Skip to main content

Thank you for visiting 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.

Detecting multiple retinal diseases in ultra-widefield fundus imaging and data-driven identification of informative regions with deep learning


Ultra-widefield (UWF) imaging is a promising modality that captures a larger retinal field of view compared with traditional fundus photography. Previous studies have shown that deep learning models are effective for detecting retinal disease in UWF images, but primarily considered individual diseases under less-than-realistic conditions (excluding images with other diseases, artefacts, comorbidities or borderline cases; and balancing healthy and diseased images) and did not systematically investigate which regions of the UWF images are relevant for disease detection. Here we first improve on the state of the field by proposing a deep learning model that can recognize multiple retinal diseases under more realistic conditions than what has previously been considered. We then use global explainability methods to identify which regions of the UWF images the model generally attends to. Our model performs very well, separating between healthy and diseased retinas with an area under the receiver operating characteristic curve (AUC) of 0.9196 (±0.0001) on an internal test set, and an AUC of 0.9848 (±0.0004) on a challenging, external test set. When diagnosing specific diseases, the model attends to regions where we would expect those diseases to occur. We further identify the posterior pole as the most important region in a purely data-driven fashion. Surprisingly, 10% of the image around the posterior pole is sufficient for achieving comparable performance across all labels to having the full images available.

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

Access options

Buy article

Get time limited or full article access on ReadCube.


All prices are NET prices.

Fig. 1: Evaluation of our model on the test set and the external validation set.
Fig. 2: Examples of the model-attention heat maps generated by GradCAM using the general ‘diseased’ label as target concept.
Fig. 3: Global attention maps of our model.
Fig. 4: Validating the global attention maps through progressive erasure and progressive restoration.

Data availability

The data are available from Hitoshi Tabuchi and the other authors of the Tsukazaki Optos Public Project subject to current export restrictions, which are imposed by Japanese legislation at the time of writing. Previously, it was publicly accessible via a project website where we obtained the copy used in this study. A subset containing images images of healthy eyes and eyes with RP used in a previous study15 is publicly accessible directly online at The external validation set we assembled from the American Society of Retina Specialists Retina Image Bank (, RetinaRocks Image Library ( and Optos Recognising Pathology resource ( is described in Supplementary Section 3 in sufficient detail to reproduce the dataset. We also note that the dataset is well known within the community (for example, refs. 16,26).

Code availability

The code for this project, a requirements.txt file listing all libraries used and their versions, and the trained model are available online at


  1. Brown, G. C. Vision and quality-of-life. Trans. Am. Ophthalmol.Soc. 97, 473–511 (1999).

    Google Scholar 

  2. Pezzullo, L., Streatfeild, J., Simkiss, P. & Shickle, D. The economic impact of sight loss and blindness in the UK adult population. BMC Health Serv. Res. 18, 63 (2018).

    Article  Google Scholar 

  3. Patel, S. N., Shi, A., Wibbelsman, T. D. & Klufas, M. A. Ultra-widefield retinal imaging: an update on recent advances. Ther. Adv. Ophthalmol. 12, (2020).

  4. Nagiel, A., Lalane, R. A., Sadda, S. R. & Schwartz, S. D. Ultra-widefield fundus imaging: a review of clinical applications and future trends. Retina 36, 660–678 (2016).

    Article  Google Scholar 

  5. Tan, T.-E., Ting, D. S. W., Wong, T. Y. & Sim, D. A. Deep learning for identification of peripheral retinal degeneration using ultra-wide-field fundus images: is it sufficient for clinical translation? Ann. Transl. Med. 8, 611 (2020).

  6. Matsuba, S. et al. Accuracy of ultra-wide-field fundus ophthalmoscopy-assisted deep learning, a machine-learning technology, for detecting age-related macular degeneration. Int. Ophthalmol. 39, 1269–1275 (2019).

    Article  Google Scholar 

  7. Nagasato, D. et al. Deep-learning classifier with ultrawide-field fundus ophthalmoscopy for detecting branch retinal vein occlusion. Int. J. Ophthalmol. 12, 94–99 (2019).

    Google Scholar 

  8. Nagasato, D. et al. Deep neural network-based method for detecting central retinal vein occlusion using ultrawide-field fundus ophthalmoscopy. J. Ophthalmol. 2018, 1875431 (2018).

    Article  Google Scholar 

  9. Tabuchi, H., Masumoto, H., Nakakura, S., Noguchi, A. & Tanabe, H. Discrimination ability of glaucoma via DCNNs models from ultra-wide angle fundus images comparing either full or confined to the optic disc. In Asian Conference on Computer Vision 229–234 (Springer, 2018).

  10. Masumoto, H. et al. Deep-learning classifier with an ultrawide-field scanning laser ophthalmoscope detects glaucoma visual field severity. J. Glaucoma 27, 647–652 (2018).

    Article  Google Scholar 

  11. Nagasawa, T. et al. Accuracy of deep learning, a machine learning technology, using ultra-wide-field fundus ophthalmoscopy for detecting idiopathic macular holes. PeerJ 6, e5696 (2018).

    Article  Google Scholar 

  12. Nagasawa, T. et al. Accuracy of ultrawide-field fundus ophthalmoscopy-assisted deep learning for detecting treatment-naive proliferative diabetic retinopathy. Int. Ophthalmol. 39, 2153–2159 (2019).

    Article  Google Scholar 

  13. Ohsugi, H., Tabuchi, H., Enno, H. & Ishitobi, N. Accuracy of deep learning, a machine-learning technology, using ultra–wide-field fundus ophthalmoscopy for detecting rhegmatogenous retinal detachment. Sci. Rep. 7, 9425 (2017).

  14. Masumoto, H. et al. Retinal detachment screening with ensembles of neural network models. In Asian Conference on Computer Vision 251–260 (Springer, 2018).

  15. Masumoto, H. et al. Accuracy of a deep convolutional neural network in detection of retinitis pigmentosa on ultrawide-field images. PeerJ 7, e6900 (2019).

    Article  Google Scholar 

  16. Antaki, F. et al. Accuracy of automated machine learning in classifying retinal pathologies from ultra-widefield pseudocolour fundus images. Br. J. Ophthalmol. (2021).

  17. Hemelings, R. et al. Deep learning on fundus images detects glaucoma beyond the optic disc. Sci. Rep. 11, 20313 (2021).

  18. Duker, J. S. et al. The international vitreomacular traction study group classification of vitreomacular adhesion, traction, and macular hole. Ophthalmology 120, 2611–2619 (2013).

    Article  Google Scholar 

  19. Beede, E. et al. A human-centered evaluation of a deep learning system deployed in clinics for the detection of diabetic retinopathy. In Proc. 2020 CHI Conference on Human Factors in Computing Systems 1–12 (Association for Computing Machinery, 2020).

  20. Selvaraju, R. R. et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. In Proc. IEEE International Conference on Computer Vision 618–626 (IEEE, 2017).

  21. Engelmann, J., Storkey, A. & Bernabeu, M. O. Global explainability in aligned image modalities. Preprint at (2021).

  22. Wilkinson, C. P., Hinton, D. R., Sadda, S. R. & Wiedemann, P. Ryan’s Retina 6th edn (Elsevier Health Sciences, 2018).

  23. DeGrave, A. J., Janizek, J. D. & Lee, S.-I. AI for radiographic COVID-19 detection selects shortcuts over signal. Nat. Mach. Intell. 3, 610–619 (2021).

  24. Poplin, R. et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat. Biomed. Eng. 2, 158–164 (2018).

    Article  Google Scholar 

  25. Yamashita, T. et al. Factors in color fundus photographs that can be used by humans to determine sex of individuals. Transl. Vis. Sci. Technol. 9, 4 (2020).

  26. Khan, S. M. et al. A global review of publicly available datasets for ophthalmological imaging: barriers to access, usability, and generalisability. Lancet Digit. Health 3, e51–e66 (2021).

    Article  Google Scholar 

  27. González-Gonzalo, C., Liefers, B., van Ginneken, B. & Sánchez, C. I. Iterative augmentation of visual evidence for weakly-supervised lesion localization in deep interpretability frameworks: application to color fundus images. IEEE Tran. Med. Imaging 39, 3499–3511 (2020).

    Article  Google Scholar 

  28. Quellec, G., Charrière, K., Boudi, Y., Cochener, B. & Lamard, M. Deep image mining for diabetic retinopathy screening. Med. Image Anal. 39, 178–193 (2017).

    Article  Google Scholar 

  29. Zhang, H., Cisse, M., Dauphin, Y. N. & Lopez-Paz, D. mixup: beyond empirical risk minimization. Preprint at (2017).

  30. He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 770–778 (IEEE, 2016).

  31. Ioffe, S. & Szegedy, C. Batch normalization: accelerating deep network training by reducing internal covariate shift. In International Conference on Machine Learning 448–456 (PMLR, 2015).

  32. Wightman, R., Touvron, H. & Jégou, H. ResNet strikes back: an improved training procedure in timm. Preprint at (2021).

  33. Bello, I. et al. Revisiting ResNets: improved training and scaling strategies. Preprint at (2021).

  34. He, K., Zhang, X., Ren, S. & Sun, J. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In Proc. IEEE International Conference on Computer Vision 1026–1034 (IEEE, 2015).

  35. Deng, J. et al. ImageNet: a large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition 248–255 (IEEE, 2009).

  36. Loshchilov, I. & Hutter, F. SGDR: stochastic gradient descent with warm restarts. Preprint at (2016).

  37. Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D. & Wilson, A. G. Averaging weights leads to wider optima and better generalization. Preprint at (2018).

  38. Zhong, Z., Zheng, L., Kang, G., Li, S. & Yang, Y. Random erasing data augmentation. In Proc. AAAI Conference on Artificial Intelligence Vol. 34, 13001–13008 (Association for the Advancement of Artificial Intelligence, 2020).

  39. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. & Salakhutdinov, R. Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014).

    MathSciNet  MATH  Google Scholar 

  40. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J. & Wojna, Z. Rethinking the inception architecture for computer vision. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 2818–2826 (IEEE, 2016).

  41. Müller, R., Kornblith, S. & Hinton, G. When does label smoothing help? Preprint at (2019).

  42. Krause, J. et al. Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy. Ophthalmology 125, 1264–1272 (2018).

    Article  Google Scholar 

  43. Breiman, L. Random forests. Mach. Learn. 45, 5–32 (2001).

    Article  MATH  Google Scholar 

  44. Friedman, J. et al. The Elements of Statistical Learning Vol. 1 (Springer Series in Statistics, Springer, 2001).

  45. Paszke, A. et al. PyTorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32, 8024–8035 (2019).

  46. Wightman, R. PyTorch image models. GitHub (2019).

  47. Harris, C. R. et al. Array programming with NumPy. Nature 585, 357–362 (2020).

    Article  Google Scholar 

  48. Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).

    MathSciNet  MATH  Google Scholar 

  49. Hunter, J. D. Matplotlib: a 2D graphics environment. Comput. Sc. Eng. 9, 90–95 (2007).

    Article  Google Scholar 

  50. Waskom, M. L. seaborn: statistical data visualization. J. Open Source Soft. 6, 3021 (2021).

    Article  Google Scholar 

Download references


We thank H. Masumoto and H. Tabuchi as well as D. Nagasato, S. Nakakura, M. Kameoka, R. Aoki, T. Sogawa, S. Matsuba, H. Tanabe, T. Nagasawa, Y. Yoshizumi, T. Sonobe, T. Yamauchi and all their colleagues at Tsukazaki Hospital for releasing the TOP dataset. This is a great contribution to AI research in ophthalmology for which we are most grateful. We also thank the American Society of Retina Specialists for their Retina Image Bank, and RetinaRocks for their Image Library. We further thank all users that submitted images for research use to these online repositories or elsewhere. This work was supported by the United Kingdom Research and Innovation (grant EP/S02431X/1), UKRI Centre for Doctoral Training in Biomedical AI at the University of Edinburgh, School of Informatics. For the purpose of open access, the author has applied a creative commons attribution (CC BY) licence to any author accepted manuscript version arising. This work was supported by The Royal College of Surgeons of Edinburgh, Sight Scotland, The RS Macdonald Charitable Trust, Chief Scientist Office, and Edinburgh & Lothians Health Foundation through a proof-of-concept award for the SCONe project. Grant EP/S02431X/1: J.E. SCONe project grants: A.D.M. and E.P.

Author information

Authors and Affiliations



J.E. was responsible for all aspects of this work, including conceptualization, study design/methods, experiments, analysis, interpretation, figures and writing. A.S. and M.O.B. jointly supervised and contributed to all aspects of this work. A.D.M., I.J.C.M. and E.P. provided domain expertise regarding ophthalmology and ultra-widefield imaging, assessed the top 20 false positives, and provided feedback on the interpretation of the results.

Corresponding authors

Correspondence to Justin Engelmann or Miguel O. Bernabeu.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Machine Intelligence thanks Edward Korot and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

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

Extended data

Extended Data Fig. 1 Six of nine images showing the same eye of the same patient.

Six of nine images showing the same eye of the same patient. All images show DR according to the labels. While there are some differences between the images in terms of artefacts and pathology, the general pattern of the pathology is consistent between images and could be memorized by a model.

Supplementary information

Supplementary Information

Supplementary Information, containing all supplementary sections (text, figures and tables).

Reporting Summary

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

Verify currency and authenticity via CrossMark

Cite this article

Engelmann, J., McTrusty, A.D., MacCormick, I.J.C. et al. Detecting multiple retinal diseases in ultra-widefield fundus imaging and data-driven identification of informative regions with deep learning. Nat Mach Intell 4, 1143–1154 (2022).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:


Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing