Beyond complex architectures: a streamlined CNN pipeline for robust Alzheimer's disease classification from brain MRI
Mohamed Amine Jabli1, Moussa Mourad2
1ENISO, NOCCS, University of Sousse, Sousse, Tunisia. jeblimedamine@gmail.com.
Neuroradiology
|July 4, 2026
Summary
Artificial Intelligence (AI) using convolutional neural networks (CNNs) can accurately detect early Alzheimer's disease from MRI scans. This AI approach achieved high accuracy, offering potential for improved diagnosis and patient care.
Area of Science:
- Neuroimaging
- Artificial Intelligence
- Medical Diagnostics
Background:
- Alzheimer's disease is a progressive dementia causing memory loss and cognitive decline due to brain cell deterioration.
- Early detection of Alzheimer's disease is crucial for timely intervention and management.
Purpose of the Study:
- To explore the efficacy of Artificial Intelligence (AI), specifically deep learning, in identifying early signs of Alzheimer's disease.
- To utilize MRI brain scans for AI-driven Alzheimer's detection.
Main Methods:
- A convolutional neural network (CNN) deep learning model was developed.
- The model was trained and validated using two large datasets: ADNI (21,324 MRI images) and OASIS (6,400 MRI images).
- The CNN was used to classify individuals into Alzheimer's disease, Mild Cognitive Impairment (MCI), and healthy control groups.
Main Results:
- The CNN model demonstrated high accuracy: 99.67% on ADNI data and 99.06% on OASIS data.
- The model effectively distinguished between Alzheimer's disease, MCI, and healthy individuals.
- Results indicate the AI method's capability for accurate analysis and classification of large-scale neuroimaging data.
Conclusions:
- AI-powered analysis of MRI scans shows significant promise for early and accurate detection of Alzheimer's disease.
- This technology can provide clinicians with advanced tools for disease prediction and diagnosis.
- Potential benefits include reduced diagnosis time, lower healthcare costs, and improved patient outcomes.
