Model-based characterization of mammographic masses

Abstract

The discrimination of benign and malignant types of mam-mographic masses is a major challenge for radiologists. The classic eigen-faces method was recently adapted for the detection of masses in mammo-grams. In the work at hand we investigate if this method is also suited for the problem of distinguishing benign and malignant types of this mammographic lesion. We furthermore evaluate two extended versions of the eigenfaces approach (fisherface and eigenfeature regularization extraction) and compare the performance of all three methods on a public mammography database. Our results indicate that all three methods can be applied to discriminate benign and malignant types of mammographic masses. However, our ROC analysis shows that the methods still require combination with other features to allow for reliable classification.