A hybrid deep learning framework for early detection of diabetic retinopathy using retinal fundus images
Problem
Diabetic retinopathy needs to be detected early and its progression monitored from retinal fundus images to guide treatment.
Why it matters
Early detection of diabetic retinopathy can prevent vision loss in a growing diabetic population.
What the AI did
A hybrid deep learning framework combines CNNs for multi-scale spatial feature extraction with RNNs that integrate temporal information across multiple retinal scans to detect and monitor diabetic retinopathy.
Results
not stated in source
Impact
Evaluated on public DRIVE and Kaggle diabetic retinopathy datasets; evidence supports only a proposed detection framework.
Record
| Venue | Scientific Reports |
|---|---|
| Published | 2025 |
| Work type | article |
| Authors | Mishmala Sushith, A. Sathiya, V. Kalaipoonguzhali, V. Sathya |
| Citations | 54 (OpenAlex, at import time) |
| References | 31 |
| Model or method | Hybrid CNN-RNN framework (no specific name stated) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41598-025-99309-w |
| Open access | gold |
| Keywords | diabetic retinopathy, deep learning, CNN, RNN, fundus images, medical imaging |
Importance rating
significant — thousands to millions affected
Preventing vision loss in a growing diabetic population is a significant benefit, but the abstract gives no scale or prevalence figures; impact rests on the proposed framework only.