Related Experiment Video
Updated: Jun 29, 2025
09:47
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
1.0K
A deeply supervised adaptable neural network for diagnosis and classification of Alzheimer's severity using multitask
Mohsen Ahmadi1, Danial Javaheri2, Matin Khajavi3
1Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, United States of America.
Plos One
|March 26, 2024
Summary
A deep learning approach using Convolutional Neural Networks (CNNs) achieved 95.3% accuracy in classifying Alzheimer's disease severity from MRI scans. This CNN model significantly outperformed traditional machine learning methods for early Alzheimer's diagnosis.
Area of Science:
- Neuroscience
- Medical Imaging
- Artificial Intelligence
Background:
- Alzheimer's disease (AD) is the leading cause of dementia, characterized by progressive cognitive decline.
- Advancements in neuroimaging provide large multimodal datasets, driving interest in deep learning for AD diagnosis.
- Early and accurate classification of AD severity is crucial for effective patient management.
Purpose of the Study:
- To evaluate machine learning (ML) methods for determining Alzheimer's disease severity using MRI data.
- To compare the performance of traditional ML algorithms with a deep learning CNN model for AD classification.
- To identify specific patterns in MRI images indicative of different AD severity levels.
Main Methods:
- Utilized a dataset of MRI images with four distinct Alzheimer's disease severity levels.
- Applied a hybrid approach combining 12 feature extraction methods.
- Implemented and compared six traditional ML classifiers: decision tree, K-nearest neighbor, linear discrimination analysis, Naïve Bayes, support vector machine, and ensemble learning.
- Trained and evaluated a Convolutional Neural Network (CNN) architecture for pattern identification.
Main Results:
- The CNN model achieved a high accuracy of 95.3% in classifying Alzheimer's disease severity.
- Traditional ML methods showed varying accuracies: Naïve Bayes (67.5%), Support Vector Machines (72.3%), K-nearest neighbor (74.5%), Linear Discrimination Analysis (65.6%), Decision Tree (62.4%), and Ensemble Learning (73.8%).
- The CNN approach demonstrated superior performance compared to all tested traditional ML methods.
Conclusions:
- The developed CNN model is highly effective for the automated classification of Alzheimer's disease severity from MRI data.
- Deep learning, specifically CNNs, offers a promising avenue for improving early diagnosis and severity assessment of Alzheimer's disease.
- This study highlights the potential of advanced ML techniques in neuroimaging for neurodegenerative disease research.
Related Concept Videos
01:26Alzheimer's Disease: Overview
469
Alzheimer's Disease (AD) is a continually advancing neurodegenerative disorder, distinguished by escalating memory loss, cognitive dysfunction, and dementia. The disease unfolds in three stages: preclinical, mild cognitive impairment (MCI), and dementia. Its onset is insidious, and the progression gradual, with the cause not well explained by other disorders.
The clinical diagnosis of AD hinges on the presence of memory and other cognitive impairments. Biomarkers, such as changes in Aβ...
The clinical diagnosis of AD hinges on the presence of memory and other cognitive impairments. Biomarkers, such as changes in Aβ...
469
01:22Alzheimer's Disease: Treatment
184
Alzheimer's Disease (AD), a neurodegenerative disorder, is pathologically identified by amyloid plaques and neurofibrillary tangles composed of tau protein. AD pharmacotherapy aims to manage cognitive symptoms, delay disease progression, and treat behavioral symptoms. The treatment is primarily symptomatic and palliative, with no definitive disease-modifying therapy available. Cholinesterase inhibitors, including donepezil (Aricept), rivastigmine (Exelon), and galantamine (Razadyne), are...
184