A supervised method to assist the diagnosis of Alzheimer´s Disease based on functional Magnetic Resonance Imaging

In this work we present a supervised method to assist the diagnosis of Alzheimer´s disease (AD) based on functional magnetic resonance images (fMRI). The method consists of five stages: a) preprocessing of fMRI data to remove non-task related variability, b) modeling the way in which the BOLD response depends on stimulus, c) feature extraction from fMRI data, d) feature selection and e) classification using the Random Forests algorithm. The proposed method is evaluated using data from 41 subjects (14 young adults, 14 non demented older adults and 13 demented older adults).