Skip to main content

Advertisement

SpringerLink
Log in

Deep learning for ultra-widefield imaging: a scoping review

  • Review Article
  • Published:
Graefe's Archive for Clinical and Experimental Ophthalmology Aims and scope Submit manuscript

Abstract

Purpose

This article is a scoping review of published and peer-reviewed articles using deep-learning (DL) applied to ultra-widefield (UWF) imaging. This study provides an overview of the published uses of DL and UWF imaging for the detection of ophthalmic and systemic diseases, generative image synthesis, quality assessment of images, and segmentation and localization of ophthalmic image features.

Methods

A literature search was performed up to August 31st, 2021 using PubMed, Embase, Cochrane Library, and Google Scholar. The inclusion criteria were as follows: (1) deep learning, (2) ultra-widefield imaging. The exclusion criteria were as follows: (1) articles published in any language other than English, (2) articles not peer-reviewed (usually preprints), (3) no full-text availability, (4) articles using machine learning algorithms other than deep learning. No study design was excluded from consideration.

Results

A total of 36 studies were included. Twenty-three studies discussed ophthalmic disease detection and classification, 5 discussed segmentation and localization of ultra-widefield images (UWFIs), 3 discussed generative image synthesis, 3 discussed ophthalmic image quality assessment, and 2 discussed detecting systemic diseases via UWF imaging.

Conclusion

The application of DL to UWF imaging has demonstrated significant effectiveness in the diagnosis and detection of ophthalmic diseases including diabetic retinopathy, retinal detachment, and glaucoma. DL has also been applied in the generation of synthetic ophthalmic images. This scoping review highlights and discusses the current uses of DL with UWF imaging, and the future of DL applications in this field.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Abbreviations

7SF:

7 Standard Field

AMD:

Age-related macular degeneration

AD:

Alzheimer’s Disease

AUROC:

Area under ROC

AUPRC:

Area under precision-recall

ANN:

Artificial neural network

AutoML:

Automated machine learning

BCVA:

Best corrected visual acuity

baPWV :

Brachial-Ankle Pulse-Wave Velocity

BRVO :

Branch RVO

CRVO:

Central RVO

CNNs:

Convolutional neural networks

DL:

Deep learning

DNN:

Deep neural network

DME:

Diabetic macular edema

DR:

Diabetic retinopathy

FA:

Fluorescein angiography

FI:

Fundus image

GC-IPL:

Ganglion cell-inner plexiform layer

GANs:

Generative adversarial networks

GON :

Glaucomatous optic neuropathy

Grad-CAM:

Gradient-weighted class activation mapping

HITL :

Human-in-the-loop

IMH:

Idiopathic macular hole

ML:

Machine learning

MAE :

Mean absolute error

MAPE:

Mean-absolute-percent error

NPDR:

Non-proliferative DR

NPRLs:

Notable peripheral retinal lesions

OCTA:

OCT angiography

OCT:

Optical coherence tomography

PDR:

Proliferative diabetic retinopathy

PSR:

Proliferative sickle cell retinopathy

ROC:

Receiver operating characteristic

RDR:

Referrable DR

ROI:

Region of interest

RD:

Retinal detachment

RED:

Retinal exudates And/Or Drusen

RH:

Retinal hemorrhage

RVO:

Retinal vein occlusion

RVA:

Retinal vessel areas

RP:

Retinitis pigmentosa

RMSE :

Root-mean-square error

SLO:

Scanning laser ophthalmoscope

SCR:

Sickle cell retinopathy

SSIM:

Structural similarity

UWF:

Ultra-widefield

UWF-FA:

Ultra-widefield fluorescein angiography

UWFI:

Ultra-widefield image

UWF-FAF:

UWF fundus autofluorescence

UWF-ICGA:

UWF indocyanine green angiography

VTDR:

Vision-threatening DR

VA:

Visual acuity

WF:

Widefield

WFIs:

Widefield images

References

  1. Agarwal A (2007) Fundus Fluorescein and Indocyanine Green Angiography: A Textbook and Atlas, 1st edn. Slack Incorporated, Thorofare, NJ

    Google Scholar 

  2. (1981) Diabetic retinopathy study. Report Number 6. Design, methods, and baseline results. Report Number 7. A modification of the Airlie House classification of diabetic retinopathy. Prepared by the Diabetic Retinopathy. Invest Ophthalmol Vis Sci 21:1–226

  3. Kumar V, Surve A, Kumawat D et al (2021) Ultra-wide field retinal imaging: a wider clinical perspective. Indian J Ophthalmol 69:824–835. https://doi.org/10.4103/ijo.IJO_1403_20

    Article  PubMed  PubMed Central  Google Scholar 

  4. Choudhry N, Duker JS, Freund KB et al (2019) Classification and guidelines for widefield imaging. Ophthalmology Retina 3:843–849. https://doi.org/10.1016/j.oret.2019.05.007

    Article  PubMed  Google Scholar 

  5. Kaines A, Oliver S, Reddy S, Schwartz SD (2009) Ultrawide angle angiography for the detection and management of diabetic retinopathy. Int Ophthalmol Clin 49:53–59. https://doi.org/10.1097/IIO.0b013e31819fd471

    Article  PubMed  Google Scholar 

  6. Nagiel A, Lalane RA, Sadda SR, Schwartz SD (2016) Ultra-widefield fundus imaging: a review of clinical applications and future trends. Retina 36:660–678. https://doi.org/10.1097/IAE.0000000000000937

    Article  PubMed  Google Scholar 

  7. Witmer MT, Kiss S (2012) The clinical utility of ultra-wide-field imaging. In: Review of ophthalmology. https://www.reviewofophthalmology.com/article/the-clinical-utility-of-ultra-wide-field-imaging. Accessed 1 Oct 2021

  8. Optos Inc. (2021) Optos.com - Optos products. In: Optos Products. https://www.optos.com/products/. Accessed 21 Aug 2021

  9. Zeiss Inc. CLARUS 500. In: Clarus 500 Product Information. https://www.zeiss.com/meditec/int/product-portfolio/retinal-cameras/clarus-500.html. Accessed 23 Apr 2022

  10. Wessel MM, Aaker GD, Parlitsis G et al (2012) Ultra–wide-field angiography improves the detection and classification of diabetic retinopathy. Retina 32:785–791. https://doi.org/10.1097/IAE.0b013e3182278b64

    Article  PubMed  Google Scholar 

  11. Antaki F, Coussa RG, Mikhail M et al (2020) The prognostic value of peripheral retinal nonperfusion in diabetic retinopathy using ultra-widefield fluorescein angiography. Graefe’s Arch Clin Exp ogy 258:2681–2690

    Article  Google Scholar 

  12. Liu TA, Arevalo JF (2019) Wide-field imaging in proliferative diabetic retinopathy. Int J Retin Vitreous 5:1–4

    Article  Google Scholar 

  13. Fogliato G, Borrelli E, Iuliano L et al (2019) Comparison between ultra-widefield pseudocolor imaging and indirect ophthalmoscopy in the detection of peripheral retinal lesions. Ophthalmic Surg Lasers Imaging Retina 50:544–549. https://doi.org/10.3928/23258160-20190905-02

    Article  PubMed  Google Scholar 

  14. Quinn NB, Azuara-Blanco A, Graham K et al (2018) Can ultra-wide field retinal imaging replace colour digital stereoscopy for glaucoma detection? Ophthalmic Epidemiol 25:63–69. https://doi.org/10.1080/09286586.2017.1351998

    Article  PubMed  Google Scholar 

  15. Forshaw TRJ, Minör ÅS, Subhi Y, Sørensen TL (2019) Peripheral retinal lesions in eyes with age-related macular degeneration using ultra-widefield imaging: a systematic review with meta-analyses. Ophthalmol Retin 3:734–743. https://doi.org/10.1016/j.oret.2019.04.014

    Article  Google Scholar 

  16. Sadda S (2019) Wide-field imaging in retina and vitreous diseases. In: International Journal of Retina and Vitreous

  17. El Naqa I, Murphy MJ (2015) What Is Machine Learning? In: El Naqa I, Li R, Murphy MJ (eds) Machine learning in radiation oncology: theory and applications. Springer International Publishing, Cham, pp 3–11

    Chapter  Google Scholar 

  18. Sathya R, Abraham A (2013) Comparison of supervised and unsupervised learning algorithms for pattern classification. International Journal of Advanced Research in Artificial Intelligence 2:34–38

    Article  Google Scholar 

  19. Deng L (2014) Deep Learning: Methods and Applications. FNT in Signal Process 7:197–387. https://doi.org/10.1561/2000000039

    Article  Google Scholar 

  20. Russell S, Norvig P (2020) Artificial intelligence: a modern approach, 4th edn. Pearson, Hoboken

    Google Scholar 

  21. Zhou X, Belkin M (2014) Chapter 22 - Semi-Supervised Learning. In: Diniz PSR, Suykens JAK, Chellappa R, Theodoridis S (eds) Academic Press Library in Signal Processing. Elsevier, pp 1239–1269

    Google Scholar 

  22. Hinton G (1999) Unsupervised learning: foundations of neural computation, 1st edn. Bradford Books, Cambridge, Mass

    Book  Google Scholar 

  23. Monarch R (2021) Human-in-the-loop machine learning: active learning and annotation for human-centered AI. Manning

  24. Dongare AD, Kharde RR, Kachare AD (2012) Introduction to artificial neural network. Int J Eng Innov Technol (IJEIT) 2:189–194

    Google Scholar 

  25. Zhou V (2019) Machine learning for beginners: an introduction to neural networks. In: Medium. https://towardsdatascience.com/machine-learning-for-beginners-an-introduction-to-neural-networks-d49f22d238f9. Accessed 21 Aug 2021

  26. Fornito A, Zalesky A, Bullmore ET (2016) Chapter 2 - Nodes and Edges. Fundamentals of brain network analysis. Academic Press, San Diego, pp 37–88

    Google Scholar 

  27. Ciresan DC, Meier U, Masci J et al (2011) Flexible, high performance convolutional neural networks for image classification. Proc Twenty-Second Int Joint Conf Artif Intell 2:1237–1242

    Google Scholar 

  28. Saha S (2018) A comprehensive guide to convolutional neural networks — the ELI5 way. In: Medium. https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53. Accessed 21 Aug 2021

  29. LeCun Y, Boser B, Denker JS et al (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1:541–551. https://doi.org/10.1162/neco.1989.1.4.541

    Article  Google Scholar 

  30. Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet Classification with Deep Convolutional Neural Networks. In: Pereira F, Burges CJ, Bottou L, Weinberger KQ (eds) Advances in Neural Information Processing Systems. Curran Associates Inc

    Google Scholar 

  31. Alippi C, Disabato S, Roveri M (2018) Moving convolutional neural networks to embedded systems: the alexnet and VGG-16 Case. In: 2018 17th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN), pp 212–223

  32. MathWorks Pretrained Inception-ResNet-v2 convolutional neural network - MATLAB inceptionresnetv2. In: MATLAB Mathworks. https://www.mathworks.com/help/deeplearning/ref/inceptionresnetv2.html;jsessionid=ae4b2abd60579ecab16f783b4f26. Accessed 21 Aug 2021

  33. Waring J, Lindvall C, Umeton R (2020) Automated machine learning: review of the state-of-the-art and opportunities for healthcare. Artif Intell Med 104:101822. https://doi.org/10.1016/j.artmed.2020.101822

    Article  PubMed  Google Scholar 

  34. Faes L, Wagner SK, Fu DJ et al (2019) Automated deep learning design for medical image classification by health-care professionals with no coding experience: a feasibility study. The Lancet Digital Health 1:e232–e242. https://doi.org/10.1016/S2589-7500(19)30108-6

    Article  PubMed  Google Scholar 

  35. Korot E, Guan Z, Ferraz D et al (2021) Code-free deep learning for multi-modality medical image classification. Nat Mach Intell 3:288–298. https://doi.org/10.1038/s42256-021-00305-2

    Article  Google Scholar 

  36. Alphabet Inc. Cloud automl custom machine learning models. In: Googlel cloud. https://cloud.google.com/automl. Accessed 5 May 2022

  37. Touma S, Antaki F, Duval R (2022) Development of a code-free machine learning model for the classification of cataract surgery phases. Sci Rep 12:2398. https://doi.org/10.1038/s41598-022-06127-5

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  38. Antaki F, Coussa RG, Hammamji K, Duval R (2021) Revisiting the problem of optic nerve detection in a retinal image using automated machine learning. Asia Pac J Ophthalmol (Phila) 10:335–336. https://doi.org/10.1097/APO.0000000000000398

    Article  Google Scholar 

  39. Antaki F, Coussa RG, Kahwati G et al (2021) Accuracy of automated machine learning in classifying retinal pathologies from ultra-widefield pseudocolour fundus images. Br J Ophthalmol. https://doi.org/10.1136/bjophthalmol-2021-319030

  40. Antaki F, Kahwati G, Sebag J et al (2020) Predictive modeling of proliferative vitreoretinopathy using automated machine learning by ophthalmologists without coding experience. Sci Rep 10:19528. https://doi.org/10.1038/s41598-020-76665-3

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  41. Shah T (2020) About train, validation and test sets in machine learning. In: Medium. https://towardsdatascience.com/train-validation-and-test-sets-72cb40cba9e7. Accessed 21 Aug 2021

  42. Talebi H, Milanfar P (2021) Learning to resize images for computer vision tasks. CoRR abs/2103.09950

  43. Calderon-Auza G, Perez A, Nakano-Miyatake M et al (2019) CNN-based quality assessment for retinal image captured by wide field of view non-mydriatic fundus camera. 2019 42nd International Conference on Telecommunications and Signal Processing (TSP) 282–285

  44. Perez L, Wang J (2017) The effectiveness of data augmentation in image classification using deep learning

  45. Nagasawa T, Tabuchi H, Masumoto H et al (2018) Accuracy of deep learning, a machine learning technology, using ultra-wide-field fundus ophthalmoscopy for detecting idiopathic macular holes. PeerJ 6:e5696. https://doi.org/10.7717/peerj.5696

    Article  PubMed  PubMed Central  Google Scholar 

  46. Li Z, Guo C, Nie D et al (2020) Deep learning for detecting retinal detachment and discerning macular status using ultra-widefield fundus images. Commun Biol 3:15. https://doi.org/10.1038/s42003-019-0730-x

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  47. Parikh R, Mathai A, Parikh S et al (2008) Understanding and using sensitivity, specificity and predictive values. Indian J Ophthalmol 56:45–50

    Article  PubMed  PubMed Central  Google Scholar 

  48. Mandrekar JN (2010) Receiver operating characteristic curve in diagnostic test assessment. J Thorac Oncol 5:1315–1316. https://doi.org/10.1097/JTO.0b013e3181ec173d

    Article  PubMed  Google Scholar 

  49. Boyd K, Eng KH, Page CD (2013) Area under the precision-recall curve: point estimates and confidence intervals. In: Blockeel H, Kersting K, Nijssen S, Železný F (eds) Machine Learning and Knowledge Discovery in Databases. Springer, Berlin, Heidelberg, pp 451–466

    Google Scholar 

  50. Zou KH, Warfield SK, Bharatha A et al (2004) Statistical validation of image segmentation quality based on a spatial overlap index. Acad Radiol 11:178–189. https://doi.org/10.1016/S1076-6332(03)00671-8

    Article  PubMed  PubMed Central  Google Scholar 

  51. Wang Z, Keane PA, Chiang M et al (2021) Artificial intelligence and deep learning in ophthalmology. In: Lidströmer N, Ashrafian H (eds) Artificial Intelligence in Medicine. Springer International Publishing, Cham, pp 1–34

    Google Scholar 

  52. Bawany MH, Ding L, Ramchandran RS et al (2020) Automated vessel density detection in fluorescein angiography images correlates with vision in proliferative diabetic retinopathy. PLoS ONE 15:e0238958. https://doi.org/10.1371/journal.pone.0238958

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  53. Oh K, Kang HM, Leem D et al (2021) Early detection of diabetic retinopathy based on deep learning and ultra-wide-field fundus images. Sci Rep 11:1897. https://doi.org/10.1038/s41598-021-81539-3

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  54. Tang F, Luenam P, Ran AR, et al (2021) Detection of diabetic retinopathy from ultra-wide field scanning laser ophthalmoscope images: a multi-center deep-learning analysis. Ophthalmology Retina S246865302100035X.https://doi.org/10.1016/j.oret.2021.01.013

  55. Wang K, Jayadev C, Nittala MG et al (2018) Automated detection of diabetic retinopathy lesions on ultrawidefield pseudocolour images. Acta Ophthalmol 96:e168–e173. https://doi.org/10.1111/aos.13528

    Article  PubMed  Google Scholar 

  56. Nagasawa T, Tabuchi H, Masumoto H et al (2019) Accuracy of ultrawide-field fundus ophthalmoscopy-assisted deep learning for detecting treatment-naïve proliferative diabetic retinopathy. Int Ophthalmol 39:2153–2159. https://doi.org/10.1007/s10792-019-01074-z

    Article  PubMed  Google Scholar 

  57. Nagasawa T, Tabuchi H, Masumoto H et al (2021) Accuracy of diabetic retinopathy staging with a deep convolutional neural network using ultra-wide-field fundus ophthalmoscopy and optical coherence tomography angiography. J Ophthalmol 2021:6651175. https://doi.org/10.1155/2021/6651175

  58. Ding L, Bawany MH, Kuriyan AE et al (2020) A novel deep learning pipeline for retinal vessel detection in fluorescein angiography. IEEE Trans Image Process 29:6561–6573. https://doi.org/10.1109/TIP.2020.2991530

    Article  Google Scholar 

  59. Orlando JI, Fu H, Barbosa Breda J et al (2020) REFUGE Challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs. Med Image Anal 59:101570. https://doi.org/10.1016/j.media.2019.101570

  60. Ohsugi H, Tabuchi H, Enno H, Ishitobi N (2017) Accuracy of deep learning, a machine-learning technology, using ultra-wide-field fundus ophthalmoscopy for detecting rhegmatogenous retinal detachment. Sci Rep 7:9425. https://doi.org/10.1038/s41598-017-09891-x

  61. Li Z, Guo C, Nie D et al (2019) A deep learning system for identifying lattice degeneration and retinal breaks using ultra-widefield fundus images. Annals of Translational Medicine 7:618–618. https://doi.org/10.21037/atm.2019.11.28

    Article  PubMed  PubMed Central  Google Scholar 

  62. Zhang C, He F, Li B et al (2021) Development of a deep-learning system for detection of lattice degeneration, retinal breaks, and retinal detachment in tessellated eyes using ultra-wide-field fundus images: a pilot study. Graefes Arch Clin Exp Ophthalmol. https://doi.org/10.1007/s00417-021-05105-3

    Article  PubMed  PubMed Central  Google Scholar 

  63. Li Z, Guo C, Lin D et al (2021) Deep learning for automated glaucomatous optic neuropathy detection from ultra-widefield fundus images. Br J Ophthalmol 105:1548–1554. https://doi.org/10.1136/bjophthalmol-2020-317327

    Article  PubMed  Google Scholar 

  64. Masumoto H, Tabuchi H, Nakakura S et al (2018) Deep-learning classifier with an ultrawide-field scanning laser ophthalmoscope detects glaucoma visual field severity. J Glaucoma 27:647–652. https://doi.org/10.1097/IJG.0000000000000988

    Article  PubMed  Google Scholar 

  65. Ran AR, Tham CC, Chan PP et al (2021) Deep learning in glaucoma with optical coherence tomography: a review. Eye 35:188–201. https://doi.org/10.1038/s41433-020-01191-5

    Article  PubMed  Google Scholar 

  66. Maetschke S, Antony B, Ishikawa H et al (2019) A feature agnostic approach for glaucoma detection in OCT volumes. PLoS ONE 14:e0219126. https://doi.org/10.1371/journal.pone.0219126

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  67. Matsuba S, Tabuchi H, Ohsugi H et al (2019) 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. https://doi.org/10.1007/s10792-018-0940-0

    Article  PubMed  Google Scholar 

  68. Li Z, Guo C, Nie D et al (2021) Automated detection of retinal exudates and drusen in ultra-widefield fundus images based on deep learning. Eye 1–6. https://doi.org/10.1038/s41433-021-01715-7

  69. Masumoto H, Tabuchi H, Nakakura S et al (2019) Accuracy of a deep convolutional neural network in detection of retinitis pigmentosa on ultrawide-field images. PeerJ 7:e6900. https://doi.org/10.7717/peerj.6900

    Article  PubMed  PubMed Central  Google Scholar 

  70. Kim IK, Lee K, Park JH et al (2021) Classification of pachychoroid disease on ultrawide-field indocyanine green angiography using auto-machine learning platform. Br J Ophthalmol 105:856–861. https://doi.org/10.1136/bjophthalmol-2020-316108

    Article  PubMed  Google Scholar 

  71. Nagasato D, Tabuchi H, Ohsugi H et al (2018) Deep neural network-based method for detecting central retinal vein occlusion using ultrawide-field fundus ophthalmoscopy. Journal of Ophthalmology 2018:1–6. https://doi.org/10.1155/2018/1875431

    Article  Google Scholar 

  72. Nagasato D, Tabuchi H, Ohsugi H et al (2019) Deep-learning classifier with ultrawide-field fundus ophthalmoscopy for detecting branch retinal vein occlusion. Int J Ophthalmol 12:94–99. https://doi.org/10.18240/ijo.2019.01.15

    Article  PubMed  PubMed Central  Google Scholar 

  73. Shi Z, Wang T, Huang Z et al (2021) A method for the automatic detection of myopia in Optos fundus images based on deep learning. Int J Numer Methods Biomed Eng 37:e3460. https://doi.org/10.1002/cnm.3460

  74. Li Z, Guo C, Nie D et al (2020) Development and evaluation of a deep learning system for screening retinal hemorrhage based on ultra-widefield fundus images. Transl Vision Sci Technol 9:3. https://doi.org/10.1167/tvst.9.2.3

    Article  Google Scholar 

  75. Dai L, Wu L, Li H et al (2021) A deep learning system for detecting diabetic retinopathy across the disease spectrum. Nat Commun 12:3242. https://doi.org/10.1038/s41467-021-23458-5

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  76. Calderon-Auza G, Carrillo-Gomez C, Nakano M et al (2020) A teleophthalmology support system based on the visibility of retinal elements using the CNNs. Sensors 20:2838. https://doi.org/10.3390/s20102838

    Article  PubMed Central  Google Scholar 

  77. Li HH, Abraham JR, Sevgi DD et al (2020) Automated quality assessment and image selection of ultra-widefield fluorescein angiography images through deep learning. Trans Vis Sci Tech 9:52–52. https://doi.org/10.1167/tvst.9.2.52

    Article  Google Scholar 

  78. Li Z, Guo C, Nie D et al (2020) Deep learning from “passive feeding” to “selective eating” of real-world data. NPJ Digit Med 3:143. https://doi.org/10.1038/s41746-020-00350-y

  79. Ding L, Kuriyan AE, Ramchandran RS et al (2021) Weakly-supervised vessel detection in ultra-widefield fundus photography via iterative multi-modal registration and learning. IEEE Trans Med Imaging 40:2748–2758. https://doi.org/10.1109/TMI.2020.3027665

  80. do Nunez Rio JM, Sen P, Rasheed R et al (2020) Deep learning-based segmentation and quantification of retinal capillary non-perfusion on ultra-wide-field retinal fluorescein angiography. J Clin Med 9:2537. https://doi.org/10.3390/jcm9082537

    Article  Google Scholar 

  81. Wang Z, Jiang X, Liu J et al (2020) Multi-task siamese network for retinal artery/vein separation via deep convolution along vessel. IEEE Trans Med Imaging 39:2904–2919. https://doi.org/10.1109/TMI.2020.2980117

    Article  PubMed  Google Scholar 

  82. Sevgi DD, Srivastava SK, Wykoff C et al (2021) Deep learning-enabled ultra-widefield retinal vessel segmentation with an automated quality-optimized angiographic phase selection tool. Eye (Lond). https://doi.org/10.1038/s41433-021-01661-4

  83. Niemeijer M, Xu X, Dumitrescu AV et al (2011) Automated measurement of the arteriolar-to-venular width ratio in digital color fundus photographs. IEEE Trans Med Imaging 30:1941–1950

    Article  PubMed  Google Scholar 

  84. Staal J, Abràmoff MD, Niemeijer M et al (2004) Ridge-based vessel segmentation in color images of the retina. IEEE Trans Med Imaging 23:501–509

    Article  PubMed  Google Scholar 

  85. Estrada R, Tomasi C, Schmidler SC, Farsiu S (2014) Tree topology estimation. IEEE Trans Pattern Anal Mach Intell 37:1688–1701

    Article  Google Scholar 

  86. Ju L, Wang X, Zhou Q et al (2020) Bridge the domain gap between ultra-wide-field and traditional fundus images via adversarial domain adaptation. https://doi.org/10.48550/ARXIV.2003.10042

  87. Ju L, Wang X, Zhao X et al (2021) Leveraging regular fundus images for training UWF fundus diagnosis models via adversarial learning and pseudo-labeling. IEEE Trans Med Imaging 40:2911–2925. https://doi.org/10.1109/TMI.2021.3056395

    Article  PubMed  Google Scholar 

  88. Xie H, Lei H, Zeng X et al (2020) AMD-GAN: Attention encoder and multi-branch structure based generative adversarial networks for fundus disease detection from scanning laser ophthalmoscopy images. Neural Netw 132:477–490. https://doi.org/10.1016/j.neunet.2020.09.005

    Article  PubMed  Google Scholar 

  89. Yoo TK, Ryu IH, Kim JK et al (2020) Deep learning can generate traditional retinal fundus photographs using ultra-widefield images via generative adversarial networks. Comput Methods Programs Biomed 197:105761. https://doi.org/10.1016/j.cmpb.2020.105761

    Article  PubMed  Google Scholar 

  90. Goodfellow I, Pouget-Abadie J, Mirza M et al (2014) Generative adversarial nets. In: Ghahramani Z, Welling M, Cortes C (eds) Advances in neural information processing systems. Curran Associates, Inc.

  91. Karpathy A, Abbeel P, Brockman G et al (2016) Generative models. In: OpenAI. https://openai.com/blog/generative-models/. Accessed 18 Aug 2021

  92. NVIDIA Research Projects (2021) StyleGAN - official tensorflow implementation. NVIDIA Research Projects

  93. Nagasato D, Tabuchi H, Masumoto H et al (2020) Prediction of age and brachial-ankle pulse-wave velocity using ultra-wide-field pseudo-color images by deep learning. Scientific Reports 10:19369. https://doi.org/10.1038/s41598-020-76513-4

  94. Wisely CE, Wang D, Henao R et al (2022) Convolutional neural network to identify symptomatic Alzheimer’s disease using multimodal retinal imaging. Br J Ophthalmol 106:388–395. https://doi.org/10.1136/bjophthalmol-2020-317659

  95. Parikh RB, Teeple S, Navathe AS (2019) Addressing bias in artificial intelligence in health care. JAMA 322:2377–2378. https://doi.org/10.1001/jama.2019.18058

    Article  PubMed  Google Scholar 

  96. Selvaraju RR, Cogswell M, Das A et al (2020) Grad-CAM: visual explanations from deep networks via gradient-based localization. Int J Comput Vis 128:336–359. https://doi.org/10.1007/s11263-019-01228-7

    Article  Google Scholar 

  97. Hanif AM, Beqiri S, Keane PA, Campbell JP (2021) Applications of interpretability in deep learning models for ophthalmology. Curr Opin Ophthalmol 32:452–458. https://doi.org/10.1097/ICU.0000000000000780

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Acknowledgements

None.

Author information

Authors and Affiliations

  1. Faculty of Medicine, McGill University, Montréal, Québec, Canada

    Nishaant Bhambra & Farida El Malt

  2. Department of Ophthalmology, Université de Montréal, Montréal, Québec, Canada

    Fares Antaki & Renaud Duval

  3. Centre Universitaire d’Ophtalmologie (CUO), Hôpital Maisonneuve-Rosemont, CIUSSS de L’Est-de-L’Île-de-Montréal, 5415 Assumption Blvd, Montréal, Québec, H1T 2M4, Canada

    Fares Antaki & Renaud Duval

  4. Faculty of Medicine, Université de Montréal, Montréal, Québec, Canada

    AnQi Xu

Authors
  1. Nishaant Bhambra
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fares Antaki
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Farida El Malt
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. AnQi Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Renaud Duval
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Renaud Duval.

Ethics declarations

Ethics approval

This article does not contain any studies with human participants performed by any of the authors. As this is a review of previously published articles, no ethical or IRB approval was required.

Conflict of interest

Fares Antaki reports research funding from Bayer and honoraria from Snell Medical Communication. Renaud Duval reports speaker honoraria from Bayer, Roche, Novartis and Alcon, a research grant and an unrestricted education grant from Bayer, and equity ownership in Optina Diagnostics. Nishaant Bhambra, Farida El-Malt, and AnQi Xu declare that they have no conflicts of interest.

Conflict of interest

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

Bhambra, N., Antaki, F., Malt, F.E. et al. Deep learning for ultra-widefield imaging: a scoping review. Graefes Arch Clin Exp Ophthalmol 260, 3737–3778 (2022). https://doi.org/10.1007/s00417-022-05741-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00417-022-05741-3

Keywords

Search

Navigation