An evaluation of the performance of artificial neural networks (ANNs) for the classification of probable Alzheimer's disease (pAD) patients was undertaken using data extracted from four regions of interest constructed on single photon emission tomographic (SPET) cerebral perfusion images. Two studies using feed-forward neural networks (FFNNs) were undertaken. The first was to determine if it would be possible to classify pAD patients and normal subjects in a mixed group, comprising 29 patients diagnosed as having pAD varying in severity from mild, established dementia to moderate dementia and 10 healthy control subjects. The second was to determine if the networks generated in the first study could prospectively classify 15 additional patients with very mild or mild cognitive impairment. The results were compared to those obtained using the same data and discriminant analysis. The relative performances of the two analysis techniques were assessed on the basis of the area under receiver operating characteristics (ROC) curves. The FFNN successfully classified all datasets in the first study, achieving an area under the ROC curve of 1.00, whereas discriminant analysis achieved 0.94. When tested on data from the second group, the areas under the ROC curves varied between 0.86 and 1.00 for the FFNN, whereas that for discriminant analysis was 0.99. We conclude that FFNNs can accurately classify pAD patients with mild to moderate dementia using data obtained from SPET cerebral perfusion images.