Fuzzy-Embedded Recurrent Neural Networks for Early Detection and Classification of Diabetic Retinopathy Using Fundus Images

DOI

10.2991/978-94-6463-940-7_26How to use a DOI?

Keywords

Diabetic Retinopathy; Retinal Fundus Images; Bilinear Double-Order Filter; Fuzzy-Embedded Recurrent Neural Network; Early Detection; Medical Image Classification

Abstract

Diabetic Retinopathy (DR) is one of the leading causes of preventable blindness worldwide, and early detection with precise severity classification is critical to reduce vision loss. Retinal fundus imaging is the most widely used modality for DR screening, but manual diagnosis is time-consuming, subjective, and prone to variability. Existing deep learning methods often suffer from noise sensitivity, overfitting, and limited ability to classify across all severity levels, which reduces their clinical applicability in large-scale screening. To address these limitations, this work is motivated by the need for an automated, accurate, and robust DR detection framework that can effectively support ophthalmologists in timely intervention. The novelty of this study lies in the development of a Fuzzy-Embedded Recurrent Neural Network (FERNN) combined with a Bilinear Double-Order Filter (BDOF). The BDOF enhances fundus image clarity by suppressing noise while preserving fine retinal details, and FERNN integrates fuzzy logic with recurrent learning to manage uncertainty and capture sequential dependencies in retinal features capabilities not achieved by conventional CNN or hybrid models. Using the Indian Diabetic Retinopathy Image Database (IDRiD), the proposed framework classifies DR into five clinically significant stages, from mild non-proliferative DR to proliferative DR. Experimental results demonstrate that FERNN achieves 89.20% accuracy and 85.44% precision, outperforming advanced baselines such as hybrid Inception-ResNet, DCGAN, and graph neural network models by up to 30.29%. These findings confirm that the proposed FERNN–BDOF framework provides a novel, robust, and scalable solution for automated DR detection, with strong potential for real-world clinical deployment.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Narendra Krishna Meka
AU  - N. Veeranjaneyulu
PY  - 2025
DA  - 2025/12/31
TI  - Fuzzy-Embedded Recurrent Neural Networks for Early Detection and Classification of Diabetic Retinopathy Using Fundus Images
BT  - Proceedings of the Conference on Social and Sustainable Innovation in Technology & Engineering (SASI-ITE 2025)
PB  - Atlantis Press
SP  - 351
EP  - 362
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-940-7_26
DO  - 10.2991/978-94-6463-940-7_26
ID  - Meka2025
ER  -