Design and Development of a Deep Learning Model for Classification of Alzheimer's disease Using Magnetic Resonance Images

Abstract

Alzheimer’s disease, an incurable neurodegenerative condition predominantly affecting memory functions in the elderly, presents a significant global health challenge, particularly among individuals aged over 65 years. Early and accurate diagnosis is crucial for effective management and intervention. However, manual diagnosis by healthcare professionals is prone to errors and time-consuming due to the increasing number of cases. While various techniques have been employed for diagnosis and classification, there remains a need for improved accuracy in early detection solutions. In this research, we propose a deep learning-based approach utilizing Convolutional Neural Network (CNN) architectures for the diagnosis and classification of Alzheimer’s disease. The proposed model distinguishes Alzheimer’s disease into four categories: Non-Dementia, Very Mild Dementia, Mild Dementia, and Moderate Dementia. The CNN architecture, with optimized hyper parameters, demonstrated superior performance during both training and testing phases, achieving accuracy values of 0.977 and 0.994, respectively. The proposed model offers a practical solution for real-time analysis and classification of Alzheimer’s disease, potentially enhancing early intervention strategies and patient care