Measures of radial correlation and trend for classification of breast masses in mammograms

In this paper, a novel approach for classification of breast masses is presented that quantifies the texture of masses without relying on accurate extraction of their contours. Two novel feature descriptors based on 2D extensions of the reverse arrangement (RA) and Mantel's tests were designed for this purpose. Measures of radial correlation and radial trend were extracted from the original gray-scale values as well as from the Gabor magnitude response of 146 regions of interest, including 120 benign masses and 26 malignant tumors. Four classifiers, Fisher-linear discriminant analysis, Bayesian, support vector machine, and an artificial neural network based on radial basis functions (ANN-RBF), were employed to predict the diagnosis, using stepwise logistic regression for feature selection and the leave-one-patient-out method for cross-validation. The ANN-RBF resulted in an area under the receiver operating characteristic curve of 0.93. The experimental results show the effectiveness of the proposed approach.