Computerized classification of benign and malignant masses on digitized mammograms: A study of robustness

Rationale and Objectives. The purpose of this study was to evaluate the rob ustness of a computerized method developed for the classification of benign and malignant masses with respect to variations in both case mix and film digitization. Materials and Methods. The classification method included automated segment ation of mass regions, automated feature-extraction, and automated lesion c haracterization. The method was evaluated independently with a 110-case dat abase consisting of 50 malignant and 60 benign cases. Mammograms were digit ized twice with two different digitizers (Konica and Lumisys). Performance of the method in differentiating benign from malignant masses was evaluated with receiver operating characteristic (ROC) analysis. Effects of variatio ns in both case mix and film digitization on performance of the method also were assessed, Results. Categorization of lesions as malignant or benign with an artificia l neural network (or a hybrid) classifier achieved an area under the ROC cu rve, A(z), value of 0.90 (0.94 for the hybrid) on the previous training dat abase in a round-robin evaluation and A(z) values of 0.82 (0.81) and 0.81 ( 0.82) on the independent database for the Konica and Lumisys formats, respe ctively, These differences, however, were not statistically significant (P > .10). Conclusion. The computerized method for the classification of lesions on ma mmograms was robust with respect to variations in case mix and film digitiz ation.