Computer aided classification of mammographic tissue using independent component analysis

A computer-aided method for the classification of regions of suspicion on digitized mammograms is presented. The method employs features extracted by a novel technique based on independent component analysis. We concentrate our approach on finding a set of independent source regions that generate the observed regions. The coefficients of the linear transformation of the source regions are used as features that describe effectively benign and malignant regions of suspicion. Extensive experiments in the WAS Database have shown a recognition accuracy of 79.31% in the task of distinguishing between benign and malignant regions, outperforming standard textural features that are widely used for cancer detection in mammograms.