Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Deep learning algorithms for timely diagnosis of retinopathy of prematurity requiring treatment

Eye volume 40, pages 63–70 (2026)Cite this article

Subjects

Abstract

Background/objectives

To evaluate the effectiveness of deep learning (DL) algorithms in diagnosing Retinopathy of Prematurity (ROP) cases that requires treatment using fundus images submitted to the ROP clinic as part of a telemedicine consultation system.

Subjects/methods

This retrospective cross-sectional study analysed 1700 RetCam fundus images from 141 preterm infants screened for ROP at Khatam-Al-Anbia Eye Hospital. The images underwent preprocessing using Contrast Limited Adaptive Histogram Equalisation (CLAHE), Automated Multiscale Retinex (AMSR), and a machine learning-based optimisation approach (ML). Various convolutional neural network (CNN) models such as MobileNet, ResNet-18, ResNet-50, and DenseNet-121, were evaluated for their diagnostic performance utilising accuracy, sensitivity, specificity, and F1-score metrics.

Results

Among the models tested, MobileNet with CLAHE preprocessing achieved the highest accuracy (91.39%) and sensitivity (94.90%), establishing it as the most effective model for ROP detection. DenseNet-121 with CLAHE preprocessing showcased high sensitivity (94.26%) but slightly lower accuracy (90.98%). Additionally, ResNet-50 with AMSR preprocessing also demonstrated high accuracy (90.58%) and sensitivity (91.44%). These findings underscore the feasibility of DL models for real-time ROP screening in telemedicine environments.

Conclusion

MobileNet with CLAHE preprocessing exhibited the highest diagnostic performance in identifying treatment-requiring ROP, positioning it as a promising tool for AI-assisted screening. Further validation in varied clinical settings is necessary to confirm its real-world applicability.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

USD 39.95

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Two sets of images illustrate various enhancement methods used in the study.
Fig. 2: Receiver operating characteristic (ROC) curves and the area under the curve (AUC) of three models with highest accuracies in the study.

Similar content being viewed by others

Data availability

The datasets used during the current study are available from the corresponding author on reasonable request.

References

  1. Chen J, Smith LE. Retinopathy of prematurity. Angiogenesis. 2007;10:133–40.

    Article  PubMed  Google Scholar 

  2. Hellström A, Smith LE, Dammann O. Retinopathy of prematurity. lancet. 2013;382:1445–57.

    Article  PubMed  PubMed Central  Google Scholar 

  3. Azami M, Jaafari Z, Rahmati S, Farahani AD, Badfar G. Prevalence and risk factors of retinopathy of prematurity in Iran: a systematic review and meta-analysis. BMC Ophthalmol. 2018;18:1–14.

    Article  Google Scholar 

  4. Gebeşçe A, Uslu H, Keleş E, Yildirim A, Gürler B, Yazgan H, et al. Retinopathy of prematurity: incidence, risk factors, and evaluation of screening criteria. Turkish J Med Sci. 2016;46:315–20.

    Article  Google Scholar 

  5. Ozen Tunay Z, Ustunyurt Z, Idil A. Causes of severe visual impairment in infants and methods of management. Eye. 2021;35:1191–7.

    Article  PubMed  Google Scholar 

  6. Solebo AL, Teoh L, Rahi J. Epidemiology of blindness in children. Archives Dis Child. 2017;102:853–7.

    Article  Google Scholar 

  7. Jonas DE, Amick HR, Wallace IF, Feltner C, Vander Schaaf EB, Brown CL, et al. Vision screening in children aged 6 months to 5 years: evidence report and systematic review for the US Preventive Services Task Force. JAMA. 2017;318:845–58.

    Article  PubMed  Google Scholar 

  8. Gilbert C, Fielder A, Gordillo L, Quinn G, Semiglia R, Visintin P, et al. Characteristics of infants with severe retinopathy of prematurity in countries with low, moderate, and high levels of development: implications for screening programs. Pediatrics. 2005;115:e518–e25.

    Article  PubMed  Google Scholar 

  9. García H, Villasis-Keever MA, Zavala-Vargas G, Bravo-Ortiz JC, Pérez-Méndez A, Escamilla-Núñez A. Global Prevalence and Severity of Retinopathy of Prematurity over the Last Four Decades (1985–2021): A Systematic Review and Meta-Analysis. Archives Med Res. 2024;55:102967.

    Article  Google Scholar 

  10. Hansen ED, Hartnett ME. A review of treatment for retinopathy of prematurity. Expert Rev Ophthalmol. 2019;14:73–87.

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  11. Quinn GE, Ying G-s, Daniel E, Hildebrand PL, Ells A, Baumritter A, et al. Validity of a telemedicine system for the evaluation of acute-phase retinopathy of prematurity. JAMA Ophthalmol. 2014;132:1178–84.

    Article  PubMed  Google Scholar 

  12. Hoffer-Hawlik M, Moran A, Zerihun L, Usseglio J, Cohn J, Gupta R. Telemedicine interventions for hypertension management in low-and middle-income countries: a scoping review. PLoS ONE. 2021;16:e0254222.

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  13. Mahmoud K, Jaramillo C, Barteit S. Telemedicine in low-and middle-income countries during the COVID-19 pandemic: a scoping review. Front Public Health. 2022;10:914423.

    Article  PubMed  PubMed Central  Google Scholar 

  14. Lu W, Tong Y, Yu Y, Xing Y, Chen C, Shen Y. Applications of artificial intelligence in ophthalmology: general overview. J Ophthalmol. 2018;2018:5278196.

    PubMed  PubMed Central  Google Scholar 

  15. Zhang J, Liu Y, Mitsuhashi T, Matsuo T. Accuracy of Deep Learning Algorithms for the Diagnosis of Retinopathy of Prematurity by Fundus Images: A Systematic Review and Meta-Analysis. J Ophthalmol. 2021;2021:8883946.

    PubMed  PubMed Central  Google Scholar 

  16. Bai A, Carty C, Dai S. Performance of deep-learning artificial intelligence algorithms in detecting retinopathy of prematurity: A systematic review. Saudi J Ophthalmol. 2022;36:296–307.

    Article  PubMed  PubMed Central  Google Scholar 

  17. Ramanathan A, Athikarisamy SE, Lam GC. Artificial intelligence for the diagnosis of retinopathy of prematurity: a systematic review of current algorithms. Eye. 2023;37:2518–26.

    Article  PubMed  Google Scholar 

  18. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521:436–44.

    Article  PubMed  CAS  Google Scholar 

  19. Coyner AS, Murickan T, Oh MA, Young BK, Ostmo SR, Singh P, et al. Multinational external validation of autonomous retinopathy of prematurity screening. JAMA Ophthalmol. 2024;142:327–35.

    Article  PubMed  Google Scholar 

  20. Young BK, Cole ED, Shah PK, Ostmo S, Subramaniam P, Venkatapathy N, et al. Efficacy of smartphone-based telescreening for retinopathy of prematurity with and without artificial intelligence in India. JAMA Ophthalmol. 2023;141:582–8.

    Article  PubMed  PubMed Central  Google Scholar 

  21. Nguyen TAL, Raileanu V, Smith B, Griffin A, Shah S. Excellent accuracy of trained neonatal nurses in the detection of referral-warranted retinopathy of prematurity within an established telemedicine screening programme. J Paediatrics Child Health. 2024;60:369–74.

    Article  Google Scholar 

  22. Chiang MF, Quinn GE, Fielder AR, Ostmo SR, Chan RP, Berrocal A, et al. International classification of retinopathy of prematurity. Ophthalmology. 2021;128:e51–e68.

    Article  PubMed  Google Scholar 

  23. Group ETfRoPC. Revised indications for the treatment of retinopathy of prematurity: results of the early treatment for retinopathy of prematurity randomized trial. Archives Ophthalmol. 2003;121:1684–94.

    Article  Google Scholar 

  24. Klaassen B, Van Beijnum B, Hermens HJ. Usability in telemedicine systems—A literature survey. International J Med Inform. 2016;93:57–69.

    Article  CAS  Google Scholar 

  25. Lorenz B, Spasovska K, Elflein H, Schneider N. Wide-field digital imaging based telemedicine for screening for acute retinopathy of prematurity (ROP). Six-year results of a multicentre field study. Graefe’s Arch Clin Exp Ophthalmol. 2009;247:1251–62.

    Article  Google Scholar 

  26. Richter GM, Williams SL, Starren J, Flynn JT, Chiang MF. Telemedicine for retinopathy of prematurity diagnosis: evaluation and challenges. Survey Ophthalmol. 2009;54:671–85.

    Article  Google Scholar 

  27. Brady CJ, D’amico S, Campbell JP. Telemedicine for retinopathy of prematurity. Telemedicine e-Health. 2020;26:556–64.

    Article  PubMed  PubMed Central  Google Scholar 

  28. Campbell JP, Singh P, Redd TK, Brown JM, Shah PK, Subramanian P, et al. Applications of artificial intelligence for retinopathy of prematurity screening. Pediatrics. 2021;147:1–8.

  29. Liu Y, Du Y, Wang X, Zhao X, Zhang S, Yu Z, et al. An Artificial Intelligence System for Screening and Recommending the Treatment Modalities for Retinopathy of Prematurity. Asia-Pac J Ophthalmol. 2023;12:468–76.

    Article  CAS  Google Scholar 

  30. Attallah O. DIAROP: automated deep learning-based diagnostic tool for retinopathy of prematurity. Diagnostics. 2021;11:2034.

    Article  PubMed  PubMed Central  Google Scholar 

  31. Huang Y-P, Vadloori S, Chu H-C, Kang EY-C, Wu W-C, Kusaka S, et al. Deep learning models for automated diagnosis of retinopathy of prematurity in preterm infants. Electronics. 2020;9:1444.

    Article  Google Scholar 

  32. Huang Y-P, Basanta H, Kang EY-C, Chen K-J, Hwang Y-S, Lai C-C, et al. Automated detection of early-stage ROP using a deep convolutional neural network. British J Ophthalmol. 2021;105:1099–103.

    Article  Google Scholar 

  33. Hu J, Chen Y, Zhong J, Ju R, Yi Z. Automated analysis for retinopathy of prematurity by deep neural networks. IEEE Trans Med Imaging. 2018;38:269–79.

    Article  PubMed  Google Scholar 

  34. Wang J, Ju R, Chen Y, Zhang L, Hu J, Wu Y, et al. Automated retinopathy of prematurity screening using deep neural networks. EBioMedicine. 2018;35:361–8.

    Article  PubMed  PubMed Central  Google Scholar 

  35. Tong Y, Lu W, Deng Q-q, Chen C, Shen Y. Automated identification of retinopathy of prematurity by image-based deep learning. Eye Vis. 2020;7:1–12.

    Article  Google Scholar 

  36. Redd TK, Campbell JP, Brown JM, Kim SJ, Ostmo S, Chan RVP, et al. Evaluation of a deep learning image assessment system for detecting severe retinopathy of prematurity. British J Ophthalmol. 2019;103:580–4.

    Article  Google Scholar 

  37. Kıran Yenice E, Kara C, Erdaş ÇB. Automated detection of type 1 ROP, type 2 ROP and A-ROP based on deep learning. Eye. 2024;38:2644–8.

    Article  PubMed  PubMed Central  Google Scholar 

  38. Rice L, Wong E, Kolter Z, editors. Overfitting in adversarially robust deep learning. International conference on machine learning; 2020.

  39. Ruamviboonsuk P, Tiwari R, Sayres R, Nganthavee V, Hemarat K, Kongprayoon A, et al. Real-time diabetic retinopathy screening by deep learning in a multisite national screening programme: a prospective interventional cohort study. Lancet Digital Health. 2022;4:e235–e44.

    Article  PubMed  CAS  Google Scholar 

  40. Bora A, Balasubramanian S, Babenko B, Virmani S, Venugopalan S, Mitani A, et al. Predicting the risk of developing diabetic retinopathy using deep learning. Lancet Digital Health. 2021;3:e10–e9.

    Article  PubMed  CAS  Google Scholar 

Download references

Funding

The authors would like to acknowledge the financial support of the Vice-Chancellor of Research of Mashhad University of Medical Sciences for this research project (code: 4012360). The funding organisation had no role in the design or conduct of this research.

Author information

Authors and Affiliations

  1. Eye Research Center, Mashhad University of Medical Sciences, Mashhad, Iran

    Nasser Shoeibi, Mohammad Reza Ansari Astaneh, Mehrdad Motamed Shariati, Seyedeh Maryam Hosseini, Mojtaba Abrishami, Majid Abrishami, Ghodsieh Zamani & Hamid Reza Heidarzadeh

  2. Faculty of Engineering, Ferdowsi University of Mashhad, Mashhad, Iran

    Nafise Ameri

  3. Medical Informatics Department, Mashhad University of Medical Scienc, Mashhad, Iran

    Mohammad Reza Hoseinkhani

Authors
  1. Nasser Shoeibi
    View author publications

    Search author on:PubMed Google Scholar

  2. Nafise Ameri
    View author publications

    Search author on:PubMed Google Scholar

  3. Mohammad Reza Hoseinkhani
    View author publications

    Search author on:PubMed Google Scholar

  4. Mohammad Reza Ansari Astaneh
    View author publications

    Search author on:PubMed Google Scholar

  5. Mehrdad Motamed Shariati
    View author publications

    Search author on:PubMed Google Scholar

  6. Seyedeh Maryam Hosseini
    View author publications

    Search author on:PubMed Google Scholar

  7. Mojtaba Abrishami
    View author publications

    Search author on:PubMed Google Scholar

  8. Majid Abrishami
    View author publications

    Search author on:PubMed Google Scholar

  9. Ghodsieh Zamani
    View author publications

    Search author on:PubMed Google Scholar

  10. Hamid Reza Heidarzadeh
    View author publications

    Search author on:PubMed Google Scholar

Contributions

NS was designed the work. NS, MRAA, SMH, MMS, MoA, MA, and GZ examined patients images. HRH and NS collected the images. NA and MRH did the CNNs training and tests. HRH and NA analysed the data. All authors were involved in the draughting and review of the manuscript. All authors contributed significantly to this report and agreed to be accountable for all aspects of the work. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Hamid Reza Heidarzadeh.

Ethics declarations

Competing interests

The authors declare no competing interests.

Consent for publication

Consent for publication was acquired from patients.

Ethics approval and consent to participate

This study was approved by the Committee of Ethics in Human Research at Mashhad University of Medical Sciences (IR.MUMS.MEDICAL.REC. 1402.158).

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Shoeibi, N., Ameri, N., Hoseinkhani, M.R. et al. Deep learning algorithms for timely diagnosis of retinopathy of prematurity requiring treatment. Eye 40, 63–70 (2026). https://doi.org/10.1038/s41433-025-04096-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1038/s41433-025-04096-3

This article is cited by

Search

Advanced search

Quick links