2692-4048ISSN (Online)
2770-0070ISSN (Print)
Volume 21 , Issue 2 , PP: 228-240, 2026 | Cite this article as | XML | Html | PDF | Full Length Article
Nazar Salih Absulhussein 1 * , Bashar I. Hameed 2 , Humam K. Yaseen 3 , Nebras H. Ghaeb 4 , Mohamed Ksantini 5
Doi: https://doi.org/10.54216/FPA.210215
Retinopathy of prematurity (ROP) remains the leading cause of blindness in children. The detection and treatment of this disease mainly depend on subjective evaluation of the features of retinal blood vessels. This method is not only time-consuming but also prone to errors. The increasing number of such cases demands an urgent need for automated models to improve the accuracy and efficiency of diagnosis and treatment. This paper presents a method for early detection of ROP using the Swin Transformer, a hierarchical vision transformer architecture. This work focuses solely on the screening stages for ROP, as documented between 2015 and 2020, based on a dataset composed of 3720 retinal images from preterm infants, kindly made available by the Al-Amal Eye Center located in Baghdad, Iraq. The proposed model achieved a classification accuracy of 98.67% on a clinical ROP dataset. The results highlight the importance of the most recent in-depth learning methods in enhancing early detection techniques, ultimately leading to improved clinical outcomes for at-risk infants.
Health Care , Deep Learning , Retinopathy of Prematurity , Fundus Images , Swin Transformer
[1] G. Skedsmo and S. G. Huber, "Assessing learning gaps and gains?," Educ. Assess. Eval. Account., vol. 35, no. 4, pp. 471–473, Nov. 2023, doi: 10.1007/s11092-023-09423-4.
[2] E. H. Hong, Y. U. Shin, and H. Cho, "Retinopathy of prematurity: a review of epidemiology and current treatment strategies," Clin. Exp. Pediatr., vol. 65, no. 3, pp. 115–126, Oct. 2021, doi: 10.3345/cep.2021.00773.
[3] J. M. Brown et al., "Automated Diagnosis of Plus Disease in Retinopathy of Prematurity Using Deep Convolutional Neural Networks," JAMA Ophthalmol., vol. 136, no. 7, p. 803, Jul. 2018, doi: 10.1001/jamaophthalmol.2018.1934.
[4] Early Treatment for Retinopathy of Prematurity Cooperative Group, "The Incidence and Course of Retinopathy of Prematurity: Findings From the Early Treatment for Retinopathy of Prematurity Study," Pediatrics, vol. 116, no. 1, pp. 15–23, Jul. 2005, doi: 10.1542/peds.2004-1413.
[5] "An international classification of retinopathy of prematurity," Pediatrics, vol. 74, no. 1, pp. 127–133, Jul. 1984.
[6] "An international classification of retinopathy of prematurity. II. The classification of retinal detachment. The International Committee for the Classification of the Late Stages of Retinopathy of Prematurity," Arch. Ophthalmol., vol. 105, no. 7, pp. 906–912, Jul. 1987.
[7] International Committee for the Classification of Retinopathy of Prematurity, "The International Classification of Retinopathy of Prematurity revisited," Arch. Ophthalmol., vol. 123, no. 7, pp. 991–999, Jul. 2005, doi: 10.1001/archopht.123.7.991.
[8] M. F. Chiang et al., "International Classification of Retinopathy of Prematurity, Third Edition," Ophthalmology, vol. 128, no. 10, pp. e51–e68, Oct. 2021, doi: 10.1016/j.ophtha.2021.05.031.
[9] J. Wang et al., "A Deep Learning System for Automated Diagnosis of Plus Disease in Retinopathy of Prematurity with Quantifiable Measurement of Vascularity," JAMA Ophthalmol., vol. 140, no. 5, pp. 491–499, May 2022, doi: 10.1001/jamaophthalmol.2022.0783.
[10] G. M. Richter, S. L. Williams, J. Starren, J. T. Flynn, and M. F. Chiang, "Telemedicine for Retinopathy of Prematurity Diagnosis: Evaluation and Challenges," Surv. Ophthalmol., vol. 54, no. 6, pp. 671–685, Nov. 2009, doi: 10.1016/j.survophthal.2009.02.020.
[11] Das et al., "Breast cancer detection using an ensemble deep learning method," Biomed. Signal Process. Control, vol. 70, p. 103009, Sep. 2021, doi: 10.1016/j.bspc.2021.103009.
[12] Bhandary et al., "Deep-learning framework to detect lung abnormality – A study with chest X-Ray and lung CT scan images," Pattern Recognit. Lett., vol. 129, pp. 271–278, Jan. 2020, doi: 10.1016/j.patrec.2019.11.013.
[13] N. Salih et al., "An Advanced Approach for Predicting ROP Stages: Deep Learning Algorithms and Belief Function Technique," Iraqi J. Sci., pp. 4047–4060, Jul. 2024, doi: 10.24996/ijs.2024.65.7.39.
[14] Z. Liu et al., "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows," arXiv:2103.14030, Aug. 2021.
[15] J. Liang, J. Cao, G. Sun, K. Zhang, L. Van Gool, and R. Timofte, "SwinIR: Image Restoration Using Swin Transformer," arXiv:2108.10257, Aug. 2021.
[16] Z. Liao, K. Xu, and N. Fan, "Swin Transformer Assisted Prior Attention Network for Medical Image Segmentation," in Proc. 8th Int. Conf. Comput. Artif. Intell., 2022, pp. 491–497, doi: 10.1145/3532213.3532287.
[17] H. Li et al., "DnSwin: Toward real-world denoising via a continuous Wavelet Sliding Transformer," Knowl.-Based Syst., vol. 255, p. 109815, Nov. 2022, doi: 10.1016/j.knosys.2022.109815.
[18] S. Hao, B. Wu, K. Zhao, Y. Ye, and W. Wang, "Two-Stream Swin Transformer with Differentiable Sobel Operator for Remote Sensing Image Classification," Remote Sens., vol. 14, no. 6, p. 1507, Mar. 2022, doi: 10.3390/rs14061507.
[19] R. A. Dihin, E. AlShemmary, and W. Al-Jawher, "Diabetic Retinopathy Classification Using Swin Transformer with Multi Wavelet," J. Kufa Math. Comput., vol. 10, no. 2, pp. 167–172, Aug. 2023, doi: 10.31642/JoKMC/2018/100225.
[20] Md. M. Haque, S. Akter, and A. F. Ashrafi, "SwinMedNet: Leveraging Swin Transformer for Robust Diabetic Retinopathy Classification from the RetinaMNIST2D Dataset," in Proc. 6th Int. Conf. Elect. Eng. Inf. Commun. Technol. (ICEEICT), May 2024, pp. 1286–1291, doi: 10.1109/ICEEICT62016.2024.10534544.
[21] Dosovitskiy et al., "An image is worth 16x16 words: Transformers for image recognition at scale," in Int. Conf. Learn. Represent., 2021. [Online]. Available: https://arxiv.org/abs/2010.11929
[22] H. Touvron, M. Cord, M. Douze, F. Massa, A. Sablayrolles, and H. Jégou, "Training data-efficient image transformers & distillation through attention," in Proc. 38th Int. Conf. Mach. Learn., 2021. [Online]. Available: https://arxiv.org/abs/2012.12877
