Proceedings of the International Conference on Sustainable Innovation with Artificial Intelligence and Machine Learning 2025 (ICSIAIML 2025)

<Previous Article In Volume
Next Article In Volume>

An Explainable Deep Learning Pipeline for Multi-Disease Classification of Retinal Fundus Images

Authors
Sharada Dhavale1, *, Ashish Sunil Pate2, Swami Kailas Patil3, S. D. Nagarale4, V. A. Kulkarni5
1Department of Electronics and Telecommunications, Pimpri Chinchwad College of Engineering, Pune, India
2Department of Electronics and Telecommunications, Pimpri Chinchwad College of Engineering, Pune, India
3Department of Electronics and Telecommunications, Pimpri Chinchwad College of Engineering, Pune, India
4Department of Electronics and Telecommunications, Pimpri Chinchwad College of Engineering, Pune, India
5Department of Electronics and Telecommunications, Pimpri Chinchwad College of Engineering, Pune, India
*Corresponding author. Email: sharda.dhvale@pccoepune.org
Corresponding Author
Sharada Dhavale
Available Online 6 January 2026.
DOI
10.2991/978-94-6463-948-3_60How to use a DOI?
Keywords
Retinal Fundus Images; Diabetic Retinopathy; Glaucoma; Cataract; Age-related Macular Degeneration; Grad-CAM
Abstract

Preventable blindness is often caused by retinal diseases such as Diabetic Retinopathy (DR), Glaucoma, Cataract, and Age-related Macular Degeneration (AMD). Early and accurate diagnosis is essential, but conventional screening uses significant resources, takes time, and depends on qualified ophthalmologists — limiting access in many areas. To address this, we propose an explainable deep learning framework for automated analysis of retinal fundus images across multiple disorders. The proposed system uses a two-stage modular design. First, a general classifier detects disease presence and type. Next, disease-specific models determine severity/stage for DR, Glaucoma, Cataract, and AMD. We leverage Convolutional Neural Networks (EfficientNet-B0, ResNet variants) and Gradient-weighted Class Activation Mapping (Grad-CAM) to generate visual explanations. This approach improves interpretability and clinical trust while maintaining high accuracy and practical applicability for telemedicine and resource-limited settings.

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)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Sustainable Innovation with Artificial Intelligence and Machine Learning 2025 (ICSIAIML 2025)
Series
Advances in Intelligent Systems Research
Publication Date
6 January 2026
ISBN
978-94-6463-948-3
ISSN
1951-6851
DOI
10.2991/978-94-6463-948-3_60How 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

risenwbib
TY  - CONF
AU  - Sharada Dhavale
AU  - Ashish Sunil Pate
AU  - Swami Kailas Patil
AU  - S. D. Nagarale
AU  - V. A. Kulkarni
PY  - 2026
DA  - 2026/01/06
TI  - An Explainable Deep Learning Pipeline for Multi-Disease Classification of Retinal Fundus Images
BT  - Proceedings of the International Conference on Sustainable Innovation with Artificial Intelligence and Machine Learning 2025 (ICSIAIML 2025)
PB  - Atlantis Press
SP  - 866
EP  - 884
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-948-3_60
DO  - 10.2991/978-94-6463-948-3_60
ID  - Dhavale2026
ER  -