Deep learning for predicting refractive error from retinal fundus images

Investigative Ophthalmology and Visual Science

Volumn 59, Issue 7, 2018, Pages 2861-2868

  Varadarajan, Avinash V ^a   Poplin, Ryan ^a   Blumer, Katy ^a   Angermueller, Christof ^a   Ledsam, Joe ^b   Chopra, Reena ^c   Keane, Pearse A ^c   Corrado, Greg S ^a   Peng, Lily ^a   Webster, Dale R ^a  

^a GOOGLE INC   (United States)

^b GOOGLE   (United Kingdom)

^c MOORFIELDS EYE HOSPITAL   (United Kingdom)

Author keywords

Deep learning; Machine learning; Refractive error; Retinal imaging

Indexed keywords

ADULT; AGED; ALGORITHM; ARTICLE; DEEP LEARNING ALGORITHM; DIAGNOSTIC IMAGING; EYE FUNDUS; FEMALE; HUMAN; MAJOR CLINICAL STUDY; MALE; MIDDLE AGED; NERVE CELL NETWORK; OPTICAL COHERENCE TOMOGRAPHY; PRIORITY JOURNAL; REFRACTION ERROR; RETINAL FUNDUS IMAGING; EYE REFRACTION; INFORMATION PROCESSING; PHYSIOLOGY; RETINA; VISION TEST; VISUAL FIELD;

ADULT; AGED; ALGORITHMS; DATASETS AS TOPIC; DEEP LEARNING; FEMALE; FUNDUS OCULI; HUMANS; MALE; MIDDLE AGED; REFRACTION, OCULAR; REFRACTIVE ERRORS; RETINA; VISION TESTS; VISUAL FIELDS;

EID: 85048032246     PISSN: 01460404     EISSN: 15525783     Source Type: Journal    
DOI: 10.1167/iovs.18-23887     Document Type: Article

References (44)

1. Pascolini D, Mariotti SP. Global estimates of visual impairment: 2010. Br J Ophthalmol. 2012;96:614–618.
2. Rabbetts R. Bennett and Rabbett’s Clinical Visual Optics. 4th ed. Amsterdam: Elsevier; 2007.
3. Foster PJ, Jiang Y. Epidemiology of myopia. Eye. 2014;28:202– 208.
4. Kovin S, Naidoo JJ. Uncorrected refractive errors. Indian J Ophthalmol. 2012;60:432–437.
5. Bolster NM, Giardini ME, Livingstone IAT, Bastawrous A. How the smartphone is driving the eye-health imaging revolution. Expert Rev Ophthalmol. 2014;9:475–485.
6. Bastawrous A, Rono HK, Livingstone IAT, et al. Development and validation of a smartphone-based visual acuity test (peek acuity) for clinical practice and community-based fieldwork. JAMA Ophthalmol. 2015;133:930–937.
7. Bolster NM, Giardini ME, Bastawrous A. The diabetic retinopathy screening workflow: potential for smartphone imaging. J Diabetes Sci Technol. 2015;10:318–324.
8. Bastawrous A, Giardini ME, Bolster NM, et al. Clinical validation of a smartphone-based adapter for optic disc imaging in Kenya. JAMA Ophthalmol. 2016;134:151–158.
9. LeCun Y, Yoshua B, Geoffrey H. Deep learning. Nature. 2015; 521:436–444.
10. Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542:115–118.
11. Gulshan V, Peng L, Coram M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016;316:2402–2410.
12. Gargeya R, Leng T. Automated identification of diabetic retinopathy using deep learning. Ophthalmology. 2017;124: 962–969.
13. Liu Y, Gadepalli K, Norouzi M, et al. Detecting cancer metastases on gigapixel pathology images. arXiv. 2017: 1703.02442.
14. Wang D, Khosla A, Gargeya R, Irshad H, Beck AH. Deep learning for identifying metastatic breast cancer. arXiv. 2016: 1606.05718.
15. Poplin R, Varadarajan AV, Blumer K, et al. Predicting cardiovascular risk factors from retinal fundus photographs using deep learning. arXiv. 2017:1708.09843.
16. He K, Zhang X, Ren S, Sun J. Identity mappings in deep residual networks. Comput Vis ECCV. 2016;4:630–645.
17. Atchison DA, Pritchard N, Schmid KL, Scott DH, Jones CE, Pope JM. Shape of the retinal surface in emmetropia and myopia. Invest Ophthalmol Vis Sci. 2005;46:2698–2707.
18. Biobank. UK About UK Biobank website. Available at: http://www.ukbiobank.ac.uk/about-biobank-uk/. Accessed March 26, 2017.
19. National Eye Institute. National Eye Institute (NEI) Age-Rel ated Eye Di sease Study (AREDS) (dbGaP ID: phs000001.v3.p1). Available at: https://www.ncbi.nlm.nih.gov/projects/gap/cgi-bin/study.cgi?study_id=phs000001.v3.p1. Accessed September 22, 2017.
20. National Eye Institute. Age-Related Eye Disease Study (AREDS). Photographic procedures. Chapter 8. dbGaP ID: phd000008. https://www.ncbi.nlm.nih.gov/projects/gap/cgi-bin/document.cgi?study_id=phs000001.v3.p1&phv=53743&phd=8&pha=2856&pht=371&phvf=&phdf=&phaf=&pht f=&dssp= 1&consent=&t emp=1. Accessed November 22, 2017.
21. Angermueller C, Pärnamaa T, Parts L, Stegle O. Deep learning for computational biology. Mol Syst Biol. 2016;12:878.
22. TensorFlow. Open source machine learning framework. http://tensorflow.org. Accessed August 3, 2017.
23. Xu K, Ba J, Kiros R, et al. Show, attend and tell: neural image caption generation with visual attention. Proc Int Conf Mach Learn Appl. 2015:2048–2057.
24. Caruana R, Lawrence S, Giles L. Overfitting in neural nets: backpropagation, conjugate gradient, and early stopping. In: Leen TK, Dietterich TG, Tresp V. Advances in Neural Information Processing Systems 13: Proceedings of the 2000 Conference. Cambridge, MA: MIT Press; 2001.
25. Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. 2012:1097–1105.
26. Ryan S, Schachat A, Wilkinson C, Hinton D, Sadda S, Wiedemann P. Retina. 5th ed. Amsterdam: Elsevier; 2012.
27. Ostrin LA, Yuzuriha J, Wildsoet CF. Refractive error and ocular parameters: comparison of two SD-OCT systems. Optom Vis Sci. 2015;92:437–446.
28. Kitaguchi Y, Bessho K, Yamaguchi T, Nakazawa N, Mihashi T, Fujikado T. In vivo measurements of cone photoreceptor spacing in myopic eyes from images obtained by an adaptive optics fundus camera. Jpn J Ophthalmol. 2007;51:456–461.
29. Newcomb RD, Potter JW. Clinical investigation of the foveal light reflex. Am J Optom Physiol Opt. 1981;58:1110–1119.
30. Czepita M, Karczewicz D, Safranow K, Czepita D. Macular pigment optical density and ocular pulse amplitude in subjects with different axial lengths and refractive errors. Med Sci Monit. 2015;21:1716–1720.
31. Bour LJ, Koo L, Delori FC, Apkarian P, Fulton AB. Fundus photography for measurement of macular pigment density distribution in children. Invest Ophthalmol Vis Sci. 2002;43: 1450–1455.
32. Ramrattan RS, Wolfs RC, Jonas JB, Hofman A, de Jong PT. Determinants of optic disc characteristics in a general population: The Rotterdam Study. Ophthalmology. 1999; 106:1588–1596.
33. Wu R-Y, Wong T-Y, Zheng Y-F, et al. Influence of refractive error on optic disc topographic parameters: the Singapore Malay Eye Study. Am J Ophthalmol. 2011;152:81–86.
34. Jonas JB. Optic disk size correlated with refractive error. Am J Ophthalmol. 2005;139:346–348.
35. Varma R, Tielsch JM, Quigley HA, et al. Race-, age-, gender-, and refractive error-related differences in the normal optic disc. Arch Ophthalmol. 1994;112:1068–1076.
36. Vongphanit J, Mitchell P, Wang JJ. Population prevalence of tilted optic disks and the relationship of this sign to refractive error. Am J Ophthalmol. 2002;133:679–685.
37. Lim LS, Cheung CY-L, Lin X, Mitchell P, Wong TY, Mei-Saw S. Influence of refractive error and axial length on retinal vessel geometric characteristics. Invest Ophthalmol Vis Sci. 2011; 52:669–678.
38. Li H, Mitchell P, Liew G, et al. Lens opacity and refractive influences on the measurement of retinal vascular fractal dimension. Acta Ophthalmol. 2010;88:e234–e240.
39. Elze T, Baniasadi N, Jin Q, Wang H, Wang M. Ametropia, retinal anatomy, and OCT abnormality patterns in glaucoma. 1. Impacts of refractive error and interartery angle. J Biomed Opt. 2017;22:121713.
40. Wang M, Jin Q, Wang H, Li D, Baniasadi N, Elze T. The interrelationship between refractive error, blood vessel anatomy, and glaucomatous visual field loss. Trans Vis Sci Tech. 2018;7(1):4.
41. Wang M, Elze T, Li D, et al. Age, ocular magnification, and circumpapillary retinal nerve fiber layer thickness. J Biomed Opt. 2017;22:1–19.
42. Baniasadi N, Wang M, Wang H, Mahd M, Elze T. Associations between optic nerve head–related anatomical parameters and refractive error over the full range of glaucoma severity. Trans Vis Sci Tech. 2017;6(4):9.
43. Wang M, Elze T, Li D, et al. Age, ocular magnification, and circumpapillary retinal nerve fiber layer thickness. J Biomed Opt. 2017;22:1–19.
44. Peek Vision. Peek Vision: Vision & Health for Everyone website. Available at: http://10ga.iapb.org/peek-vision-vision-health-for-everyone. Accessed December 4, 2017.