ABSTRACT
Alzheimer’s disease (AD) is a progressive neurological disease commonly found in adults over 65 years. Significant growth is estimated for this neurological disorder where diagnosis should be handled effectively and efficiently. Therefore, early detection and medication are crucial in the progression of AD. This study focuses on developing a deep-learning-based computational model by considering Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) as the neurological modalities. These two types of modalities provide rich information on the neurological and anatomical aspects of the human brain to assist AD identification. We consider three main architectures, namely Capsule neural network, Dense Net, and Inception V3 as the learning models. The optimized Inception V3 model has shown high accuracy results of 96.05% and 95.49% for MRI and PET data, respectively. fMRI images, PET images, Inception V3, capsule neural network, neurological disorder, decision-support
