Volume 15, Issue 5

DIABETIC RETINOPATHY DETECTION SYSTEM USING RETINAL IMAGES

Author

Pankhuri Verma, Shivam Kumar, Er Shilpi Khanna

Abstract

Diabetic Retinopathy is a disease that impacts the retina and happens after a long duration of diabetes. Diabetic Retinopathy is one of the primary causes of blindness worldwide. It is necessary to diagnose the retinal disease at an early stage by analyzing the images of the fundus of the eye with the help of software solutions to ensure appropriate treatment to prevent blindness. Recently, artificial intelligence has helped the researchers to implement computer-aided detection systems for Diabetic Retinopathy. This paper digs into software solutions for detecting Diabetic Retinopathy, zeroing in on Vision Transformer models. We compared different ways of preprocessing retinal fundus images, along with various feature extraction and classification methods. When you stack Vision Transformers up against Convolutional Neural Networks (CNNs), Vision Transformers really shine. They handle global features better — they don’t just focus on small patches. That’s a big deal when you’re analyzing something as intricate as retinal images. This paper focuses on Vision Transformer models and compares them with classical and CNN-based approaches for diabetic retinopathy detection.

REFERENCES

[1] A. Sopharak, B. Uyyanonvara, S. Barman, and T. H. Williamson, “Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods,” Computers in Medicine and Biology, vol. 38, no. 8, pp. 843–852, 2008.

[2] M. Niemeijer, B. van Ginneken, J. Staal, M. Suttorp-Schulten, and M. Abràmoff, “Automatic detection of red lesions in digital color fundus photographs,” IEEE Transactions on Medical Imaging, vol. 24, no. 5, pp. 584–592, 2005.

[3] V. Gulshan et al., “Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs,” JAMA, vol. 316, no. 22, pp. 2402–2410, 2016.

[4] Kaggle, “APTOS 2019 Blindness Detection Dataset,” 2019.

[5] E. Decencière et al., “Feedback on a publicly distributed database: The Messidor database,” Image Analysis & Stereology, vol. 33, no. 3, pp. 231–234, 2014.

[6] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE CVPR, 2016, pp. 770– 778.

[7] A. Vaswani et al., “Attention is all you need,” in Advances in Neural Information Processing Systems (NeurIPS), 2017.

[8] A. Dosovitskiy et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” in Proc. ICLR, 2021.

[9] Z. Liu et al., “Swin Transformer: Hierarchical vision transformer using shifted windows,” in Proc. IEEE ICCV, 2021.

[10] Y. Li et al., “Vision transformer-based automated diabetic retinopathy grading,” IEEE Access, vol. 10, pp. 112345–112356, 2022.

[11] K. V. Shanthala and N. C. Kundur, “RetinoFusionNet: A scalable and interpretable Vision Transformer framework for diabetic retinopathy detection,” Eng., Technol. & Appl. Sci. Res., vol. 16, no. 1, pp. 31386–31392, Feb. 2026.

[12] Y. Tewari, N. S. Parihar, K. Rautela, N. Kaundal, M. Diwakar, and N. K. Pandey, “Diabetic retinopathy detection and analysis with convolutional neural networks and Vision Transformer,” BISH, vol. 1, no. 1, pp. 18– 26, Jun. 2025.

[13] OcuViT: A Vision TransformerBased approach for automated diabetic retinopathy and AMD classification, J. Imaging Inform. Med., 2025, doi:10.1007/s10278-025-01676-3.

[14] K. Patni and S. Yagnik, “Cross-Dataset Unified Vision Transformer model for diabetic retinopathy detection,” J. Comput. & Biomed. Inform., vol. 10, no. 1, pp. 1–14, Dec. 2025.

[15] A. Shukla, S. Tiwari, and A. Jain, “HybridFusionNet: Deep learning for multi-stage diabetic retinopathy detection,” Technologies, vol. 12, no. 12, p. 256, Dec. 2024.

[16] W. Zhang, V. Belcheva, and T. Ermakova, “Interpretable deep learning for diabetic retinopathy: A comparative study of CNN, ViT, and hybrid architectures,” Computers, vol. 14, no. 5, p. 187, May 2025.

[17] S. Akhtar et al., “A deep learning-based model for diabetic retinopathy grading,” Sci. Rep., vol. 15, Art. no. 3763, Jan.

DOI

https://doi.org/10.62226/ijarst20262660

PAGES : 1915-1918 | 10 VIEWS | 5 DOWNLOADS

Download Full Article