Deep learning in ophthalmology

The technical and clinical considerations

Daniel S.W. Ting, Lily Peng, Avinash V. Varadarajan, Pearse A. Keane, Philippe M. Burlina, Michael Chiang, Leopold Schmetterer, Louis R. Pasquale, Neil M. Bressler, Dale R. Webster, Michael Abramoff, Tien Y. Wong

Research output: Contribution to journalReview article

Abstract

The advent of computer graphic processing units, improvement in mathematical models and availability of big data has allowed artificial intelligence (AI) using machine learning (ML) and deep learning (DL) techniques to achieve robust performance for broad applications in social-media, the internet of things, the automotive industry and healthcare. DL systems in particular provide improved capability in image, speech and motion recognition as well as in natural language processing. In medicine, significant progress of AI and DL systems has been demonstrated in image-centric specialties such as radiology, dermatology, pathology and ophthalmology. New studies, including pre-registered prospective clinical trials, have shown DL systems are accurate and effective in detecting diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD), retinopathy of prematurity, refractive error and in identifying cardiovascular risk factors and diseases, from digital fundus photographs. There is also increasing attention on the use of AI and DL systems in identifying disease features, progression and treatment response for retinal diseases such as neovascular AMD and diabetic macular edema using optical coherence tomography (OCT). Additionally, the application of ML to visual fields may be useful in detecting glaucoma progression. There are limited studies that incorporate clinical data including electronic health records, in AL and DL algorithms, and no prospective studies to demonstrate that AI and DL algorithms can predict the development of clinical eye disease. This article describes global eye disease burden, unmet needs and common conditions of public health importance for which AI and DL systems may be applicable. Technical and clinical aspects to build a DL system to address those needs, and the potential challenges for clinical adoption are discussed. AI, ML and DL will likely play a crucial role in clinical ophthalmology practice, with implications for screening, diagnosis and follow up of the major causes of vision impairment in the setting of ageing populations globally.

Original languageEnglish (US)
JournalProgress in Retinal and Eye Research
DOIs
StatePublished - Jan 1 2019

Fingerprint

Ophthalmology
Learning
Artificial Intelligence
Eye Diseases
Macular Degeneration
Glaucoma
Natural Language Processing
Computer Graphics
Social Media
Retinal Diseases
Retinopathy of Prematurity
Health Care Sector
Refractive Errors
Macular Edema
Electronic Health Records
Optical Coherence Tomography
Diabetic Retinopathy
Dermatology
Visual Fields
Radiology

ASJC Scopus subject areas

  • Ophthalmology
  • Sensory Systems

Cite this

Deep learning in ophthalmology : The technical and clinical considerations. / Ting, Daniel S.W.; Peng, Lily; Varadarajan, Avinash V.; Keane, Pearse A.; Burlina, Philippe M.; Chiang, Michael; Schmetterer, Leopold; Pasquale, Louis R.; Bressler, Neil M.; Webster, Dale R.; Abramoff, Michael; Wong, Tien Y.

In: Progress in Retinal and Eye Research, 01.01.2019.

Research output: Contribution to journalReview article

Ting, DSW, Peng, L, Varadarajan, AV, Keane, PA, Burlina, PM, Chiang, M, Schmetterer, L, Pasquale, LR, Bressler, NM, Webster, DR, Abramoff, M & Wong, TY 2019, 'Deep learning in ophthalmology: The technical and clinical considerations', Progress in Retinal and Eye Research. https://doi.org/10.1016/j.preteyeres.2019.04.003
Ting, Daniel S.W. ; Peng, Lily ; Varadarajan, Avinash V. ; Keane, Pearse A. ; Burlina, Philippe M. ; Chiang, Michael ; Schmetterer, Leopold ; Pasquale, Louis R. ; Bressler, Neil M. ; Webster, Dale R. ; Abramoff, Michael ; Wong, Tien Y. / Deep learning in ophthalmology : The technical and clinical considerations. In: Progress in Retinal and Eye Research. 2019.
@article{166ded0807d54984a08204a285ff610e,
title = "Deep learning in ophthalmology: The technical and clinical considerations",
abstract = "The advent of computer graphic processing units, improvement in mathematical models and availability of big data has allowed artificial intelligence (AI) using machine learning (ML) and deep learning (DL) techniques to achieve robust performance for broad applications in social-media, the internet of things, the automotive industry and healthcare. DL systems in particular provide improved capability in image, speech and motion recognition as well as in natural language processing. In medicine, significant progress of AI and DL systems has been demonstrated in image-centric specialties such as radiology, dermatology, pathology and ophthalmology. New studies, including pre-registered prospective clinical trials, have shown DL systems are accurate and effective in detecting diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD), retinopathy of prematurity, refractive error and in identifying cardiovascular risk factors and diseases, from digital fundus photographs. There is also increasing attention on the use of AI and DL systems in identifying disease features, progression and treatment response for retinal diseases such as neovascular AMD and diabetic macular edema using optical coherence tomography (OCT). Additionally, the application of ML to visual fields may be useful in detecting glaucoma progression. There are limited studies that incorporate clinical data including electronic health records, in AL and DL algorithms, and no prospective studies to demonstrate that AI and DL algorithms can predict the development of clinical eye disease. This article describes global eye disease burden, unmet needs and common conditions of public health importance for which AI and DL systems may be applicable. Technical and clinical aspects to build a DL system to address those needs, and the potential challenges for clinical adoption are discussed. AI, ML and DL will likely play a crucial role in clinical ophthalmology practice, with implications for screening, diagnosis and follow up of the major causes of vision impairment in the setting of ageing populations globally.",
author = "Ting, {Daniel S.W.} and Lily Peng and Varadarajan, {Avinash V.} and Keane, {Pearse A.} and Burlina, {Philippe M.} and Michael Chiang and Leopold Schmetterer and Pasquale, {Louis R.} and Bressler, {Neil M.} and Webster, {Dale R.} and Michael Abramoff and Wong, {Tien Y.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/j.preteyeres.2019.04.003",
language = "English (US)",
journal = "Progress in Retinal and Eye Research",
issn = "1350-9462",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Deep learning in ophthalmology

T2 - The technical and clinical considerations

AU - Ting, Daniel S.W.

AU - Peng, Lily

AU - Varadarajan, Avinash V.

AU - Keane, Pearse A.

AU - Burlina, Philippe M.

AU - Chiang, Michael

AU - Schmetterer, Leopold

AU - Pasquale, Louis R.

AU - Bressler, Neil M.

AU - Webster, Dale R.

AU - Abramoff, Michael

AU - Wong, Tien Y.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The advent of computer graphic processing units, improvement in mathematical models and availability of big data has allowed artificial intelligence (AI) using machine learning (ML) and deep learning (DL) techniques to achieve robust performance for broad applications in social-media, the internet of things, the automotive industry and healthcare. DL systems in particular provide improved capability in image, speech and motion recognition as well as in natural language processing. In medicine, significant progress of AI and DL systems has been demonstrated in image-centric specialties such as radiology, dermatology, pathology and ophthalmology. New studies, including pre-registered prospective clinical trials, have shown DL systems are accurate and effective in detecting diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD), retinopathy of prematurity, refractive error and in identifying cardiovascular risk factors and diseases, from digital fundus photographs. There is also increasing attention on the use of AI and DL systems in identifying disease features, progression and treatment response for retinal diseases such as neovascular AMD and diabetic macular edema using optical coherence tomography (OCT). Additionally, the application of ML to visual fields may be useful in detecting glaucoma progression. There are limited studies that incorporate clinical data including electronic health records, in AL and DL algorithms, and no prospective studies to demonstrate that AI and DL algorithms can predict the development of clinical eye disease. This article describes global eye disease burden, unmet needs and common conditions of public health importance for which AI and DL systems may be applicable. Technical and clinical aspects to build a DL system to address those needs, and the potential challenges for clinical adoption are discussed. AI, ML and DL will likely play a crucial role in clinical ophthalmology practice, with implications for screening, diagnosis and follow up of the major causes of vision impairment in the setting of ageing populations globally.

AB - The advent of computer graphic processing units, improvement in mathematical models and availability of big data has allowed artificial intelligence (AI) using machine learning (ML) and deep learning (DL) techniques to achieve robust performance for broad applications in social-media, the internet of things, the automotive industry and healthcare. DL systems in particular provide improved capability in image, speech and motion recognition as well as in natural language processing. In medicine, significant progress of AI and DL systems has been demonstrated in image-centric specialties such as radiology, dermatology, pathology and ophthalmology. New studies, including pre-registered prospective clinical trials, have shown DL systems are accurate and effective in detecting diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD), retinopathy of prematurity, refractive error and in identifying cardiovascular risk factors and diseases, from digital fundus photographs. There is also increasing attention on the use of AI and DL systems in identifying disease features, progression and treatment response for retinal diseases such as neovascular AMD and diabetic macular edema using optical coherence tomography (OCT). Additionally, the application of ML to visual fields may be useful in detecting glaucoma progression. There are limited studies that incorporate clinical data including electronic health records, in AL and DL algorithms, and no prospective studies to demonstrate that AI and DL algorithms can predict the development of clinical eye disease. This article describes global eye disease burden, unmet needs and common conditions of public health importance for which AI and DL systems may be applicable. Technical and clinical aspects to build a DL system to address those needs, and the potential challenges for clinical adoption are discussed. AI, ML and DL will likely play a crucial role in clinical ophthalmology practice, with implications for screening, diagnosis and follow up of the major causes of vision impairment in the setting of ageing populations globally.

UR - http://www.scopus.com/inward/record.url?scp=85065560866&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065560866&partnerID=8YFLogxK

U2 - 10.1016/j.preteyeres.2019.04.003

DO - 10.1016/j.preteyeres.2019.04.003

M3 - Review article

JO - Progress in Retinal and Eye Research

JF - Progress in Retinal and Eye Research

SN - 1350-9462

ER -