The calculation of the left ventricular ejection fraction (LVEF) is dependent upon the accurate measurement of diastolic and systolic left ventricular volumes. Although breath-hold cine magnetic resonance imaging (MRI) allows coverage of the whole cardiac cycle with an excellent time resolution, many authors rely on the visual selection of diastolic and the systolic short-axis slices in order to reduce the postprocessing time. An automatic method was developed to detect the endocardial contour on each image, allowing an automatic selection of the systolic frame. The calculated ejection fraction was compared with radionuclide ventriculography (RNV). Sixty-five patients were examined using an electrocardiogram (ECG)-gated gradient echo sequence. Among these examinations, manual and automatic processing with MRI were compared when the time of the systolic frame concorded. Good correlations have been found between the automatic MRI approach and RNV, and between manual and automatic processing on MRI alone. The results show that the automatic determination of the ejection fraction is feasible, and should constitute an important step toward a larger acceptance of MRI as a routine tool in heart disease imaging. One major benefit of using automatic postprocessing is that it may eliminate the visual choice of the systolic frame, inaccurate in more than 50% of the studied patients.