ClairVue-Diabetic Retinopathy detection using EfficientNet and Grad-CAM

DOI

10.2991/978-94-6463-858-5_82How to use a DOI?

Keywords

Diabetic Retinopathy; Deep Learning; EfficientNet; Transfer Learning; Fundus Image Analysis; Automated Diagnosis; Grad-CAM; Explainable AI

Abstract

Diabetic Retinopathy (DR) is the most common cause of blindness and visual impairment in diabetic patients, primarily due to delayed diagnosis and inadequate screening. The diagnosis is currently human interpretation of fundus retinal images by ophthalmologists, which is time-consuming, labor-intensive, and prone to human errors. For alleviating these complications, we propose ClairVue as an AI framework with the aid of EfficientNet, a superior deep learning-based model, as an extension strategy for early detection of DR. EfficientNet is a better deep learning based model with greater accuracy but greater computational complexity and thus more efficient to use. ClairVue also offers the enhanced transparency and confidence in the diagnosis by applying Grad-CAM (Gradient-weighted Class Activation Mapping), where it provides a visually impaired replica of the impaired retina regions so that the system outputs become more understandable for the medical officers. The system is coupled with a user-friendly interface to facilitate easy screening for the physicians as well as the patients. We also highlight the socio-economic benefits of AI-based DR detection, i.e., better access to health care for rural communities. Accessibility of an inexpensive, scalable and accurate screening device, ClairVue can potentially democratize preventive eye care and prevent blindness worldwide by a large margin.

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  - Shraddha Rai
AU  - K. Shivabalaji
AU  - P. Pavan Kumar
AU  - S. Sowjanya
PY  - 2025
DA  - 2025/11/04
TI  - ClairVue-Diabetic Retinopathy detection using EfficientNet and Grad-CAM
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 978
EP  - 991
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_82
DO  - 10.2991/978-94-6463-858-5_82
ID  - Rai2025
ER  -