Deep Learning-Driven Early Detection of Alzheimer’s Disease using CNN

Researchers evaluate Convolutional Neural Networks as tools for early identification and staging of Alzheimer's disease (AD) using MRI data collected from the Open Access Series of Imaging Studies (OASIS). The dataset encompasses 4 classes: Very Mild Dementia, Mild Dementia, Non-Demented and Moderate Dementia. The proposed Convolutional Neural Networks (CNN) model exhibited robust performance by achieving 95% classification accuracy while maintaining near perfect precision, recall and F1-scores of about 0.95 throughout the dataset classes. Accurate classification across all dementia stages stands validated by both macro and weighted average assessments. This paper reveals DL methods as essential tools for precise disease progression detection which leads to earlier intervention and enhanced patient care. Automated AD detection benefits from this research while demonstrating that CNN serves as practical solutions in medical imagery for neurodegenerative disease management.