The development of non-invasive techniques for the early diagnosis of Alzheimer's disease are of high importance facing the growing number of affected persons and the immense cost to our society caused be dementia. Computer based analysis of FDG-PET scans might become a possibility to make early diagnosis more efficient. Temporal lobe is the the main location of medical findings. We have clues that in PET images the parietal lobe contains more information about Alzheimer's disease. We used a probabilistic brain atlas to include prior information about the localization of changes in the human brain, classified Alzheimer's disease versus normal control group and got better classification rates focusing on parietal lobe.