The first category of features includes second-order histogram statisticsbased features representing the global texture and the wavelet decomposition-based features representing the local texture of the microcalcification area of interest. The second category of features represents the first-order gray-level histogram-based statistics of the segmented microcalcification regions and the size, number, and distance features of the segmented microcalcification cluster. Various features in each category were correlated with the biopsy examination results of 191 ''difficult-to-diagnosc eases for selection of the best set of features representing the complete gray-level image structure information. The selection of the best features was performed using the multivariate cluster analysis as well as a genetic algorithm (GA)-based search method. The selected features were used for classification using backpropagation neural network and parameteric statistical classifiers. Receiver operating characteristic (ROC) analysis was performed to compare the neural network-based classification with linear and fc-nearest neighbor (KNN) classifiers. The neural network classifier yielded better results using the combined set of features selected through the GA-based search method for classification of difficult-to-diagnose microcalcifications.