Retinal Disease Detection Using Deep Learning Techniques: A Comprehensive Review
importance 7/10
partially solved
Retinal Imaging and Analysis ophthalmology stage: research
Problem
Manual detection of retinal diseases such as glaucoma, diabetic retinopathy and AMD is time-consuming, tedious and lacks repeatability.
Why it matters
Early detection could arrest progression and save millions from avoidable blindness.
What the AI did
Reviews deep learning models (DCNNs, vision transformers) for computer-aided detection and grading of retinal diseases; states they performed well but challenges remain.
Results
not stated in source
Impact
Review concludes deep-learning CAD will be increasingly vital for retinal disease care.
Record
| Venue | Journal of Imaging |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Stewart Muchuchuti, Serestina Viriri |
| Citations | 136 (OpenAlex, at import time) |
| References | 136 |
| Model or method | Deep CNNs, vision transformers |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/jimaging9040084 |
| Open access | gold |
| Keywords | deep learning, retinal disease, diabetic retinopathy, glaucoma, computer-aided diagnosis |
Importance rating
7
significant — thousands to millions affected
Abstract states millions affected worldwide; early detection and treatment could arrest progression, saving multitudes from avoidable blindness.