The disease of Alzheimer’s (AD) is a progressive neurode- generative condition, which ultimately results in dementia and imposes a substantial global healthcare burden. Timely and accurate diagnosis is crucial to enabling early intervention and managing disease progression. While Magnetic Resonance Imaging(MRI) is widely used to detect structural alterations in the brain associated with AD, conven- tional visual assessments of MRI data are often inconsistent and highly subjectiveThis research introduces an automated classification framework that leverages transfer learning with Convolutional Neural Networks (CNNs) to detect and categorize Alzheimer’s disease stages from MRI scans. Among the models evaluated, ResNet demonstrated superior performance across multiple evaluation metrics. The findings suggest that deep learning–based approaches can enhance diagnostic accuracy and offer scalable, AI-driven tools for the early detection of neurodegenerative disorders.