Perceptrons are typically trained to minimize mean square error (MSE). In computer-aided diagnosis (CAD),
model performance is usually evaluated according to other more clinically relevant measures. The purpose of
this study was to investigate the relationship between MSE and the area (Az) under the receiver operating
characteristic (ROC) curve and the high-sensitivity partial ROC area (0:90A z). A perceptron was used to predict
lesion malignancy based on two mammographic :ndings and patient age. For each performance measure, the
error surface in weight space was visualized. Comparison of the surfaces indicated that minimizing MSE
tended to maximize Az, but not 0:90A z. ? 2002 Elsevier Science Ltd. All rights reserved.