Diagnosing Alzheimer Disease Using MRI Scan: A Deep Learning Approach

The neurodegenerative disease known as Alzheimer's disease (AD), which affects people worldwide, is complicated to treat and expensive. Conventional approaches, including manual Support Vector Machine (SVM) based methods with separate feature extraction and preprocessing, lack automation and pose limitations. This project recognizes the pressing need for efficient and automated solutions. Building on existing work that employed SVM and manual processing for Alzheimer's diagnosis, this work proposes a novel approach. Utilizing brain MRI scans and the VGG16 architecture, our automated system achieves high accuracy in predicting both labeled and unlabeled data. The integration of VGG16 ensures a streamlined process, eliminating manual intervention in feature extraction and preprocessing. This automation enhances accessibility, reduces costs, and offers a user-friendly interface for users. In contrast to traditional methods, our proposed system allows users to input MRI scans, facilitating prompt and accurate predictions. Upon analysis, the proposed system provides doctor recommendations and suggests prescriptions. The VGG16-based approach not only ensures superior diagnostic accuracy but also streamlines the entire process, emphasizing the importance of early detection for improved outcomes in Alzheimer's disease management.