Abstract
Artificial intelligence (AI) has shown promise in retinal imaging, yet its application to longitudinal optical coherence tomography angiography (OCTA) remains limited. This study developed and evaluated an AI model for classifying treatment response in neovascular age-related macular degeneration (nAMD) using paired OCTA images acquired before and after anti-VEGF therapy. In this retrospective cohort study, paired OCTA en-face images and corresponding OCT B-scans were collected for each treatment course. OCTA image pairs were manually segmented and aligned for AI input, while ground-truth labels (Improved, Unchanged, Worsened) were determined based on structural OCT findings and clinical visual acuity outcomes. After quality exclusion, 1033 OCTA pairs were included and divided into training, validation, and independent testing subsets. Two experienced retina specialists graded all OCTA pairs for comparison. On the test set, the AI model achieved an overall accuracy of 82.08%, with class-specific accuracies of 74.29% (worsened), 81.48% (unchanged), and 88.64% (improved). In contrast, overall human grading accuracy was 61.40%. Human graders were significantly more likely to misclassify treatment response than the AI model for all groups (odds ratio = 2.88; 95% CI 1.68–4.92; p < 0.0001). These findings demonstrate that AI-based paired OCTA analysis can provide a more accurate and objective assessment of treatment response in nAMD.
Data availability
The data that support the findings of this study are not publicly available due to patient privacy considerations but are available from the corresponding author, Dr. William R. Freeman, upon reasonable request.
References
Bourne, R. R. A. et al. Causes of vision loss worldwide, 1990–2010: A systematic analysis. Lancet Glob. Health. 1, (2013).
Baybora, H. Perifoveal retinal thickness changes after intravitreal aflibercept injection for choroidal neovascularization in age-related macular degeneration. Photodiagn. Photodyn. Ther. 46, (2024).
Garweg, J. G. et al. Continued anti-VEGF treatment does not prevent recurrences in eyes with stable neovascular age-related macular degeneration using a treat-and-extend regimen: a retrospective case series. Eye (Lond). 36, 862–868 (2022).
Spaide, R. F. et al. Consensus nomenclature for reporting neovascular age-related macular degeneration data: Consensus on neovascular age-related macular degeneration nomenclature study group. Ophthalmology. 127, 616–636 (2020).
Faatz, H. & Lommatzsch, A. Overview of the use of optical coherence tomography angiography in neovascular age-related macular degeneration. J. Clin. Med. 13, 5042 (2024).
Brown, D. M. et al. Ranibizumab versus verteporfin for neovascular age-related macular degeneration. N. Engl. J. Med. 355, 1432–1444 (2006).
Liang, M. C. et al. Retina. 36, 2265–2273 (2016).
Kozak, I. et al. Discrepancy between fluorescein angiography and optical coherence tomography in detection of macular disease. Retina. 28, 538 (2008).
El Ameen, A. et al. Type 2 neovascularization secondary to age-related macular degeneration imaged by optical coherence tomography angiography. Retina. 35, 2212–2218 (2015).
Kuehlewein, L. et al. Optical coherence tomography angiography of type 1 neovascularization in age-related macular degeneration. Am. J. Ophthalmol. 160, 739–748e2 (2015).
Faatz, H. & Lommatzsch, A. Overview of the use of optical coherence tomography angiography in neovascular age-related macular degeneration. J. Clin. Med.. 13, 5042 (2024).
Choi, M., Kim, S. W., Yun, C., Oh, J. H. & Oh, J. Predictive role of optical coherence tomography angiography for exudation recurrence in patients with type 1 neovascular age-related macular degeneration treated with pro-re-nata protocol. Eye 37, 34 (2022).
Hormel, T. T. et al. Artificial intelligence in OCT angiography. Prog. Retin Eye Res. 85, (2021).
Burlina, P. M. et al. Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks. JAMA Ophthalmol. 135, 1170–1176 (2017).
Hormel, T. T. et al. Artificial intelligence in OCT angiography. Prog. Retin Eye Res. 85, (2021).
Heinke, A. et al. Artificial intelligence for OCTA-based disease activity prediction in age-related macular degeneration. Retina 44, 465 (2024).
Wongchaisuwat, N. et al. Detection of macular neovascularization in eyes presenting with macular edema using OCT angiography and a deep learning model. Ophthalmol. Retina. 9, 378–385 (2025).
Heinke, A. et al. Cross-instrument optical coherence tomography-angiography (OCTA)-based prediction of age-related macular degeneration (AMD) disease activity using artificial intelligence. Sci. Rep. 14, (2024).
Morsy, M. S. et al. Effect of faricimab on optical coherence tomography angiography and artificial intelligence-based analysis in resistant choroidal neovascularization. Ophthalmologica. 1–10. https://doi.org/10.1159/000548690 (2025).
Fırat, M. et al. AI-based response classification after anti-VEGF loading in neovascular age-related macular degeneration. Diagnostics. 15, 15 (2025).
Miere, A. et al. Retina. 39, 548–557 (2019).
Faatz, H. et al. The architecture of macular neovascularizations predicts treatment responses to anti-VEGF therapy in neovascular AMD. Diagnostics (Basel). 12, (2022).
Acknowledgements
The authors would like to acknowledge the following financial support: This article has been supported in part by UCSD Vision Research Center Core Grant P30EY022589, NIH grant R01EY033847, an unrestricted grant from Research to Prevent Blindness, NY (WRF), and unrestricted funds from UCSD Jacobs Retina Center.
Funding
This article has been supported in part by UCSD Vision Research Center Core Grant P30EY022589, NIH grant R01EY033847, an unrestricted grant from Research to Prevent Blindness, NY (WRF), and unrestricted funds from UCSD Jacobs Retina Center. No conflicting relationship exists for any author. No author(s) have commercial associations that pose conflict of interest in connection with the submitted article.
Author information
Authors and Affiliations
Contributions
Conception and design: M.M., W.R.F. Data collection: M.M., N.N.M., A.L.A., S.J. Analysis and interpretation: M.M., L.C. Methodology and software development (AI model): N.A.D., H.Z.C.A., T.N. Writing-original draft: M.M. Writing review and editing: M.M., N.N.M., A.L.A., E.I.E., M.M.K., H.A.E., W.R.F., D.U.B. Obtainment of funding: W.R.F., D.U.B .The guarantor: WRF. All authors listed have contributed to the work and approved the final version of the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethics Statement
Institutional Review Board approval was obtained from the University of California San Diego for review of patient charts and imaging data (IRB #120516). Due to the retrospective nature of the study, the requirement for informed consent was waived by the IRB. The study was conducted in accordance with the tenets of the Declaration of Helsinki and complied with the Health Insurance Portability and Accountability Act (HIPAA) regulations. All data were de-identified to ensure patient confidentiality.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Morsy, M.S., Dutta, N.A., Eldessouky, E.I. et al. Artificial intelligence based assessment of treatment response in wet age related macular degeneration using paired OCT angiography. Sci Rep (2026). https://doi.org/10.1038/s41598-026-42999-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-42999-7
