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 based automated quantification of critical optical coherence tomography features in neovascular age-related macular degeneration

Eye volume 38, pages 537–544 (2024)Cite this article

Subjects

Abstract

Purpose

To validate a deep learning algorithm for automated intraretinal fluid (IRF), subretinal fluid (SRF) and neovascular pigment epithelium detachment (nPED) segmentations in neovascular age-related macular degeneration (nAMD).

Methods

In this IRB-approved study, optical coherence tomography (OCT) data from 50 patients (50 eyes) with exudative nAMD were retrospectively analysed. Two models, A1 and A2, were created based on gradings from two masked readers, R1 and R2. Area under the curve (AUC) values gauged detection performance, and quantification between readers and models was evaluated using Dice and correlation (R2) coefficients.

Results

The deep learning–based algorithms had high accuracies for all fluid types between all models and readers: per B-scan IRF AUCs were 0.953, 0.932, 0.990, 0.942 for comparisons A1-R1, A1-R2, A2-R1 and A2-R2, respectively; SRF AUCs were 0.984, 0.974, 0.987, 0.979; and nPED AUCs were 0.963, 0.969, 0.961 and 0.966. Similarly, the R2 coefficients for IRF were 0.973, 0.974, 0.889 and 0.973; SRF were 0.928, 0.964, 0.965 and 0.998; and nPED were 0.908, 0.952, 0.839 and 0.905. The Dice coefficients for IRF averaged 0.702, 0.667, 0.649 and 0.631; for SRF were 0.699, 0.651, 0.692 and 0.701; and for nPED were 0.636, 0.703, 0.719 and 0.775. In an inter-observer comparison between manual readers R1 and R2, the R2 coefficient was 0.968 for IRF, 0.960 for SRF, and 0.906 for nPED, with Dice coefficients of 0.692, 0.660 and 0.784 for the same features.

Conclusions

Our deep learning-based method applied on nAMD can segment critical OCT features with performance akin to manual grading.

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

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

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

Fig. 1: Receiver operating characteristic (ROC) curves for the different comparisons.
Fig. 2: Representation of the manual and automated grading.
Fig. 3: Graphical representation of R2 and Bland-Altman plots.
Fig. 4: Graphical representation of R2 and Bland-Altman plots.

Similar content being viewed by others

Data availability

Data that support the findings of this study are available upon reasonable request to the corresponding author.

References

  1. Friedman DS, O’Colmain BJ, Muñoz B, Tomany SC, McCarty C, de Jong PTVM, et al. Prevalence of age-related macular degeneration in the United States. Arch Ophthalmol. 2004;122:564–72.

    Article  PubMed  Google Scholar 

  2. 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;127:616–36.

  3. Ferris FL, Wilkinson CP, Bird A, Chakravarthy U, Chew E, Csaky K, et al. Clinical classification of age-related macular degeneration. Ophthalmology 2013;120:844–51.

    Article  PubMed  Google Scholar 

  4. Ferris FL, Fine SL, Hyman L. Age-Related Macular Degeneration and Blindness Due to Neovascular Maculopathy. Arch Ophthalmol. 1984;102:1640–2.

  5. Kaiser PK, Wykoff CC, Singh RP, Khanani AM, Do DV, Patel H, et al. Retinal Fluid And Thickness As Measures of Disease Activity In Neovascular Age-Related Macular Degeneration. Retina. 2021;41:1579–86.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  6. Sharma A, Cheung CMG, Arias-Barquet L, Ozdek S, Parachuri N, Kumar N, et al. Fluid-Based Visual Prognostication In Type 3 Macular Neovascularization-Flip-3 Study. Retina. 2022;42:107–13.

    Article  CAS  PubMed  Google Scholar 

  7. Jaffe GJ, Ying G-S, Toth CA, Daniel E, Grunwald JE, Martin DF, et al. Macular Morphology and Visual Acuity in Year Five of the Comparison of Age-related Macular Degeneration Treatments Trials. Ophthalmology. 2019;126:252–60.

    Article  PubMed  Google Scholar 

  8. Schmidt-Erfurth U, Waldstein SM. A paradigm shift in imaging biomarkers in neovascular age-related macular degeneration. Prog Retin Eye Res. 2016;50:1–24.

    Article  CAS  PubMed  Google Scholar 

  9. Fang M, Chanwimol K, Maram J, Datoo O’Keefe GA, Wykoff CC, Sarraf D, et al. Morphological characteristics of eyes with neovascular age-related macular degeneration and good long-term visual outcomes after anti-VEGF therapy. Br J Ophthalmol. 2021. https://doi.org/10.1136/bjophthalmol-2021-319602.

  10. Lee CS, Baughman DM, Lee AY. Deep learning is effective for the classification of OCT images of normal versus Age-related Macular Degeneration. Ophthalmol Retin. 2017;1:322–7.

    Article  Google Scholar 

  11. Moraes G, Fu DJ, Wilson M, Khalid H, Wagner SK, Korot E, et al. Quantitative Analysis of OCT for Neovascular Age-Related Macular Degeneration Using Deep Learning. Ophthalmology. 2021;128:693–705.

    Article  PubMed  Google Scholar 

  12. Schmidt-Erfurth U, Bogunovic H, Sadeghipour A, Schlegl T, Langs G, Gerendas BS, et al. Machine Learning to Analyze the Prognostic Value of Current Imaging Biomarkers in Neovascular Age-Related Macular Degeneration. Ophthalmol Retin. 2018;2:24–30.

    Article  Google Scholar 

  13. Borrelli E, Bandello F, Souied EH, Barresi C, Miere A, Querques L, et al. Neovascular age-related macular degeneration: advancement in retinal imaging builds a bridge between histopathology and clinical findings. Graefes Arch Clin Exp Ophthalmol. 2022;260:2087–93.

  14. Borrelli E, Sarraf D, Freund KB, Sadda SR OCT angiography and evaluation of the choroid and choroidal vascular disorders. Progress in Retinal and Eye Research. 2018;67:30–55.

  15. Barresi C, Borrelli E, Fantaguzzi F, Grosso D, Sacconi R, Bandello F, et al. Complications Associated with Worse Visual Outcomes in Patients with Exudative Neovascular Age-Related Macular Degeneration. Ophthalmologica. 2021;244:512–22.

    Article  CAS  PubMed  Google Scholar 

  16. Huang Y, Gangaputra S, Lee KE, Narkar AR, Klein R, Klein BEK, et al. Signal quality assessment of retinal optical coherence tomography images. Investig Ophthalmol Vis Sci. 2012;53:2133–41.

    Article  Google Scholar 

  17. Oakley JD, Verdooner S, Russakoff DB, Brucker AJ, Seaman J, Sahni J, et al. Quantitative Assessment of Automated Optical Coherence Tomography Image Analysis Using A Home-Based Device For Self-Monitoring Neovascular Age-Related Macular Degeneration. Retina. 2023;43:433–43.

  18. Borrelli E, Grosso D, Barresi C, Lari G, Sacconi R, Senni C, et al. Long-term Visual Outcomes and Morphologic Biomarkers of Vision Loss in Eyes with Diabetic Macular Edema treated with Anti-VEGF Therapy. Am J Ophthalmol. 2022;235:80–9.

  19. Borrelli E, Viganò C, Battista M, Sacconi R, Senni C, Querques L, et al. Individual vs. combined imaging modalities for diagnosing neovascular central serous chorioretinopathy. Graefes Arch Clin Exp Ophthalmol. 2023;261:1267–73.

  20. Sodhi SK, Pereira A, Oakley JD, Golding J, Trimboli C, Russakoff DB, et al. Utilization of deep learning to quantify fluid volume of neovascular age-related macular degeneration patients based on swept-source OCT imaging: The ONTARIO study. PLoS One. 2022;17:e0262111.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  21. Ronneberger O, Fischer P, Brox T U-Net: Convolutional Networks for Biomedical Image Segmentation BT - Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. In: Navab N, Hornegger J, Wells WM, Frangi AF (eds). Cham: Springer International Publishing; 2015. pp. 234–41.

  22. Oakley JD, Sodhi SK, Russakoff DB, Choudhry N. Automated deep learning-based multi-class fluid segmentation in swept-source optical coherence tomography images. Biorxiv. 2020. https://doi.org/10.1101/2020.09.01.278259.

  23. Kottner J, Audigé L, Brorson S, Donner A, Gajewski BJ, Hróbjartsson A, et al. Guidelines for Reporting Reliability and Agreement Studies (GRRAS) were proposed. J Clin Epidemiol. 2011;64:96–106.

    Article  PubMed  Google Scholar 

  24. Bonett DG. Sample size requirements for estimating intraclass correlations with desired precision. Stat Med. 2002;21:1331–5.

    Article  PubMed  Google Scholar 

  25. Schlegl T, Waldstein SM, Bogunovic H, Endstraßer F, Sadeghipour A, Philip A-M, et al. Fully Automated Detection and Quantification of Macular Fluid in OCT Using Deep Learning. Ophthalmology. 2018;125:549–58.

    Article  PubMed  Google Scholar 

  26. Liefers B, Taylor P, Alsaedi A, Bailey C, Balaskas K, Dhingra N, et al. Quantification of Key Retinal Features in Early and Late Age-Related Macular Degeneration Using Deep Learning. Am J Ophthalmol. 2021;226:1–12.

    Article  PubMed  Google Scholar 

  27. Mantel I, Mosinska A, Bergin C, Polito MS, Guidotti J, Apostolopoulos S, et al. Automated Quantification of Pathological Fluids in Neovascular Age-Related Macular Degeneration, and Its Repeatability Using Deep Learning. Transl Vis Sci Technol. 2021;10:17.

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Author information

Author notes

  1. These authors contributed equally: Enrico Borrelli, Jonathan D. Oakley.

Authors and Affiliations

  1. Vita-Salute San Raffaele University Milan, Milan, Italy

    Enrico Borrelli, Giorgio Iaccarino, Marco Battista, Domenico Grosso, Federico Borghesan, Costanza Barresi, Riccardo Sacconi, Francesco Bandello & Giuseppe Querques

  2. IRCCS San Raffaele Scientific Institute, Milan, Italy

    Enrico Borrelli, Giorgio Iaccarino, Marco Battista, Domenico Grosso, Federico Borghesan, Costanza Barresi, Riccardo Sacconi, Francesco Bandello & Giuseppe Querques

  3. Voxeleron LLC, Austin, TX, USA

    Jonathan D. Oakley & Daniel B. Russakoff

Authors
  1. Enrico Borrelli
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jonathan D. Oakley
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Giorgio Iaccarino
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Daniel B. Russakoff
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Marco Battista
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Domenico Grosso
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Federico Borghesan
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Costanza Barresi
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Riccardo Sacconi
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Francesco Bandello
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Giuseppe Querques
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Concept and design: EB, JDO, GQ. Acquisition, analysis, or interpretation of data: All authors. Methodological development and statistical analysis: JDO, EB, DBR. Drafting of the paper: EB. Critical revision of the paper for important intellectual content: All authors. Final approval of the manuscript: All authors.

Corresponding author

Correspondence to Giuseppe Querques.

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.

Supplementary information

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

Borrelli, E., Oakley, J.D., Iaccarino, G. et al. Deep-learning based automated quantification of critical optical coherence tomography features in neovascular age-related macular degeneration. Eye 38, 537–544 (2024). https://doi.org/10.1038/s41433-023-02720-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41433-023-02720-8

Search

Advanced search

Quick links