Authors : Vijaya Jyothi Chiluka; P. Jasmitha; R. Srikavya; S. Meghana; V. Sruthi

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/2pvvfrhn

Scribd : https://tinyurl.com/db7phytm

DOI : https://doi.org/10.38124/ijisrt/26apr1398

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Retinal conditions like Diabetic Retinopathy (DR), Glaucoma, and Neovascularization (NV) are some of the common reasons for permanent blindness across the globe, but their early detection is challenging due to the need for manual evaluation of retinal images, which is time-intensive and subjective and not feasible for population-level screening. This study proposes an automated deep learning system capable of classifying retinal fundus images based on the following classes: Diabetic Retinopathy, Glaucoma, Neovascularization, and Normal. The performance of three transfer learning models (EfficientNet, ResNet50, and MobileNetV2) was assessed using the APTOS 2019 dataset, consisting of around 3,500 retinal fundus images. Preprocessing methods such as resizing to 224 × 224, pixel normalization, Gaussian noise removal, and augmentation were applied to improve the performance of the proposed deep learning system. Grad-CAM was also incorporated to provide clinicians with heatmaps indicating the areas of the retina that play a crucial role in the classification task.

Keywords : Retinal Disease Classification, Multi-Disease Detection, Diabetic Retinopathy, Glaucoma, Neovascularization, Deep Learning, Transfer Learning, EfficientNet, ResNet50, MobileNetV2, Convolutional Neural Networks, Grad-CAM, Fundus Image Analysis, APTOS 2019, Medical Image Classification.

References :

1. K. M. Almustafa, "Classification of eye disease and defects using deep learning techniques," EURASIP Journal on Image and Video Processing, vol. 2020, no. 1, pp. 1–12, 2020.
2. B. Bulut, "Classification of eye disease from fundus images using EfficientNet," Artificial Intelligence: Theory and Applications, vol. 2, no. 1, pp. 1–7, 2022.
3. O. Arslan, Y. Taskiran, and E. Gunduz, "Intelligent retinal disease detection using deep learning architectures: a comparative study," Scientific Reports, Nature Publishing Group, vol. 13, 2023.
4. S. Muchuchuti and S. Viriri, "Retinal disease detection using deep learning techniques: a comprehensive review," Journal of Imaging, vol. 9, no. 4, p. 84, 2023.
5. R. B. Sara, M. Ahmed, and K. Islam, "A deep learning framework for the early detection of multi-retinal diseases using fundus images," PLOS ONE, vol. 19, no. 3, 2024.
6. Z. Wang, L. Chen, and H. Zhang, "Combining EfficientNet with ML-Decoder classification head for multi-label retinal disease classification from color fundus photographs," Neural Computing and Applications, Springer Nature, 2024.
7. P. Porwal, S. Pachade, R. Kamble, M. Kokare, G. Deshmukh, V. Sahasrabuddhe, and F. Meriaudeau, "Indian diabetic retinopathy image dataset (IDRiD): a database for diabetic retinopathy screening research," Data, vol. 3, no. 3, p. 25, 2018.
8. M. Tan and Q. V. Le, "EfficientNet: rethinking model scaling for convolutional neural networks," in Proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, CA, USA, pp. 6105–6114, 2019.
9. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 770–778, 2016.
10. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. C. Chen, "MobileNetV2: inverted residuals and linear bottlenecks," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, pp. 4510–4520, 2018.
11. R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, "Grad-CAM: visual explanations from deep networks via gradient-based localization," in Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy, pp. 618–626, 2017.

12. APTOS 2019 Blindness Detection Dataset, Kaggle, 2019. [Online]. Available: https://www.kaggle.com/c/aptos2019-blindness-detection