Classifying and diagnosing Alzheimer’s disease with deep learning using 6735 brain MRI images
importance 6/10
ai assisted
Dementia and Cognitive Impairment Research neurology imaging stage: research
Problem
Diagnosing and classifying Alzheimer's disease from brain MRI scans, where traditional methods are slow and less accurate.
Why it matters
Delayed or inaccurate diagnosis postpones crucial interventions and patient care.
What the AI did
Four deep CNN architectures were trained on 6735 preprocessed MRI images with hyperparameter tuning, early stopping and dynamic learning rate to classify Alzheimer's patients.
Results
InceptionResNetV2 showed superior performance; metric values truncated, not stated in source
Impact
CNNs classified Alzheimer's from MRI with InceptionResNetV2 best; clinical adoption not stated.
Record
| Venue | Scientific Reports |
|---|---|
| Published | 2025 |
| Work type | article |
| Authors | Seyed Mohammad Mousavi, Khadijeh Moulaei, Leila Ahmadian |
| Citations | 33 (OpenAlex, at import time) |
| References | 30 |
| Model or method | InceptionResNetV2, Xception, VGG19, VGG16 (CNNs) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41598-025-08092-1 |
| Open access | gold |
| Keywords | Alzheimer's disease, deep learning, CNN, MRI, InceptionResNetV2, classification |
Importance rating
6
significant — thousands to millions affected
Alzheimer's diagnosis delays postpone interventions; significant disease but abstract states no scale numbers.