Automatic classification of alzheimer's desease vs. frontotemporal dementia: a spatial decision tree aprroach with FDG-PET

We introduce a novel approach for the automatic classification of FDG-PET scans of subjects with Alzheimers Disease (AD) and Frontotemporal dementia (FTD). Unlike previous work in the literature which focuses on principal component analysis and predefined regions of interest, we propose the combined use of information gain and spatial proximity to group cortical pixels into empirically determined regions that can best separate the two diseases. These regions are then used as attributes in a decision tree learning framework. We demonstrate that the proposed method provides better classification accuracy compared to other methods on a group of 48 autopsy confirmed AD and FTD patients.