Diabetic Retinopathy Detection using SWIN Transformer

Sheetal Jiwanbhai Nagar, Nikhil Gondaliya

Abstract


Diabetic Retinopathy (DR) is a diabetes related eye disorder that damages the retina. DR is among the most specific complications of diabetes. A vital challenge for automated detection systems in medical image diagnosis is to minimize the false negative rate for patients’ timely treatment. This paper presents a novel strategy employing the Shifted Window (SWIN) Transformer for efficiently modeling local and global visual information to address this challenge. We have proposed our work to maximize the true positive ratio and minimize the false negative ratio for the automated process of diagnosing the level of Diabetic Retinopathy so that patients with positive signs of DR can be predicted most accurately and can save vison. The results suggest that SWIN Transformer architecture along with Contrast Limited Adaptive Histogram Equalization (CLAHE) technique, provides a robust option for developing a reliable diabetic retinopathy detection system. The results indicate that the proposed approach achieves 96% weighted recall across all the levels of DR detection and 97.45% validation accuracy for eyePACS Diabetic Retinopathy Detection dataset as well as 99% weighted recall across all the levels of DR detection along with 99.26% validation accuracy for APTOS 2019 Blindness Detection dataset. Thus, this study aimed to develop a DR detection system focused on minimizing false negatives using the SWIN Transformer.

Keywords


Diabetic Retinopathy, Medical Image Classification, CLAHE, SWIN transformer, False Negative Reduction

Full Text:

PDF

References


Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, et al. “Swin Transformer: Hierarchical Vision Transformer using Shifted Windows”, in IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, 2021, pp. 9992-10002, Feb. 2022, doi: 10.1109/ICCV48922.2021.00986.

Rajendra Pradeepa and Viswanathan Mohan, “Epidemiology of type 2 diabetes in India”, Indian Journal of Ophthalmology, vol. 69, no. 11, pp. 2932-2938, Oct. 2021, doi: 10.4103/ijo.IJO_1627_21.

World Health Organization, Strengthening diagnosis and treatment of diabetic retinopathy in the South-East Asia Region. New Delhi. World Health Organization, Regional Office for South-East Asia; (2020), https://www.who.int/publications/i/item/9789290227946, last accessed 2025/07/27.

APTOS : Eye Preprocessing in Diabetic Retinopathy https://www.kaggle.com/code/ratthachat/aptos-eye-preprocessing-in-diabetic-retinopathy/data, last accessed 2025/07/27.

Dolly Das, Saroj Kumar Biswas and Sivaji Bandyopadhyay, “Detection of Diabetic Retinopathy using Convolutional Neural Networks for Feature Extraction and Classification (DRFEC)”, Multimedia Tools and Applications, vol. 82, pp. 29943–30001, Nov. 2022, doi: 10.1007/s11042-022-14165-4.

Xiaoling Luo, Wei Wang, Yong Xu1, Zhihui Lai, Xiaopeng Jin, Bob Zhang, et al., “A deep convolutional neural network for diabetic retinopathy detection via mining local and long‐range dependence”, CAAI Transactions on Intelligence Technology 2022, pp. 153-166, Jan. 2023, doi: 10.1049/cit2.12155.

Guanghua Zhang, Bin Sun, Zhixian Chen, Yuxi Gao, Zhaoxia Zhang, Keran Li, et al. “Diabetic Retinopathy Grading by Deep Graph Correlation Network on Retinal Images Without Manual Annotations”, Frontiers in Medicine, vol. 9, Apr. 2022, pp. 1-9, doi: 10.3389/fmed.2022.872214.

A. M. Mutawa, Shahad Alnajdi and Sai Sruthi, “Transfer Learning for Diabetic Retinopathy Detection: A Study of Dataset Combination and Model Performance”, Applied Sciences, vol. 13, no. 9, pp. 1-17, May 2023, doi: 10.3390/app13095685.

Abdul Rahaman Wahab Sait, “A Lightweight Diabetic Retinopathy Detection Model Using a Deep-Learning Technique, diagnostics”, Diagnostics, vol. 13, no. 19 , pp. 1-18, Oct. 2023, doi: 10.3390/diagnostics13193120.

Chaichana Suedumrong, Suriya Phongmoo, Tachanat Akarajaka and Komgrit Leksakul, “Diabetic Retinopathy Detection Using Convolutional Neural Networks with Background Removal, and Data Augmentation”, Applied Sciences, vol. 14, no. 19, pp. 1-16, Sep. 2024, doi: 10.3390/app14198823.

Mohamed Touati, Rabeb Touati, Laurent Nana, Faouzi Benzarti and Sadok Ben Yahia, “DRCCT: Enhancing Diabetic Retinopathy Classification with a Compact Convolutional Transformer”, Big Data and Cognitive Computing, vol. 9, no. 1, pp. 1-25, Jan. 2025, doi: 10.3390/bdcc9010009.

Saranya, P., Umamaheswari, K.M., Patnaik, S.C., Patyal and J.S., “Red Lesion Detection in Color Fundus Images for Diabetic Retinopathy Detection” in Proceedings of International Conference on Deep Learning, Computing and Intelligence. Advances in Intelligent Systems and Computing, Springer Singapore, vol 1396, Apr. 2022, doi: 10.1007/978-981-16-5652-1_50.

Muhammad Mohsin Butt, D. N. F. Awang Iskandar, Sherif E. Abdelhamid, Ghazanfar Latif, Runna Alghazo “Diabetic Retinopathy Detection from Fundus Images of the Eye Using Hybrid Deep Learning Features” , diagnostics, MDPI 2022, vol. 12, no. 7, pp. 1-17, Jul. 2022, doi: 10.3390/diagnostics12071607.

Brahami Menaouer, Zoulikha Dermane, Nour El Houda Kebir, Nada Matta, “Diabetic Retinopathy Classification Using Hybrid Deep Learning Approach”, SN Computer Science, vol. 3, Jul. 2022, doi: 10.1007/s42979-022-01240-8.

Md. Nahiduzzaman, Md. Robiul Islam, Md. Omaer Faruq Goni, Md. Shamim Anower, Mominul Ahsan, Julfikar Haider, et al. “Diabetic retinopathy identification using parallel convolutional neural network based feature extractor and ELM classifier”, Expert Systems with Applications, vol. 217, pp. 1-11, May 2023, doi: 10.1016/j.eswa.2023.119557.

Ghadah Alwakid, Walaa Gouda, Mamoona Humayun and NZ Jhanjhi, “Enhancing diabetic retinopathy classification using deep learning”, Digital Health, vol. 9, Aug. 2023, doi: 10.1177/20552076231194942.

Huanqing Xu, Xian Shao, Dandan Fang, Fangliang Huang “A hybrid neural network approach for classifying diabetic retinopathy subtypes”, Frontiers in Medicine, pp. 1-13, Jan. 2024, doi: 10.3389/fmed.2023.1293019.

Diabetic Retinopathy Detection Competition Dataset Resized/Cropped, https://www.kaggle.com/tanlikesmath/diabetic-retinopathy-resized, last accessed 2025/05/27.

Ze Liu, Han Hu, Yutong Lin, Zhuliang Yao, Zhenda Xie, Yixuan Wei, et al., “Swin Transformer V2: Scaling Up Capacity and Resolution”, in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12009-12019, Sep. 2022, doi: 10.1109/CVPR52688.2022.01170.

Gazi Jannatul Ferdous, Khaleda Akhter Sathi, Md. Azad Hossain and M. Ali Akber Dewan, “SPT-Swin: A Shifted Patch Tokenization Swin Transformer for Image Classification”, IEEE Access, vol. 12, pp. 117617- 117626, Aug. 2024, doi: 10.1109/ACCESS.2024.3448304.

Mira Hayati, Kahlil Muchtar, Roslidar, Novi Maulina, Irfan Syamsuddin, Gregorius Natanael Elwirehardha, et al., “Impact of CLAHE-based image enhancement for diabetic retinopathy classification through deep learning”, in 7th International Conference on Computer Science and Computational Intelligence 2022, vol. 216, pp. 57-66, 2023, doi: 10.1016/j.procs.2022.12.111.

Olubunmi Sule and Serestina Viriri, “Contrast Enhancement of RGB Retinal Fundus Images for Improved Segmentation of Blood Vessels Using Convolutional Neural Networks”, Journal of Digital Imaging, Springer (2022), vol 36, pp. 414-432, Dec. 2022 doi: 10.1007/s10278-022-00738-0.

Ishak Pacal, “A novel Swin transformer approach utilizing residual multi‑layer perceptron for diagnosing brain tumors in MRI images”, International Journal of Machine Learning and Cybernetics, Springer 2024, vol. 15, pp. 3579-3597, Mar. 2024, doi: 10.1007/s13042-024-02110-w.

Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, et al., “PyTorch: An Imperative Style, High-Performance Deep Learning Library”, in 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), pp. 8026-8037, Dec. 2019, doi: 10.5555/3454287.3455008.

Sheetal J. Nagar and Nikhil Gondaliya, “Identification of Severity Level for Diabetic Retinopathy Detection Using Neural Networks” in International Conference on Data Science and Applications 2023, Lecture Notes in Networks and Systems, Springer, Singapore 2024, vol. 818, pp. 205-220, doi: 10.1007/978-981-99-7862-5_16.

Shuhe Zhang, Carroll A. B. Webers and Tos T. J. M. Berendschot, “Computational singlefundus image restoration techniques: a review”, Frontiers in Ophthalmology, vol. 4, pp. 1-18, Jun. 2024, doi: https://doi.org/10.3389/fopht.2024.1332197.

Zhaomin Yao, Yizhe Yuan, Zhenning Shi, Wenxin Mao, Gancheng Zhu, Guoxu Zhang and Zhiguo Wang, “FunSwin: A deep learning method to analysis diabetic retinopathy grade and macular edema risk based on fundus images”, Frontiers in Physiology, vol. 13, pp. 1-9, Jul. 2022, doi: https://doi.org/10.3389/fphys.2022.961386.




DOI: http://doi.org/10.11591/ijict.v15i2.pp750-758

Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Sheetal Jiwanbhai Nagar

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

The International Journal of Informatics and Communication Technology (IJ-ICT)
p-ISSN 2252-8776, e-ISSN 2722-2616
This journal is published by the Intelektual Pustaka Media Utama (IPMU).

Web Analytics View IJICT Stats