Related Experiment Video
Updated: May 16, 2025
09:47
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
916
An efficient method for early Alzheimer's disease detection based on MRI images using deep convolutional neural
1Department of Computer Science, College of Computing and Information Technology, Shaqra University, Shaqraa, Saudi Arabia.
Frontiers in Artificial Intelligence
|May 14, 2025
Summary
This study introduces a deep convolutional neural network (CNN) for early Alzheimer's disease (AD) detection. The AI model achieved 99.68% accuracy in classifying AD stages from MRI scans.
Area of Science:
- Artificial Intelligence in Medicine
- Neurological Disorders Diagnostics
- Medical Imaging Analysis
Background:
- Alzheimer's disease (AD) is a progressive, incurable neurological disorder causing cognitive decline.
- Early detection of AD is crucial for symptom management and improving patient quality of life.
- Healthcare systems face challenges due to a shortage of medical experts, necessitating automated diagnostic tools.
Purpose of the Study:
- To develop and evaluate a deep convolutional neural network (CNN) for automated Alzheimer's disease classification.
- To enhance early detection and diagnosis of AD, aiding timely intervention and patient care.
- To provide a reliable tool for healthcare professionals to manage the global health challenge of AD.
Main Methods:
- A deep convolutional neural network (CNN) architecture with 6,026,324 parameters was designed.
- The model features three distinct convolutional branches with varying lengths and kernel sizes for improved feature extraction.
- The OASIS dataset, comprising 80,000 MRI images across four classes (Non-Dementia, Very Mild Dementia, Mild Dementia, Moderate Dementia), was utilized, with data augmentation applied to address class imbalance.
Main Results:
- The proposed CNN model achieved a high accuracy of 99.68% in classifying the four stages of Alzheimer's disease.
- The model demonstrated significant capability in distinguishing between Non-Dementia, Very Mild Dementia, Mild Dementia, and Moderate Dementia.
- The results indicate the model's effectiveness for real-time analysis and early diagnosis of AD.
Conclusions:
- The developed deep convolutional neural network shows exceptional accuracy for Alzheimer's disease classification.
- This AI-driven approach offers a promising solution for early AD detection, potentially transforming patient management.
- The model serves as a valuable tool for healthcare providers, addressing the need for efficient and accurate diagnostic systems in neurology.
