Glaucoma Detection using Ensemble and Transfer Learning

DOI

10.2991/978-94-6463-852-3_18How to use a DOI?

Keywords

Glaucoma; Deep Learning; Transfer Learning; Ensemble Learning; Retinal Fundus Images; Convolutional Neural Networks; CLAHE Preprocessing; Accuracy Improvement

Abstract

Glaucoma is a chronic eye disease that causes irreversible blindness, necessitating early and precise detection. The lack of symptoms in the early stages makes detection particularly challenging. This study introduces a deep learning-based approach leveraging Transfer Learning and Ensemble Learning to improve the accuracy of glaucoma detection from retinal fundus images. Several pre-trained Convolutional Neural Network (CNN) models, including VGG16, NASNetMobile, MobileNetV2, and InceptionV3, were evaluated. Using a dataset consisting of 1,291 images from the ORIGA and Drishti-GS datasets, data augmentation expanded the dataset to 12,910 images, ensuring model generalization. The highest accuracy achieved by an individual model was 87.02% with InceptionV3. Additionally, CLAHE preprocessing significantly improved model performance, with an average accuracy gain of 4%. Ensemble learning techniques further enhanced the classification, with the Weighted Average Ensemble achieving the highest accuracy of 95.48%. Sensitivity and specificity metrics also showed substantial improvements, with the final model reaching a sensitivity of 96.2% and specificity of 94.8%. These results demonstrate a notable improvement over previous studies, showcasing the potential of deep learning and ensemble methods in early glaucoma detection.

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  - Abhishek Joshi
AU  - Baasim Riyaz Kondkari
AU  - Om Uttam Patil
AU  - Krishna Patel
AU  - Vivek Solavande
PY  - 2025
DA  - 2025/10/07
TI  - Glaucoma Detection using Ensemble and Transfer Learning
BT  - Proceedings of the MULTINOVA: First International Conference on Artificial Intelligence in Engineering, Healthcare and Sciences (ICAIEHS- 2025)
PB  - Atlantis Press
SP  - 276
EP  - 295
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-852-3_18
DO  - 10.2991/978-94-6463-852-3_18
ID  - Joshi2025
ER  -