Robust Alzheimer's disease classification based on multimodal neuroimaging

Alzheimer's disease (AD) is a neurodegenerative disorder which leads to severe brain damage. The main objective of this work is to diagnosis Alzheimer's disease using Elman Back Propagation (BP) algorithm. In the proposed method, the Positron Emission Tomography (PET) and Magnetic Resonance Imaging (MRI) datasets are obtained from the freely availed database called ANDI. The preprocessing of input images was done by weiner filter. The PET and MR features are extracted using Gray-level Co-occurrence Matrix (GLCM). Finally, the classification was done using Elman Back Propagation Neural Network. The experimental results on dataset validate the efficiency of the proposed method in diagnosing Alzheimer's disease.