GRIFD: a graded region-wise dissection and cross-pooling RNN framework for precise diabetic retinopathy detection in fundus images
Open Access
- 30 October 2025
- journal article
- Published by PeerJ in PeerJ Computer Science
- Vol. 11, e3197
Abstract
Early and precise detection of diabetic retinopathy (DR) is essential in averting vision impairment. This work introduces graded region wise inspection and feature dissection (GRIFD), a novel deep learning architecture designed explicitly for fine-grained DR detection from fundus images. GRIFD enforces a graded region of interest (ROI) dissection approach, which methodically segments fundus images into diagnostic blocks to promote local lesion visibility. A recurrent neural network (RNN) is used to model sequential dependencies between these ROI blocks, aiming to mimic the progressive development of DR symptoms. We also introduce a cross-pooling refinement procedure to eliminate inter-region inconsistencies and improve feature continuity. Experiments on the Mendeley and EyePACS benchmarks show that GRIFD obtains 94.35% accuracy, 96.05% precision, and 94.91% specificity on Mendeley, all of which surpass baseline models such as convolutional neural network (CNN), long short-term memory (LSTM), Transformer, and some published DR detection models. The introduced framework presents a lightweight and robust method for DR screening and can potentially facilitate real-time clinical practice.Keywords
Funding Information
- Deanship of Research and Graduate Studies at King Khalid University (RGP2/231/46)
- Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia (PNURSP2025R203)
- Deanship of Scientific Research at Northern Border University, Arar, KSA (NBU-FFR-2025-1564-9)
- Prince Sattam bin Abdulaziz University (PSAU/2025/R/1446)
- Deanship of Graduate Studies and Scientific Research at University
This publication has 50 references indexed in Scilit:
- Glucose‐Responsive and Analgesic Gel for Diabetic Subcutaneous Abscess Treatment by Simultaneously Boosting Photodynamic Therapy and Relieving HypoxiaAdvanced Science, 2025
- Multimodal Masked Autoencoder Based on Adaptive Masking for Vitiligo Stage ClassificationJournal of Imaging Informatics in Medicine, 2025
- HCTTI: High-Performance Heterogeneous Computing Toolkit for Tissue Image Stain NormalizationJournal of Imaging Informatics in Medicine, 2025
- Clinical characteristics, treatment, and outcomes of pembrolizumab-induced uveitisInvestigational New Drugs, 2024
- Diabetic retinopathy detection by fundus images using fine tuned deep learning modelMultimedia Tools and Applications, 2024
- Deep learning model using classification for diabetic retinopathy detection: an overviewArtificial Intelligence Review, 2024
- A Systematic Review on Deep Learning Techniques for Diabetic Retinopathy Segmentation and Detection Using Ocular Imaging ModalitiesWireless Personal Communications, 2024
- Detection of Diabetic Retinopathy using Convolutional Neural Networks for Feature Extraction and Classification (DRFEC)Multimedia Tools and Applications, 2022
- Optimized hybrid machine learning approach for smartphone based diabetic retinopathy detectionMultimedia Tools and Applications, 2022
- Multithreshold Image Segmentation Technique Using Remora Optimization Algorithm for Diabetic Retinopathy Detection from Fundus ImagesNeural Processing Letters, 2022