Alzheimer Disease Classification through Transfer Learning Approach

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Neuroscience

Background:

• Alzheimer's disease (AD) is a progressive neurological disorder impacting cognitive function, with increasing prevalence in individuals over 60.
• Accurate and early diagnosis of AD is crucial for patient management and therapeutic interventions.

Purpose of the Study:

• To develop and evaluate a deep learning model for the segmentation and classification of Alzheimer's disease using brain MRI.
• To investigate the efficacy of transfer learning and customized convolutional neural networks (CNNs) for AD detection.

Main Methods:

• Utilized Magnetic Resonance Imaging (MRI) scans, focusing on segmented Gray Matter (GM) images.
• Employed transfer learning by adapting a pre-trained deep learning model.
• Customized a convolutional neural network (CNN) architecture for image classification.

Main Results:

• The proposed model achieved a high classification accuracy of 97.84% for Alzheimer's disease detection.
• Model performance was evaluated across different training epochs (10, 25, and 50).

Conclusions:

• Transfer learning with customized CNNs offers a highly accurate approach for diagnosing Alzheimer's disease from MRI scans.
• This method shows significant potential for improving early detection and diagnosis of AD.