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:

Comparison of effectiveness of geographic atrophy automatic segmentation with different imaging methods

Eye volume 39, pages 2003–2007 (2025)Cite this article

Subjects

Abstract

Purpose

To compare geographic atrophy (GA) size measured with fundus autofluorescence (FAF), near-infrared (N-IR) imaging, retromode (RM) imaging and optical coherence tomography angiography (OCTA) imaging and to compare accuracy of artificial intelligence(AI)-based automatic segmentation of GA with each method.

Methods

Available good quality FAF, N-IR- RM and OCTA images acquired on the same date for each patient diagnosed with GA from 2022 to 2024 were retrospectively collected. Seventy(70)% of the images were used to train a Trainable Weka Segmenter (v 3.3.2) based on manual segmentation of GA and spurious areas performed by 2 different blinded expert graders for each of the 4 imaging modalities. For the remaining 30%(testing set), automatic measurement and manual measurement were compared to determine accuracy of the segmentation.

Results

A total of 157 eyes were included. Mean ground truth GA area (graders’ manual contouring), mean automatic area and mean spurious area of testing set were significantly different with the 4 techniques(respectively p < 0.001, p < 0.001 and p = 0.002). Intraclass correlation coefficient(ICC) between manual and automatic measurements was 0.82 (0.78–0.84) for FAF model, 0.81 (0.78–0.82) for N-IR model, 0.67 (0.64–0.71) for RM model and 0.77 (0.73–0.81) for OCTA model.

Conclusion

We report very good performance of automatic segmentation performed on FAF, N-IR and OCTA. A slight overestimation of GA area with automatic measurements would be considered when assessing GA area on FAF and N-IR imaging. RM imaging should not be considered as a valid method for automatic GA area assessment due to superiority of other available enface imaging techniques.

Access through your institution
Buy or subscribe

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

Access options

Access through your institution

Buy this article

  • Purchase on SpringerLink
  • Instant access to full article PDF
Buy now

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

Fig. 1: Manual segmentation of geographic atrophy area on images acquired with the 4 different techniques.
Fig. 2: Segmentation of geographic atrophy using a Trainable Weka Segmenter.
Fig. 3: Bland Altman plot analysis of the agreement between manual and automatic segmentation.

Similar content being viewed by others

References

  1. Querques G, Amblard JC, Andrao A, Badura F, Bandello F, Holz F, et al. Expert Consensus on Geographic Atrophy in the EU: A Call for Urgent Policy Action. Ophthalmol Ther. 2024;13:867–81. https://doi.org/10.1007/s40123-024-00899-x

    Article  PubMed  PubMed Central  Google Scholar 

  2. Guymer RH. Treating Geographic Atrophy–Are We Ready? A Call to Image. Oph Retin. 2023;7:1–3. https://doi.org/10.1016/j.oret.2022.08.022

    Article  Google Scholar 

  3. Ahluwalia A, Shen LL, Bao Y, Sun M, Young BK, Park MM, et al. The influence of the topographic location of geographic atrophy on vision-related quality of life in nonexudative age-related macular degeneration. Graefes Arch Clin Exp Ophthalmol. 2023;261:699–708. https://doi.org/10.1007/s00417-022-05849-6

    Article  PubMed  Google Scholar 

  4. Shen LL, Sun M, Ahluwalia A, Young BK, Park MM, Toth CA, et al. Relationship of Topographic Distribution of Geographic Atrophy to Visual Acuity in Nonexudative Age-Related Macular Degeneration. Ophthalmology Retin. 2021;5:761–74. https://doi.org/10.1016/j.oret.2020.11.003

    Article  Google Scholar 

  5. Künzel SH, Möller PT, Lindner M, Goerdt L, Nadal J, Schmid M, et al. Determinants of Quality of Life in Geographic Atrophy Secondary to Age-Related Macular Degeneration. Investigative Ophthalmol Vis Sci. 2020;61:63. https://doi.org/10.1167/iovs.61.5.63

    Article  Google Scholar 

  6. Fleckenstein M, Mitchell P, Freund KB, Sadda S, Holz FG, Brittain C, et al. The Progression of Geographic Atrophy Secondary to Age-Related Macular Degeneration. Ophthalmology. 2018;125:369–90. https://doi.org/10.1016/j.ophtha.2017.08.038

    Article  PubMed  Google Scholar 

  7. Lindner M, Böker A, Mauschitz MM, Göbel AP, Fimmers R, Brinkmann CK, et al. Directional Kinetics of Geographic Atrophy Progression in Age-Related Macular Degeneration with Foveal Sparing. Ophthalmology. 2015;122:1356–65. https://doi.org/10.1016/j.ophtha.2015.03.027

    Article  PubMed  Google Scholar 

  8. Thiele S, Nadal J, Pfau M, Saßmannshausen M, Fleckenstein M, Holz FG, et al. Prognostic value of intermediate age-related macular degeneration phenotypes for geographic atrophy progression. British J Ophthalmol. 2021;105:239–45. https://doi.org/10.1136/bjophthalmol-2020-316004

    Article  Google Scholar 

  9. Wu Z, Fletcher EL, Kumar H, Greferath U, Guymer RH. Reticular pseudodrusen: A critical phenotype in age-related macular degeneration. Progress Retinal Eye Res. 2022;88:101017. https://doi.org/10.1016/j.preteyeres.2021.101017

    Article  Google Scholar 

  10. Fleckenstein M, Schmitz-Valckenberg S, Adrion C, Visvalingam S, Göbel AP, Mössner A, et al. Progression of age-related geographic atrophy: role of the fellow eye. Invest Ophthalmol Vis Sci. 2011;52:6552–7. https://doi.org/10.1167/iovs.11-7298

    Article  PubMed  Google Scholar 

  11. Domalpally A, Danis RP, White J, Narkar A, Clemons T, Ferris F, et al. Circularity Index as a Risk Factor for Progression of Geographic Atrophy. Ophthalmology. 2013;120:2666–71. https://doi.org/10.1016/j.ophtha.2013.07.047

    Article  PubMed  Google Scholar 

  12. Vogl WD, Riedl S, Mai J, Reiter GS, Lachinov D, Bogunović H, et al. Predicting Topographic Disease Progression and Treatment Response of Pegcetacoplan in Geographic Atrophy Quantified by Deep Learning. Ophthalmology Retin. 2023;7:4–13. https://doi.org/10.1016/j.oret.2022.08.003

    Article  Google Scholar 

  13. Nattagh K, Zhou H, Rinella N, Zhang Q, Dai Y, Foote KG, et al. OCT Angiography to Predict Geographic Atrophy Progression using Choriocapillaris Flow Void as a Biomarker. Translational Vis Sci Technol. 2020;9:6. https://doi.org/10.1167/tvst.9.7.6

    Article  Google Scholar 

  14. You QS, Camino A, Wang J, Guo Y, Flaxel CJ, Hwang TS, et al. Geographic Atrophy Progression Is Associated With Choriocapillaris Flow Deficits Measured With Optical Coherence Tomographic Angiography. Investigative Ophthalmol Vis Sci. 2021;62:28. https://doi.org/10.1167/iovs.62.15.28

    Article  Google Scholar 

  15. Holz FG, Bindewald-Wittich A, Fleckenstein M, Dreyhaupt J, Scholl HPN, Schmitz-Valckenberg S. Progression of Geographic Atrophy and Impact of Fundus Autofluorescence Patterns in Age-related Macular Degeneration. American J Ophthalmol. 2007;143:463–72.e2. https://doi.org/10.1016/j.ajo.2006.11.041

    Article  Google Scholar 

  16. Arslan J, Samarasinghe G, Benke KK, Sowmya A, Wu Z, Guymer RH, et al. Artificial Intelligence Algorithms for Analysis of Geographic Atrophy: A Review and Evaluation. Translational Vis Sci Technol. 2020;9:57. https://doi.org/10.1167/tvst.9.2.57

    Article  Google Scholar 

  17. Streho M, Lavallee G, Aimadaly M, Perrenoud F, Puech M, Tadayoni R, et al. Geographic Atrophy and OCT Angiography: Descriptive Study and Correlation With Autofluorescence. Ophthalmic Surg, Lasers Imaging Retin. 2019;50:e222–e228. https://doi.org/10.3928/23258160-20190905-13

    Article  Google Scholar 

  18. Corradetti G, Byon I, Corvi F, Cozzi M, Staurenghi G, Sadda SR. Retro mode illumination for detecting and quantifying the area of geographic atrophy in non-neovascular age-related macular degeneration. Eye. 2022;36:1560–6. https://doi.org/10.1038/s41433-021-01670-3

    Article  PubMed  Google Scholar 

  19. Corbelli E, Sacconi R, Rabiolo A, Mercuri S, Carnevali A, Querques L, et al. Optical Coherence Tomography Angiography in the Evaluation of Geographic Atrophy Area Extension. Investigative Ophthalmol Vis Sci. 2017;58:5201–8. https://doi.org/10.1167/iovs.17-22508

    Article  Google Scholar 

  20. Borrelli E, Olivieri C, Serafino S, Coletto A, Ricardi F, Neri G, et al. Interreader and Intermodality Variability in Macular Atrophy Quantification in Neovascular Age-related Macular Degeneration: Comparison of 6 Imaging Modalities. Ophthalmology Retina. Published online August 30, 2024. https://doi.org/10.1016/j.oret.2024.08.017

  21. Abdelfattah NS, Sadda J, Wang Z, Hu Z, Sadda S. Near-Infrared Reflectance Imaging for Quantification of Atrophy Associated with Age-Related Macular Degeneration. American J Ophthalmol. 2020;212:169–74. https://doi.org/10.1016/j.ajo.2020.01.005

    Article  Google Scholar 

  22. Arslan J, Samarasinghe G, Sowmya A, Benke KK, Hodgson LAB, Guymer RH, et al. Deep Learning Applied to Automated Segmentation of Geographic Atrophy in Fundus Autofluorescence Images. Translational Vis Sci Technol. 2021;10:2. https://doi.org/10.1167/tvst.10.8.2

    Article  Google Scholar 

  23. Sarao V, Veritti D, Nardin AD, Misciagna M, Foresti G, Lanzetta P. Explainable artificial intelligence model for the detection of geographic atrophy using colour retinal photographs. BMJ Open Ophthalmol. 2023;8:e001411. https://doi.org/10.1136/bmjophth-2023-001411

    Article  PubMed  PubMed Central  Google Scholar 

  24. Crincoli E, De Rosa I, Miere A, Colantuono D, Mehanna CJ, Souied EH. Comparison of Multimodal Imaging for the Characterization of Geographic Atrophy. Transl Vis Sci Technol. 2022;11:21. https://doi.org/10.1167/tvst.11.11.21

    Article  PubMed  PubMed Central  Google Scholar 

  25. Schmidt-Erfurth U, Mai J, Reiter GS, Riedl S, Vogl WD, Sadeghipour A, et al. Disease Activity and Therapeutic Response to Pegcetacoplan for Geographic Atrophy Identified by Deep Learning-Based Analysis of OCT. Ophthalmology. 2025;132:181–93. https://doi.org/10.1016/j.ophtha.2024.08.017

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

Italian Ministry of Health -RC2025.

Author information

Author notes

  1. These authors contributed equally: Maria Cristina Savastano, Emanuele Crincoli.

Authors and Affiliations

  1. Ophthalmology Unit, “Fondazione Policlinico Universitario A. Gemelli IRCCS”, Rome, Italy

    Maria Cristina Savastano, Emanuele Crincoli, Alfonso Savastano, Matteo Mario Carlà & Stanislao Rizzo

  2. Catholic University of “Sacro Cuore”, Rome, Italy

    Maria Cristina Savastano, Emanuele Crincoli, Alfonso Savastano, Alessandro Gravina, Matteo Mario Carlà & Stanislao Rizzo

  3. Ophthalmology, Department of Surgical, Medical and Molecular Pathology and Critical Care Medicine, University of Pisa, Pisa, Italy

    Clara Rizzo

  4. Ophthalmic Unit, Department of Neurosciences, Biomedicine and Movement Sciences, University of Verona, Verona, Italy

    Raphael Kilian

  5. “Consiglio Nazionale delle Ricerche, Istituto di Neuroscienze”, Pisa, Italy

    Stanislao Rizzo

Authors
  1. Maria Cristina Savastano
    View author publications

    Search author on:PubMed Google Scholar

  2. Emanuele Crincoli
    View author publications

    Search author on:PubMed Google Scholar

  3. Alfonso Savastano
    View author publications

    Search author on:PubMed Google Scholar

  4. Alessandro Gravina
    View author publications

    Search author on:PubMed Google Scholar

  5. Matteo Mario Carlà
    View author publications

    Search author on:PubMed Google Scholar

  6. Clara Rizzo
    View author publications

    Search author on:PubMed Google Scholar

  7. Raphael Kilian
    View author publications

    Search author on:PubMed Google Scholar

  8. Stanislao Rizzo
    View author publications

    Search author on:PubMed Google Scholar

Contributions

Design of the study: MCS, EC; Analysis: MCS, EC, AG; Interpretation: AS, CR, MMC, RK; Draft: EC; Revision: MCS, AS, SR.

Corresponding author

Correspondence to Emanuele Crincoli.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethical approval

The study adhered to the declaration of Helsinki and the protocol was approved by the Ethics Committee of Università Cattolica del Sacro Cuore di Roma (n959).

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

Savastano, M.C., Crincoli, E., Savastano, A. et al. Comparison of effectiveness of geographic atrophy automatic segmentation with different imaging methods. Eye 39, 2003–2007 (2025). https://doi.org/10.1038/s41433-025-03794-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue date:

  • DOI: https://doi.org/10.1038/s41433-025-03794-2

Search

Advanced search

Quick links