Proceedings of the 2025 International Conference on Advanced Research in Electronics and Communication Systems (ICARECS-2025)

Diabetic Retinopathy Detection Using Deep Convolution Neural Network

Authors
A. Rajeshwari1, *, M. Sathishkumar1
1Department of Computer Science and Engineering, Excel Engineering College, Namakkal, India
*Corresponding author. Email: harichandrarajesh179@gmail.com
Corresponding Author
A. Rajeshwari
Available Online 30 June 2025.
DOI
10.2991/978-94-6463-754-0_48How to use a DOI?
Keywords
Diabetic Retinopathy; Machine Learning; ID Rid Dataset; DCNN; Random Forest; AUC-ROC
Abstract

Deep learning is used by the AI-enabled ECG (AI ECG) program to extract meaningful patterns from complicated ECG data. In patients with heart failure, left ventricular hypertrophies, paroxysmal atrial fibrillation, and other cardiovascular conditions, it has been shown to be beneficial. The difficulties of manual screening can be lessened by early identification via automated techniques, especially in environments with limited resources. Using the publicly accessible IDRiD Blindness Detection dataset, which is posted on Kaggle and comprises annotated retinal fundus pictures from various stages of DR, this work uses ML algorithms to identify and categorize the severity of DR. Deep Convolution Neural Networks are the main tool used in this study to evaluate and categorize these photos into several DR groups. Important procedures include training deep learning models forCLAHE feature extraction and classification, augmentation to solve dataset imbalance, and data preparation to improve picture quality. The models’ efficacy is assessed using performance measures, including the sensitivity region beneath the operating characteristic curve of the receiver, as well as specificity and accuracy. These findings show that the suggested method achieves high DR detection and grading accuracy, indicating its potential for effective and scalable screening solutions. Additionally covered are issues including class imbalance, imaging fluctuation, and the requirement for clinical validation. This work advances machine learning applications in ophthalmology by using the Kaggle dataset, providing a route to a diagnosis of DR that is both accessible and accurate.

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)

Volume Title
Proceedings of the 2025 International Conference on Advanced Research in Electronics and Communication Systems (ICARECS-2025)
Series
Atlantis Highlights in Engineering
Publication Date
30 June 2025
ISBN
978-94-6463-754-0
ISSN
2589-4943
DOI
10.2991/978-94-6463-754-0_48How to use a DOI?
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.

Cite this article

TY  - CONF
AU  - A. Rajeshwari
AU  - M. Sathishkumar
PY  - 2025
DA  - 2025/06/30
TI  - Diabetic Retinopathy Detection Using Deep Convolution Neural Network
BT  - Proceedings of the 2025 International Conference on Advanced Research in Electronics and Communication Systems (ICARECS-2025)
PB  - Atlantis Press
SP  - 544
EP  - 558
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-754-0_48
DO  - 10.2991/978-94-6463-754-0_48
ID  - Rajeshwari2025
ER  -