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.

  • Comment
  • Published:

Advancing personalised therapy in neovascular AMD through deep learning–based OCT biomarker quantification

Eye volume 40, pages 7–8 (2026)Cite this article

Subjects

We read with great interest the recent article by Asani et al. titled “Evaluation of OCT biomarker changes in treatment-naive neovascular AMD using a deep semantic segmentation algorithm” [1]. The authors present a robust deep learning framework for segmenting 11 OCT biomarkers and provide a large-scale volumetric analysis of treatment-naïve neovascular age-related macular degeneration (nAMD) patients under anti-VEGF therapy. Their work marks a significant step toward data-driven, personalised ophthalmology. Based on their findings, we would like to offer some constructive suggestions for future research and clinical translation.

First, the algorithm’s high performance in segmenting neurosensory retina (F1 ≈ 0.98) and subretinal fluid (SRF) supports its utility in automated OCT analysis. However, the lower F1 scores for subretinal hyperreflective material (SHRM) and fibrovascular pigment epithelial detachment (fPED) highlight the need for improved annotation protocols. As shown in the inter-annotator variability analysis, even experts disagree on ambiguous features like fibrosis. Future studies could incorporate continuous learning frameworks to refine these challenging classes, especially as ambiguous zones may represent transitional pathologies such as fibrotic components within fPED [2].

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

References

  1. Asani B, Holmberg O, Schiefelbein JB, Hafner M, Herold T, Spitzer H, et al. Evaluation of OCT biomarker changes in treatment-naive neovascular AMD using a deep semantic segmentation algorithm. EYE. 2024;38:3180–6.

    Article  PubMed  PubMed Central  Google Scholar 

  2. Ohayon A, De Rosa I, Semoun O, Jung C, Colantuono D, El Ameen A, et al. Subretinal pigment epithelium fibrotic tissue morphological changes after a single anti-vascular endothelial growth factor injection in age-related macular degeneration. Br J Ophthalmol. 2020;104:1855.

    Article  Google Scholar 

  3. Bolz M, Simader C, Ritter M, Ahlers C, Benesch T, Prünte C, et al. Morphological and functional analysis of the loading regimen with intravitreal ranibizumab in neovascular age-related macular degeneration. Br J Ophthalmol. 2010;94:185–9.

    Article  PubMed  Google Scholar 

  4. Cheung CMG, Lai TYY, Ruamviboonsuk P, et al. Polypoidal choroidal vasculopathy: definition, diagnosis, and treatment. Prog Retin Eye Res. 2018;66:1–37.

    Google Scholar 

  5. Guymer RH, Markey CM, McAllister IL, Gillies MC, Hunyor AP, Arnold JJ. Tolerating subretinal fluid in neovascular age-related macular degeneration treated with ranibizumab using a treat-and-extend regimen: FLUID study 24-month results. Ophthalmology. 2019;126:723–34.

    Article  PubMed  Google Scholar 

  6. Schmidt-Erfurth U, Waldstein SM, Klimscha S, Sadeghipour A, Hu X, Gerendas BS, et al. Prediction of individual disease conversion in early AMD using artificial intelligence. Invest Ophthalmol Vis Sci. 2018;59:3199–208.

    Article  PubMed  Google Scholar 

  7. Koch Y, Holmberg O, Spitzer H, et al. Noise transfer for unsupervised domain adaptation of retinal OCT images. In: Medical Image Computing and Computer Assisted Intervention–MICCAI 2022. Springer Nature; 2022:699–708.

  8. Spaide RF, Jaffe GJ, Sarraf D, Freund KB, Sadda SR, Staurenghi G, et al. Consensus nomenclature for reporting neovascular age-related macular degeneration data: consensus on neovascular age-related macular degeneration nomenclature study group.Ophthalmology. 2020;127:616–6.

    Article  PubMed  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Ophthalmology, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China

    Ying Wei & Zhenggao Xie

Authors
  1. Ying Wei
    View author publications

    Search author on:PubMed Google Scholar

  2. Zhenggao Xie
    View author publications

    Search author on:PubMed Google Scholar

Contributions

Ying Wei: Conceptualisation, Investigation, Methodology, Supervision, Writing–original draft, Writing–review & editing. Zhenggao Xie: Conceptualisation, Investigation, Writing–review & editing.

Corresponding author

Correspondence to Zhenggao Xie.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wei, Y., Xie, Z. Advancing personalised therapy in neovascular AMD through deep learning–based OCT biomarker quantification. Eye 40, 7–8 (2026). https://doi.org/10.1038/s41433-025-04133-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1038/s41433-025-04133-1

Search

Advanced search

Quick links