Alzheimer disease (AD) is a neurodegenerative disease which can be diagnosed using Positron Emission Tomography (PET). A quantitative evaluation of this disease, using computer aided methods, is of importance. In this paper a novel ranking method of the effectiveness of brain region of interest to classify healthy and AD brain is developed. Brain images are first segmented into 116 regions according to an anatomical atlas. A spatial normalization and four grey level normalization methods are used for comparison. Each extracted region is then characterized by a feature set based on grey level histogram moments and age and gender. Using a receiver Operating Characteristic curve for each region, it was possible to rank region's ability to separate healthy from AD brain images. Using a set of selected regions, according to their rank, and when inputting them to a Support Vector Machine, it was possible to show that classification results were similar or slightly better to those obtained when using the whole voxels or the 116 regions as input features to the classifier.