Computer-aided diagnosis of breast cancer using artificial neural networks: comparison of backpropagation and genetic algorithms

Abstract

The authors investigated computer-aided diagnosis (CAD) schemes to determine the probability for the presence of breast cancer using artificial neural networks (ANNs) that were trained by a backpropagation (BP) algorithm or by a genetic algorithm (GA). A clinical database of 418 previously verified patient cases was employed and randomly partitioned into two independent sets for CAD training and testing. During training, the BP and the GA were independently applied to optimize, or to evolve the inter-connecting weights of the ANNs. Both the BP/GA-trained CAD performances were then compared using the receiver-operating characteristics (ROC) analysis. In the training set, both the BP/GA-trained CAD schemes yielded the areas under ROC curves of 0.91 and 0.93, respectively. In the testing set, both the BP/GA-trained ANNs yielded the areas under ROC curves of approximately 0.83. These results demonstrated that the GA performed slightly better, although not significantly, than BP for the training of the CAD schemes.