Ocular image-based deep learning for predicting refractive error: A systematic review

Samantha Min Er Yew; Yibing Chen; Jocelyn Hui Lin Goh; David Ziyou Chen; Marcus Chun Jin Tan; Ching-Yu Cheng; Victor Teck Chang Koh; Yih Chung Tham

doi:10.1016/j.aopr.2024.06.005

您当前的位置：

首页 >

文章列表页 >

Ocular image-based deep learning for predicting refractive error: A systematic review

Review | 更新时间：2024-12-14

- Ocular image-based deep learning for predicting refractive error: A systematic review
- Ocular image-based deep learning for predicting refractive error: A systematic review
- 眼科实践与研究新进展 2024年4卷第3期页码：164-172
- 作者机构：
  
  1. Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore,Singapore
  2. Centre for Innovation and Precision Eye Health, Yong Loo Lin School of Medicine, National University of Singapore,Singapore
  3. School of Chemistry, Chemical Engineering, and Biotechnology, Nanyang Technological University,Singapore
  4. Singapore Eye Research Institute, Singapore National Eye Centre,Singapore
  5. Department of Ophthalmology, National University Hospital,Singapore
  6. Ophthalmology and Visual Sciences (Eye ACP), Duke-NUS Medical School,Singapore
- 作者简介：
- 基金信息：
- DOI：10.1016/j.aopr.2024.06.005
  中图分类号：
- 纸质出版日期：2024，
- 稿件说明：
移动端阅览
Samantha Min Er Yew, Yibing Chen, Jocelyn Hui Lin Goh, 等. Ocular image-based deep learning for predicting refractive error: A systematic review[J]. 眼科实践与研究新进展, 2024,4(3):164-172.

SAMANTHA MIN ER YEW, YIBING CHEN, JOCELYN HUI LIN GOH, et al. Ocular image-based deep learning for predicting refractive error: A systematic review. [J]. Aopr, 2024, 4(3): 164-172.
Samantha Min Er Yew, Yibing Chen, Jocelyn Hui Lin Goh, 等. Ocular image-based deep learning for predicting refractive error: A systematic review[J]. 眼科实践与研究新进展, 2024,4(3):164-172. DOI： 10.1016/j.aopr.2024.06.005.

SAMANTHA MIN ER YEW, YIBING CHEN, JOCELYN HUI LIN GOH, et al. Ocular image-based deep learning for predicting refractive error: A systematic review. [J]. Aopr, 2024, 4(3): 164-172. DOI： 10.1016/j.aopr.2024.06.005.

摘要

Abstract

BackgroundUncorrected refractive error is a major cause of vision impairment worldwide and its increasing prevalent necessitates effective screening and management strategies. Meanwhile

deep learning

a subset of Artificial Intelligence

has significantly advanced ophthalmological diagnostics by automating tasks that required extensive clinical expertise. Although recent studies have investigated the use of deep learning models for refractive power detection through various imaging techniques

a comprehensive systematic review on this topic is has yet be done. This review aims to summarise and evaluate the performance of ocular image-based deep learning models in predicting refractive errors.Main textWe search on three databases (PubMed

Scopus

Web of Science) up till June 2023

focusing on deep learning applications in detecting refractive error from ocular images. We included studies that had reported refractive error outcomes

regardless of publication years. We systematically extracted and evaluated the continuous outcomes (sphere

cylinder) and categorical outcomes (myopia)

ground truth measurements

ocular imaging modalities

deep learning models

and performance metrics

adhering to PRISMA guidelines. Nine studies were identified and categorised into three groups: retinal photo-based (n = 5)

OCT-based (n = 1)

and external ocular photo-based (n = 3).For high myopia prediction

retinal photo-based models achieved AUC between 0.91 and 0.98

sensitivity levels between 85.10% and 97.80%

and specificity levels between 76.40% and 94.50%. For continuous prediction

retinal photo-based models reported MAE ranging from 0.31D to 2.19D

and

between 0.05 and 0.96. The OCT-based model achieved an AUC of 0.79–0.81

sensitivity of 82.30% and 87.20% and specificity of 61.70%–68.90%. For external ocular photo-based models

the AUC ranged from 0.91 to 0.99

sensitivity of 81.13%–84.00% and specificity of 74.00%–86.42%

MAE ranges from 0.07D to 0.18D and accuracy ranges from 81.60% to 96.70%. The reported papers collectively showed promising performances

in particular the retinal photo-based and external eye photo -based DL models.ConclusionsThe integration of deep learning model and ocular imaging for refractive error detection appear promising. However

their real-world clinical utility in current screening workflow have yet been evaluated and would require thoughtful consideration in design and implementation.

关键词

Keywords

Deep learningArtificial intelligenceRefractive errorRetinal imagesOpticalCoherence TomographyPhotorefractionOcular imagesPrediction

references

1 G.B.D. Blindness, C. Vision Impairment, Vision Loss Expert Group of the Global Burden of Disease SCauses of blindness and vision impairment in 2020 and trends over 30 years, and prevalence of avoidable blindness in relation to VISION 2020: the Right to Sight: an analysis for the Global Burden of Disease Study Lancet Global Health, 9 (2) (Feb 2021), pp. e144-e160, 10.1016/S2214-109X(20)30489-7

2 S.R. Flaxman, R.R.A. Bourne, S. Resnikoff, et al.Global causes of blindness and distance vision impairment 1990-2020: a systematic review and meta-analysis Lancet Global Health, 5 (12) (Dec 2017), pp. e1221-e1234, 10.1016/S2214-109X(17)30393-5

3 S. Keel, Z. Li, J. Scheetz, et al.Development and validation of a deep-learning algorithm for the detection of neovascular age-related macular degeneration from colour fundus photographs Clin Exp Ophthalmol, 47 (8) (Nov 2019), pp. 1009-1018, 10.1111/ceo.13575

4 K.S. Naidoo, J. Leasher, R.R. Bourne, et al.Global vision impairment and blindness due to uncorrected refractive error, 1990-2010 Optom Vis Sci, 93 (3) (Mar 2016), pp. 227-234, 10.1097/opx.0000000000000796

5 S.G. HonavarThe burden of uncorrected refractive error Indian J Ophthalmol, 67 (5) (May 2019), pp. 577-578, 10.4103/ijo.IJO_762_19

6 W. Dai, Y.-C. Tham, M.-L. Chee, et al.Falls and recurrent falls among adults in A multi-ethnic asian population: the Singapore Epidemiology of eye diseases study Sci Rep, 8 (1) (2018/05/15 2018), p. 7575, 10.1038/s41598-018-25894-8

7 E.L. Lamoreux, E. Chong, J.J. Wang, et al.Visual impairment, causes of vision loss, and falls: the Singapore Malay eye study Invest Ophthalmol Vis Sci, 49 (2) (2008), pp. 528-533, 10.1167/iovs.07-1036

8 J. Mehta, G. Czanner, S. Harding, D. Newsham, J. RobinsonVisual risk factors for falls in older adults: a case-control study BMC Geriatr, 22 (1) (2022/02/17 2022), p. 134, 10.1186/s12877-022-02784-3

9 W.H. OrganizationReport of the 2030 Targets on Effective Coverage of Eye Care (2022)

10 V. Gulshan, L. Peng, M. Coram, et al.Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs JAMA Network, 316 (22) (Dec 13 2016), pp. 2402-2410, 10.1001/jama.2016.17216

11 D.S.W. Ting, C.Y. Cheung, G. Lim, et al.Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes JAMA Network, 318 (22) (Dec 12 2017), pp. 2211-2223, 10.1001/jama.2017.18152

12 F. Grassmann, J. Mengelkamp, C. Brandl, et al.A deep learning algorithm for prediction of age-related eye disease study severity scale for age-related macular degeneration from color fundus photography Ophthalmology, 125 (9) (Sep 2018), pp. 1410-1420, 10.1016/j.ophtha.2018.02.037

13 World Report on Vision, World Health Organization, Geneva (2019)

14 Y. Peng, S. Dharssi, Q. Chen, et al.DeepSeeNet: a deep learning model for automated classification of patient-based age-related macular degeneration severity from color fundus photographs Ophthalmology, 126 (4) (Apr 2019), pp. 565-575, 10.1016/j.ophtha.2018.11.015

15 Y. Tham, J.H.L. Goh, A. Anees, et al.Detecting visually significant cataract using retinal photograph-based deep learning Nature Aging (2022), 10.1038/s43587-022-00171-6

16 Y.C. Tham, A. Anees, L. Zhang, et al.Referral for disease-related visual impairment using retinal photograph-based deep learning: a proof-of-concept, model development study Lancet Digit Health, 3 (1) (Jan 2021), pp. e29-e40, 10.1016/S2589-7500(20)30271-5

17 H. Liu, L. Li, I.M. Wormstone, et al.Development and validation of a deep learning system to detect glaucomatous optic neuropathy using fundus photographs JAMA Ophthalmol, 137 (12) (Dec 1 2019), pp. 1353-1360, 10.1001/jamaophthalmol.2019.3501

18 J. Chun, Y. Kim, K.Y. Shin, et al.Deep learning-based prediction of refractive error using photorefraction images captured by a smartphone: model development and validation study JMIR Med Inform, 8 (5) (May 5 2020), Article e16225, 10.2196/16225

19 Z. Shi, T. Wang, Z. Huang, F. Xie, G. SongA method for the automatic detection of myopia in Optos fundus images based on deep learning Int J Numer Method Biomed Eng, 37 (6) (2021), Article e3460, 10.1002/cnm.3460

20 T.E. Tan, A. Anees, C. Chen, et al.Retinal photograph-based deep learning algorithms for myopia and a blockchain platform to facilitate artificial intelligence medical research: a retrospective multicohort study Lancet Digit Health, 3 (5) (May 2021), pp. e317-e329, 10.1016/S2589-7500(21)00055-8

21 A.V. Varadarajan, R. Poplin, K. Blumer, et al.Deep learning for predicting refractive error from retinal fundus images Invest Ophthalmol Vis Sci, 59 (7) (Jun 1 2018), pp. 2861-2868, 10.1167/iovs.18-23887

22 D. Xu, S. Ding, T. Zheng, et al.Deep learning for predicting refractive error from multiple photorefraction images Biomed Eng Online, 21 (1) (Aug 8 2022), p. 55, 10.1186/s12938-022-01025-3

23 D. Yang, M. Li, W. Li, et al.Prediction of refractive error based on ultrawide field images with deep learning models in myopia patients Front Med, 9 (2022), Article 834281, 10.3389/fmed.2022.834281

24 Y. Yang, R. Li, D. Lin, et al.Automatic identification of myopia based on ocular appearance images using deep learning Ann Transl Med, 8 (11) (Jun 2020), p. 705, 10.21037/atm.2019.12.39

25 T.K. Yoo, I.H. Ryu, J.K. Kim, I.S. LeeDeep learning for predicting uncorrected refractive error using posterior segment optical coherence tomography images Eye, 36 (10) (2022), pp. 1959-1965, 10.1038/s41433-021-01795-5

26 H. Zou, S. Shi, X. Yang, et al.Identification of ocular refraction based on deep learning algorithm as a novel retinoscopy method Biomed Eng Online, 21 (1) (2022), p. 87, 10.1186/s12938-022-01057-9

27 D.A. Atchison, N. Pritchard, K.L. Schmid, D.H. Scott, C.E. Jones, J.M. PopeShape of the retinal surface in emmetropia and myopia Invest Ophthalmol Vis Sci, 46 (8) (Aug 2005), pp. 2698-2707, 10.1167/iovs.04-1506

28 L. Chang, C.W. Pan, K. Ohno-Matsui, et al.Myopia-related fundus changes in Singapore adults with high myopia Am J Ophthalmol, 155 (6) (Jun 2013), pp. 991-999 e1, 10.1016/j.ajo.2013.01.016

29 N. Shimada, K. Ohno-Matsui, A. Nishimuta, T. Tokoro, M. MochizukiPeripapillary changes detected by optical coherence tomography in eyes with high myopia Ophthalmology, 114 (11) (Nov 2007), pp. 2070-2076, 10.1016/j.ophtha.2007.01.016

30 L.A. Ostrin, J. Yuzuriha, C.F. WildsoetRefractive error and ocular parameters: comparison of two SD-OCT systems Optom Vis Sci, 92 (4) (Apr 2015), pp. 437-446, 10.1097/OPX.0000000000000559

31 V. Oner, M. Tas, F.M. Turkcu, M.F. Alakus, Y. Iscan, A.T. YaziciEvaluation of peripapillary retinal nerve fiber layer thickness of myopic and hyperopic patients: a controlled study by Stratus optical coherence tomography Curr Eye Res, 38 (1) (Jan 2013), pp. 102-107, 10.3109/02713683.2012.715714

32 J.B. Jonas, M.M. Bikbov, Y.X. Wang, R.A. Jonas, S. Panda-JonasAnatomic peculiarities associated with axial elongation of the myopic eye J Clin Med, 12 (4) (Feb 7 2023), 10.3390/jcm12041317

33 V. Thambawita, I. Strumke, S.A. Hicks, P. Halvorsen, S. Parasa, M.A. RieglerImpact of image resolution on deep learning performance in endoscopy image classification: an experimental study using a large dataset of endoscopic images Diagnostics, 11 (12) (Nov 24 2021), 10.3390/diagnostics11122183

34 T. Das, B. Takkar, S. Sivaprasad, et al.Recently updated global diabetic retinopathy screening guidelines: commonalities, differences, and future possibilities Eye, 35 (10) (2021/10/01 2021), pp. 2685-2698, 10.1038/s41433-021-01572-4

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

Artificial intelligence and deep learning in ophthalmology: Current status and future perspectives

A deep learning-based image analysis for assessing the extent of abduction in abducens nerve palsy patients before and after strabismus surgery

Integration of smartphone technology and artificial intelligence for advanced ophthalmic care: A systematic review

Global research on artificial intelligence in thyroid-associated ophthalmopathy: A bibliometric analysis

Relationship between axial length and spherical equivalent refraction in Chinese children