International Journal of Information Technology and Computer Science (IJITCS)
IJITCS Vol. 17, No. 6, 8 Dec. 2025
Cover page and Table of Contents: PDF (size: 796KB)
A Swin-transformer Integrated with Radial Optimization Model for Accurate Diabetic Retinopathy Detection and Classification
PDF (796KB), PP.160-175
Views: 0 Downloads: 0
Author(s)
Vijayalaxmi Gopu
1,*
M. Selvi
1
Index Terms
Diabetic Retinopathy (DR), Deep Learning, Transformer Model, Classification, Optimization, and Disease Detection
Abstract
According to anticipation, Diabetic Retinopathy (DR) is one among the most potential causes of visual disability and even blindness across the globe. Prompt diagnosis and treatment will stall the development towards irreversible damage. Hence, detection and staging of DR must play a huge role in early medical intervention and treatment planning. There exist tremendous challenges in accuracy, ability to capture retinal features, overfitting from poorly represented features, and inefficiencies in optimisation of parameters. These are likely to provide a very challenging situation for the clinical application of these methods, especially when dealing with huge heterogeneous datasets. The paper is discussing a new hybrid framework for detection and classification of DR that integrates the Swin-Transformer Integrated radial Residual Network (Swin-RadialNet) with a Butterfly-Mayfly Radial Optimizer (BMRO). This framework is intended to address those challenges. Hierarchical extraction of features from a model trained with radial residual connections atop the Swin Transformer architecture is carried out by Swin-RadialNet to guarantee the best learning of the complex k structures in retina on-the-fly through BMRO, which would act as an optimizer hybridizing to estimate radial spread parameters, thereby supporting acceleration of models' performance and converging rates. The core novelties of the proposed method shall lie in merging advanced transformer-based feature extraction with nature-inspired hybrid optimization to tackle efficiently critical issues regarding feature abstraction, parameter fine-tuning, and classification reliability. The method will be evaluated on several benchmark datasets such as Kaggle's Diabetic Retinopathy and APTOS 2019, and will expect to show state-of-the-art results for all DR stages in terms of accuracy, precision, recall, and F1-score.
Cite This Paper
Vijayalaxmi Gopu, M. Selvi, "A Swin-transformer Integrated with Radial Optimization Model for Accurate Diabetic Retinopathy Detection and Classification", International Journal of Information Technology and Computer Science(IJITCS), Vol.17, No.6, pp.160-175, 2025. DOI:10.5815/ijitcs.2025.06.09
Reference
[1]D. Muthusamy and P. Palani, "Deep neural network model for diagnosing diabetic retinopathy detection: An efficient mechanism for diabetic management," Biomedical Signal Processing and Control, vol. 100, p. 107035, 2025.
[2]S. A. Kumar, J. S. Kumar, and S. C. Bharadwaj, "Efficient diabetic retinopathy detection using deep learning approaches and Raspberry Pi 4," Bulletin of Electrical Engineering and Informatics, vol. 14, pp. 1063-1072, 2025.
[3]M. Hussain, H. A. Ahmed, M. Z. Babar, A. Ali, H. Shahzad, S. ur Rehman, et al., "An Enhanced Convolutional Neural Network (CNN) based P-EDR Mechanism for Diagnosis of Diabetic Retinopathy (DR) using Machine Learning," Engineering, Technology & Applied Science Research, vol. 15, pp. 19062-19067, 2025.
[4]A. Biswas and R. Banik, "Deep Learning‐Based Image Segmentation for Early Detection of Diabetic Retinopathy and Other Retinal Disorders," Deep Learning Applications in Medical Image Segmentation: Overview, Approaches, and Challenges, pp. 133-148, 2025.
[5]Choubey, S. B., Chitra, T., & Hephzipah, J. J. (2024). Big Data Mining for Chronic Disease Prediction using Principal Component Analysis and eXtreme Gradient Boosting. GK International Journal of Advanced Research in Engineering and Technology, 1(1), 1-11.
[6]Anusuya, S., & Jayarin, P. J. (2017, March). Survey on multimodel biometrics on human identification using real time filtering algorithm. In 2017 Third International Conference on Science Technology Engineering & Management (ICONSTEM) (pp. 142-147). IEEE.
[7]Y. Tao, M. Xiong, Y. Peng, L. Yao, H. Zhu, Q. Zhou, et al., "Machine learning-based identification and validation of immune-related biomarkers for early diagnosis and targeted therapy in diabetic retinopathy," Gene, vol. 934, p. 149015, 2025.
[8]G. Maheswari and S. Gopalakrishnan, "Advanced Attention Capsule Network with Curved Wavelet Attention for Illuminating Low-Light Capsule Endoscopy," in 2024 IEEE 3rd World Conference on Applied Intelligence and Computing (AIC), 2024, pp. 1148-1154.
[9]V. K. Isukapalli, R. D. Kumar, and S. Gopalakrishnan, "Image-Based Bone Marrow Malignancy Detection: Motivation, Challenges and Recommendations," in 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), 2024, pp. 1-6.
[10]R. Kavitha, "A Deep Learning Framework to Detect Diabetic Retinopathy Using CNN," in Deep Learning in Medical Image Analysis, ed: Chapman and Hall/CRC, 2025, pp. 79-96.
[11]A. K. Singh, S. Madarapu, and S. Ari, "Diabetic retinopathy grading based on multi-scale residual network and cross-attention module," Digital Signal Processing, vol. 157, p. 104888, 2025.
[12]S. Aftab and S. Akhtar, "Diabetic Retinopathy Severity Classification Using Data Fusion and Ensemble Transfer Learning," Journal of Software Engineering and Applications, vol. 18, pp. 1-23, 2025.
[13]R. Manjushree, D. Bhoomika, R. R. Nair, and T. Babu, "Automated detection of diabetic retinopathy using deep learning in retinal fundus images: analysis," in 2022 3rd International Conference on Communication, Computing and Industry 4.0 (C2I4), 2022, pp. 1-6.
[14]N. M. Suganthi and M. Arun, "Diabetic retinopathy grading using curvelet CNN with optimized SSO activations and wavelet-based image enhancement," Ain Shams Engineering Journal, vol. 16, p. 103239, 2025.
[15]G. Maheswari and S. Gopalakrishnan, "A smart multimodal framework based on squeeze excitation capsule network (SECNet) model for disease diagnosis using dissimilar medical images," International Journal of Information Technology, pp. 1-19, 2024.
[16]N. Kavitha and N. Kasthuri, "An efficient automatic diabetic retinopathy grading using a two-way cascaded convolution neural network," Discover Computing, vol. 28, pp. 1-16, 2025.
[17]M. Akram, M. Adnan, S. F. Ali, J. Ahmad, A. Yousef, T. A. N. Alshalali, et al., "Uncertainty-aware diabetic retinopathy detection using deep learning enhanced by Bayesian approaches," Scientific Reports, vol. 15, p. 1342, 2025.
[18]K. Kaushik, A. Bhardwaj, X. Cheng, S. Dahiya, A. Shankar, M. Kumar, et al., "Residual Network-Based Deep Learning Framework for Diabetic Retinopathy Detection," Journal of Database Management (JDM), vol. 36, pp. 1-21, 2025.
[19]I. Govindharaj, A. Poongodai, G. Rajaram, D. Santhakumar, S. Ravichandran, K. Udayakumar, et al., "Enhanced diabetic retinopathy detection using U-shaped network and capsule network-driven deep learning," MethodsX, vol. 14, p. 103052, 2025.
[20]G. Neri, S. Sharma, B. Ghezzo, C. Novarese, C. Olivieri, D. Tibaldi, et al., "Deep learning model for automatic detection of different types of microaneurysms in diabetic retinopathy," Eye, pp. 1-8, 2025.
[21]A. Ikram and A. Imran, "ResViT FusionNet Model: An explainable AI-driven approach for automated grading of diabetic retinopathy in retinal images," Computers in Biology and Medicine, vol. 186, p. 109656, 2025.
[22]U. Bhimavarapu, "Automated detection of diabetic retinopathy using an improved deep learning model with smartphone images," International Journal of Diabetes in Developing Countries, pp. 1-13, 2025.
[23]A. Luong, J. Cheung, S. McMurtry, C. Nelson, T. Najac, P. Ortiz, et al., "Comparison of Machine Learning Models to a Novel Score in the Identification of Patients at Low Risk for Diabetic Retinopathy," Ophthalmology Science, vol. 5, p. 100592, 2025.
[24]R. Manohar and M. S. Aarthi, "Leveraging Deep Learning for Early Stage Diabetic Retinopathy Detection: a Novel CNN and Transfer Learning Comparision," in 2024 2nd International Conference on Artificial Intelligence and Machine Learning Applications Theme: Healthcare and Internet of Things (AIMLA), 2024, pp. 1-6.
[25]S. Guefrachi, A. Echtioui, and H. Hamam, "Diabetic Retinopathy Detection Using Deep Learning Multistage Training Method," Arabian Journal for Science and Engineering, pp. 1-18, 2024.