Cargando…

Deep-Learning–Based Pre-Diagnosis Assessment Module for Retinal Photographs: A Multicenter Study

PURPOSE: Artificial intelligence (AI) deep learning (DL) has been shown to have significant potential for eye disease detection and screening on retinal photographs in different clinical settings, particular in primary care. However, an automated pre-diagnosis image assessment is essential to stream...

Descripción completa

Detalles Bibliográficos
Autores principales: Yuen, Vincent, Ran, Anran, Shi, Jian, Sham, Kaiser, Yang, Dawei, Chan, Victor T. T., Chan, Raymond, Yam, Jason C., Tham, Clement C., McKay, Gareth J., Williams, Michael A., Schmetterer, Leopold, Cheng, Ching-Yu, Mok, Vincent, Chen, Christopher L., Wong, Tien Y., Cheung, Carol Y.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Association for Research in Vision and Ophthalmology 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8444486/
https://www.ncbi.nlm.nih.gov/pubmed/34524409
http://dx.doi.org/10.1167/tvst.10.11.16
_version_ 1784568503365271552
author Yuen, Vincent
Ran, Anran
Shi, Jian
Sham, Kaiser
Yang, Dawei
Chan, Victor T. T.
Chan, Raymond
Yam, Jason C.
Tham, Clement C.
McKay, Gareth J.
Williams, Michael A.
Schmetterer, Leopold
Cheng, Ching-Yu
Mok, Vincent
Chen, Christopher L.
Wong, Tien Y.
Cheung, Carol Y.
author_facet Yuen, Vincent
Ran, Anran
Shi, Jian
Sham, Kaiser
Yang, Dawei
Chan, Victor T. T.
Chan, Raymond
Yam, Jason C.
Tham, Clement C.
McKay, Gareth J.
Williams, Michael A.
Schmetterer, Leopold
Cheng, Ching-Yu
Mok, Vincent
Chen, Christopher L.
Wong, Tien Y.
Cheung, Carol Y.
author_sort Yuen, Vincent
collection PubMed
description PURPOSE: Artificial intelligence (AI) deep learning (DL) has been shown to have significant potential for eye disease detection and screening on retinal photographs in different clinical settings, particular in primary care. However, an automated pre-diagnosis image assessment is essential to streamline the application of the developed AI-DL algorithms. In this study, we developed and validated a DL-based pre-diagnosis assessment module for retinal photographs, targeting image quality (gradable vs. ungradable), field of view (macula-centered vs. optic-disc-centered), and laterality of the eye (right vs. left). METHODS: A total of 21,348 retinal photographs from 1914 subjects from various clinical settings in Hong Kong, Singapore, and the United Kingdom were used for training, internal validation, and external testing for the DL module, developed by two DL-based algorithms (EfficientNet-B0 and MobileNet-V2). RESULTS: For image-quality assessment, the pre-diagnosis module achieved area under the receiver operating characteristic curve (AUROC) values of 0.975, 0.999, and 0.987 in the internal validation dataset and the two external testing datasets, respectively. For field-of-view assessment, the module had an AUROC value of 1.000 in all of the datasets. For laterality-of-the-eye assessment, the module had AUROC values of 1.000, 0.999, and 0.985 in the internal validation dataset and the two external testing datasets, respectively. CONCLUSIONS: Our study showed that this three-in-one DL module for assessing image quality, field of view, and laterality of the eye of retinal photographs achieved excellent performance and generalizability across different centers and ethnicities. TRANSLATIONAL RELEVANCE: The proposed DL-based pre-diagnosis module realized accurate and automated assessments of image quality, field of view, and laterality of the eye of retinal photographs, which could be further integrated into AI-based models to improve operational flow for enhancing disease screening and diagnosis.
format Online
Article
Text
id pubmed-8444486
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher The Association for Research in Vision and Ophthalmology
record_format MEDLINE/PubMed
spelling pubmed-84444862021-09-30 Deep-Learning–Based Pre-Diagnosis Assessment Module for Retinal Photographs: A Multicenter Study Yuen, Vincent Ran, Anran Shi, Jian Sham, Kaiser Yang, Dawei Chan, Victor T. T. Chan, Raymond Yam, Jason C. Tham, Clement C. McKay, Gareth J. Williams, Michael A. Schmetterer, Leopold Cheng, Ching-Yu Mok, Vincent Chen, Christopher L. Wong, Tien Y. Cheung, Carol Y. Transl Vis Sci Technol Article PURPOSE: Artificial intelligence (AI) deep learning (DL) has been shown to have significant potential for eye disease detection and screening on retinal photographs in different clinical settings, particular in primary care. However, an automated pre-diagnosis image assessment is essential to streamline the application of the developed AI-DL algorithms. In this study, we developed and validated a DL-based pre-diagnosis assessment module for retinal photographs, targeting image quality (gradable vs. ungradable), field of view (macula-centered vs. optic-disc-centered), and laterality of the eye (right vs. left). METHODS: A total of 21,348 retinal photographs from 1914 subjects from various clinical settings in Hong Kong, Singapore, and the United Kingdom were used for training, internal validation, and external testing for the DL module, developed by two DL-based algorithms (EfficientNet-B0 and MobileNet-V2). RESULTS: For image-quality assessment, the pre-diagnosis module achieved area under the receiver operating characteristic curve (AUROC) values of 0.975, 0.999, and 0.987 in the internal validation dataset and the two external testing datasets, respectively. For field-of-view assessment, the module had an AUROC value of 1.000 in all of the datasets. For laterality-of-the-eye assessment, the module had AUROC values of 1.000, 0.999, and 0.985 in the internal validation dataset and the two external testing datasets, respectively. CONCLUSIONS: Our study showed that this three-in-one DL module for assessing image quality, field of view, and laterality of the eye of retinal photographs achieved excellent performance and generalizability across different centers and ethnicities. TRANSLATIONAL RELEVANCE: The proposed DL-based pre-diagnosis module realized accurate and automated assessments of image quality, field of view, and laterality of the eye of retinal photographs, which could be further integrated into AI-based models to improve operational flow for enhancing disease screening and diagnosis. The Association for Research in Vision and Ophthalmology 2021-09-15 /pmc/articles/PMC8444486/ /pubmed/34524409 http://dx.doi.org/10.1167/tvst.10.11.16 Text en Copyright 2021 The Authors https://creativecommons.org/licenses/by-nc-nd/4.0/This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
spellingShingle Article
Yuen, Vincent
Ran, Anran
Shi, Jian
Sham, Kaiser
Yang, Dawei
Chan, Victor T. T.
Chan, Raymond
Yam, Jason C.
Tham, Clement C.
McKay, Gareth J.
Williams, Michael A.
Schmetterer, Leopold
Cheng, Ching-Yu
Mok, Vincent
Chen, Christopher L.
Wong, Tien Y.
Cheung, Carol Y.
Deep-Learning–Based Pre-Diagnosis Assessment Module for Retinal Photographs: A Multicenter Study
title Deep-Learning–Based Pre-Diagnosis Assessment Module for Retinal Photographs: A Multicenter Study
title_full Deep-Learning–Based Pre-Diagnosis Assessment Module for Retinal Photographs: A Multicenter Study
title_fullStr Deep-Learning–Based Pre-Diagnosis Assessment Module for Retinal Photographs: A Multicenter Study
title_full_unstemmed Deep-Learning–Based Pre-Diagnosis Assessment Module for Retinal Photographs: A Multicenter Study
title_short Deep-Learning–Based Pre-Diagnosis Assessment Module for Retinal Photographs: A Multicenter Study
title_sort deep-learning–based pre-diagnosis assessment module for retinal photographs: a multicenter study
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8444486/
https://www.ncbi.nlm.nih.gov/pubmed/34524409
http://dx.doi.org/10.1167/tvst.10.11.16
work_keys_str_mv AT yuenvincent deeplearningbasedprediagnosisassessmentmoduleforretinalphotographsamulticenterstudy
AT rananran deeplearningbasedprediagnosisassessmentmoduleforretinalphotographsamulticenterstudy
AT shijian deeplearningbasedprediagnosisassessmentmoduleforretinalphotographsamulticenterstudy
AT shamkaiser deeplearningbasedprediagnosisassessmentmoduleforretinalphotographsamulticenterstudy
AT yangdawei deeplearningbasedprediagnosisassessmentmoduleforretinalphotographsamulticenterstudy
AT chanvictortt deeplearningbasedprediagnosisassessmentmoduleforretinalphotographsamulticenterstudy
AT chanraymond deeplearningbasedprediagnosisassessmentmoduleforretinalphotographsamulticenterstudy
AT yamjasonc deeplearningbasedprediagnosisassessmentmoduleforretinalphotographsamulticenterstudy
AT thamclementc deeplearningbasedprediagnosisassessmentmoduleforretinalphotographsamulticenterstudy
AT mckaygarethj deeplearningbasedprediagnosisassessmentmoduleforretinalphotographsamulticenterstudy
AT williamsmichaela deeplearningbasedprediagnosisassessmentmoduleforretinalphotographsamulticenterstudy
AT schmettererleopold deeplearningbasedprediagnosisassessmentmoduleforretinalphotographsamulticenterstudy
AT chengchingyu deeplearningbasedprediagnosisassessmentmoduleforretinalphotographsamulticenterstudy
AT mokvincent deeplearningbasedprediagnosisassessmentmoduleforretinalphotographsamulticenterstudy
AT chenchristopherl deeplearningbasedprediagnosisassessmentmoduleforretinalphotographsamulticenterstudy
AT wongtieny deeplearningbasedprediagnosisassessmentmoduleforretinalphotographsamulticenterstudy
AT cheungcaroly deeplearningbasedprediagnosisassessmentmoduleforretinalphotographsamulticenterstudy