Alzheimer’s disease diagnosis and classification using deep learning techniques
Problem
Manual diagnosis of Alzheimer's disease is error-prone and time-consuming, and early accurate detection is needed.
Why it matters
Alzheimer's is an incurable disease mainly affecting people over 65, so early detection matters for care.
What the AI did
A deep learning model using DenseNet-169 and ResNet-50 CNN architectures classified Alzheimer's disease into four severity stages (Non-Dementia to Moderate Dementia), with DenseNet-169 outperforming in training and testing.
Results
DenseNet-169 outperformed ResNet-50; numeric accuracy values not stated in source (abstract truncated)
Impact
Supports AI-assisted dementia classification research; no clinical deployment or external validation stated.
Record
| Venue | PeerJ Computer Science |
|---|---|
| Published | 2022 |
| Work type | article |
| Authors | Waleed A. Al Shehri |
| Citations | 122 (OpenAlex, at import time) |
| References | 18 |
| Model or method | DenseNet-169, ResNet-50 |
| Organization | not stated in source |
| Primary source | https://doi.org/10.7717/peerj-cs.1177 |
| Open access | gold |
| Keywords | Alzheimer's, deep learning, DenseNet-169, ResNet-50, medical imaging, classification |
Importance rating
significant — thousands to millions affected
Abstract states Alzheimer's occurs worldwide, mainly affecting people over 65, with large patient numbers making manual diagnosis error-prone; early detection need stated; solution remains research-stage.