A method and apparatus of comparing the results of medical imaging by, for example, PET scanning dispenses with the need for intensity normalization. The relationships between features extracted from relevant regions of interest in the image are studied. In one example, mean intensities in the principle brain lobes are compared to each other and a short image ID is constructed and used to derive population statistics and diagnosis. The population statistics are compared with ‘reference’ statistics in order to assess abnormality. Comparison by a number of methods is possible, and the invention further provides concerns a novel voting mechanism which derives abnormality scores for each region.