Alzheimer’s Disease (AD) is a neurodegenerative disorder characterized by disruptions in brain connectivity. Resting-state functional MRI (rs-fMRI) and structural MRI (sMRI) offer valuable insights into these alterations, but their high dimensionality poses significant challenges for data processing and classification. This study leverages artificial intelligence and machine learning to preprocess and analyze 4D rs-fMRI and 3D T1-weighted sMRI data, extracting meaningful features that characterize functional connectivity in AD. A comprehensive preprocessing pipeline was implemented, including motion correction, spatial normalization, coregistration, global signal regression, and functional connectivity computation. Two brain atlases, AAL90 and Schaefer200, were used to parcellate the brain and extract region-wise time series. Functional connectivity matrices were constructed to quantify interactions between brain regions, forming the basis for classification. A Support Vector Machine classifier was trained on these extracted features, achieving an accuracy of 96%, with perfect sensitivity and an F1-score of 97%, demonstrating highly effective group separation.