We developed a method for extracting the left ventricular (LV) contours from left ventriculograms by means of a neural edge detector (NED) in order to extract the contours which agree with those traced by a cardiologist. The NED is a supervised edge detector based on a linear-output artificial neural network model, which is trained with a modified back-propagation training algorithm. The NED can acquire the function of a desired edge detector through training with a set of input images and the desired edges obtained from the contours traced by a cardiologist. Our computer-aided diagnostic (CAD) system consisted of (a) detection of subjective edgesEby use of the NED, (b) extraction of rough contours by use of low-pass filtering and edge enhancement, and (c) a contour-tracing method based on the contour candidates synthesized from the edges detected by the NED and the rough contours. Through experiments, we showed that the proposed method was able to extract the contours in agreement with those traced by an experienced cardiologist, i.e., we achieved an average contour error of 6.2% for left ventriculograms at end-diastole and an average difference of 4.1% between the ejection fractions obtained from the manually traced contours and those obtained from the computer-extracted contours.