Computer-Aided Diagnosis System for Alzheimer's Disease Using Fuzzy-Possibilistic Tissue Segmentation and SVM Classification

We describe a computer-aided diagnosis (CAD) system for discriminating patients suffering from Alzheimer's disease (AD) dementia and healthy patients. It is based on: 1) a clustering process to assess white matter, gray matter and cerebrospinal fluid volumes from noisy anatomical magnetic resonance (MR) and functional positron emission tomography (PET) brain images11The MR and PET data used in this work were obtained from the Alzheimer's disease Neuroimaging Initiative (ADNI) database (http://adni.loni.usc.edu/).; 2) a classification process that distinguishes the brain images of normal and AD patients. The clustering stage consists of three steps: First, the fuzzy c-means (FCM) algorithm is used for a fuzzy partition of the initial class centroids. Second, fuzzy tissue maps are computed using a possibilistic C-means (PCM) algorithm that uses the FCM partition to obtain the final image clusters. The final segmentation is then made to delimit the brain tissue volumes. For the classification stage, a support vector machine (SVM) is used with different kernel functions. Validating the proposed CAD system on the MRI and PET images of 45 AD and 50 healthy brains, of subjects aged between 55 and 90 years, shows better sensitivity, specificity and accuracy in comparison to three alternative approaches, namely FCM, PCM and VAF (Voxels-As-Features). The accuracy rates for the noisiest images (20% of noise) were 75% for MRI and 73% for PET scan, compared to 71 % and 70,2%, 68.5% and 67%, and 65 % and 64.7 % with the three other approaches, respectively.