Fuzzy Computer-aided Diagnosis of Alzheimer's Disease Using MRI and PET Statistical Features

In this paper, MRI and PET image features from selected brain regions are used as inputs in a fuzzy inference classification system for automatic diagnosis of Alzheimer's Disease (AD). Mean values of voxel intensity in spatial regions of interest which are extracted from normalized MRI and PET scans of brain gray matter were used as features. Area under receiver operating characteristic (AUC) was used as a classification performance measure, being function of the number of brain anatomical and functional regions of interest from which the features were extracted. In the result, combination of features from 7 MRI regions and 39 PET regions gave the highest performance of classification (AUC=0.94).