Single photon emission with computed tomography (SPECT) hexamethylphenylethyleneamineoxime technetium-99 images were analyzed by an optimal interpolative neural network (OINN) algorithm to determine whether the network could discriminate among clinically diagnosed groups of elderly normal, Alzheimer disease (AD), and vascular dementia (VD) subjects. After initial image preprocessing and registration, image features were obtained that were representative of the mean regional tissue uptake. These features were extracted from a given image by averaging the intensities over various regions defined by suitable masks. After training, the network classified independent trials of patients whose clinical diagnoses conformed to published criteria for probable AD or probable/possible VD. For the SPECT data used in the current tests, the OINN agreement was 80 and 86% for probable AD and probable/possible VD, respectively. These results suggest that artificial neural network methods offer potential in diagnoses from brain images and possibly in other areas of scientific research where complex patterns of data may have scientifically meaningful groupings that are not easily identifiable by the researcher.Alzheimer disease (AD), vascular dementia (VD), or both occur in 70-90% of all dementias and are often clinically difficult to distinguish. Brain imaging is an important part of the diagnostic evaluation (1-4). However, the brain image may be qualitatively difficult to distinguish between normal and demented persons, and more so between different dementia types such as AD and VD. Since disturbances of brain metabolism may precede structural changes, metabolic images can detect more subtle patterns of change earlier than anatomical ones. We chose single photon emission with computed tomography (SPECT) because (i) it provides measures of regional tissue uptake (hexamethylphenylethyleneamineoxime technetium-99 or HMPAO-99Tc) that show complex patterns of brain activity and because (ii) it is widely available. Improvements in the recognition, quantification, and classification of these image patterns could increase diagnostic sensitivity between normal and abnormal as well as between different subtypes of dementia.The need for better methods of diagnostic interpretation of brain images is illustrated by the large variability in their diagnostic interpretation by even well-trained neuroradiologists using standardized criteria. For example, the Consortium to Establish a Registry for Alzheimer's Disease (CERAD) conducted an interrater reliability study among 14 participating CERAD neuroradiologists for interpreting specific mag-The publication costs of this article were defrayed in part by page charge payment. This article must therefore be hereby marked "advertisement" in accordance with 18 U.S.C. §1734 solely to indicate this fact. netic resonance imaging features and found within-feature correlations ranging from 0.64 (for detecting cerebral sulcal dilatation) to 0.79 (for rating the size of the lateral and third ventricl...