Deep learning models for screening of high myopia using optical coherence tomography

Abstract This study aimed to validate and evaluate deep learning (DL) models for screening of high myopia using spectral-domain optical coherence tomography (OCT). This retrospective cross-sectional study included 690 eyes in 492 patients with OCT images and axial length measurement. Eyes were divid...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Kyung Jun Choi, Jung Eun Choi, Hyeon Cheol Roh, Jun Soo Eun, Jong Min Kim, Yong Kyun Shin, Min Chae Kang, Joon Kyo Chung, Chaeyeon Lee, Dongyoung Lee, Se Woong Kang, Baek Hwan Cho, Sang Jin Kim
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/5a2f8fb3c9c24baa96e29995bceba8ee
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5a2f8fb3c9c24baa96e29995bceba8ee
record_format	dspace
spelling	oai:doaj.org-article:5a2f8fb3c9c24baa96e29995bceba8ee2021-11-08T10:55:55ZDeep learning models for screening of high myopia using optical coherence tomography10.1038/s41598-021-00622-x2045-2322https://doaj.org/article/5a2f8fb3c9c24baa96e29995bceba8ee2021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-00622-xhttps://doaj.org/toc/2045-2322Abstract This study aimed to validate and evaluate deep learning (DL) models for screening of high myopia using spectral-domain optical coherence tomography (OCT). This retrospective cross-sectional study included 690 eyes in 492 patients with OCT images and axial length measurement. Eyes were divided into three groups based on axial length: a “normal group,” a “high myopia group,” and an “other retinal disease” group. The researchers trained and validated three DL models to classify the three groups based on horizontal and vertical OCT images of the 600 eyes. For evaluation, OCT images of 90 eyes were used. Diagnostic agreements of human doctors and DL models were analyzed. The area under the receiver operating characteristic curve of the three DL models was evaluated. Absolute agreement of retina specialists was 99.11% (range: 97.78–100%). Absolute agreement of the DL models with multiple-column model was 100.0% (ResNet 50), 90.0% (Inception V3), and 72.22% (VGG 16). Areas under the receiver operating characteristic curves of the DL models with multiple-column model were 0.99 (ResNet 50), 0.97 (Inception V3), and 0.86 (VGG 16). The DL model based on ResNet 50 showed comparable diagnostic performance with retinal specialists. The DL model using OCT images demonstrated reliable diagnostic performance to identify high myopia.Kyung Jun ChoiJung Eun ChoiHyeon Cheol RohJun Soo EunJong Min KimYong Kyun ShinMin Chae KangJoon Kyo ChungChaeyeon LeeDongyoung LeeSe Woong KangBaek Hwan ChoSang Jin KimNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Kyung Jun Choi Jung Eun Choi Hyeon Cheol Roh Jun Soo Eun Jong Min Kim Yong Kyun Shin Min Chae Kang Joon Kyo Chung Chaeyeon Lee Dongyoung Lee Se Woong Kang Baek Hwan Cho Sang Jin Kim Deep learning models for screening of high myopia using optical coherence tomography
description	Abstract This study aimed to validate and evaluate deep learning (DL) models for screening of high myopia using spectral-domain optical coherence tomography (OCT). This retrospective cross-sectional study included 690 eyes in 492 patients with OCT images and axial length measurement. Eyes were divided into three groups based on axial length: a “normal group,” a “high myopia group,” and an “other retinal disease” group. The researchers trained and validated three DL models to classify the three groups based on horizontal and vertical OCT images of the 600 eyes. For evaluation, OCT images of 90 eyes were used. Diagnostic agreements of human doctors and DL models were analyzed. The area under the receiver operating characteristic curve of the three DL models was evaluated. Absolute agreement of retina specialists was 99.11% (range: 97.78–100%). Absolute agreement of the DL models with multiple-column model was 100.0% (ResNet 50), 90.0% (Inception V3), and 72.22% (VGG 16). Areas under the receiver operating characteristic curves of the DL models with multiple-column model were 0.99 (ResNet 50), 0.97 (Inception V3), and 0.86 (VGG 16). The DL model based on ResNet 50 showed comparable diagnostic performance with retinal specialists. The DL model using OCT images demonstrated reliable diagnostic performance to identify high myopia.
format	article
author	Kyung Jun Choi Jung Eun Choi Hyeon Cheol Roh Jun Soo Eun Jong Min Kim Yong Kyun Shin Min Chae Kang Joon Kyo Chung Chaeyeon Lee Dongyoung Lee Se Woong Kang Baek Hwan Cho Sang Jin Kim
author_facet	Kyung Jun Choi Jung Eun Choi Hyeon Cheol Roh Jun Soo Eun Jong Min Kim Yong Kyun Shin Min Chae Kang Joon Kyo Chung Chaeyeon Lee Dongyoung Lee Se Woong Kang Baek Hwan Cho Sang Jin Kim
author_sort	Kyung Jun Choi
title	Deep learning models for screening of high myopia using optical coherence tomography
title_short	Deep learning models for screening of high myopia using optical coherence tomography
title_full	Deep learning models for screening of high myopia using optical coherence tomography
title_fullStr	Deep learning models for screening of high myopia using optical coherence tomography
title_full_unstemmed	Deep learning models for screening of high myopia using optical coherence tomography
title_sort	deep learning models for screening of high myopia using optical coherence tomography
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/5a2f8fb3c9c24baa96e29995bceba8ee
work_keys_str_mv	AT kyungjunchoi deeplearningmodelsforscreeningofhighmyopiausingopticalcoherencetomography AT jungeunchoi deeplearningmodelsforscreeningofhighmyopiausingopticalcoherencetomography AT hyeoncheolroh deeplearningmodelsforscreeningofhighmyopiausingopticalcoherencetomography AT junsooeun deeplearningmodelsforscreeningofhighmyopiausingopticalcoherencetomography AT jongminkim deeplearningmodelsforscreeningofhighmyopiausingopticalcoherencetomography AT yongkyunshin deeplearningmodelsforscreeningofhighmyopiausingopticalcoherencetomography AT minchaekang deeplearningmodelsforscreeningofhighmyopiausingopticalcoherencetomography AT joonkyochung deeplearningmodelsforscreeningofhighmyopiausingopticalcoherencetomography AT chaeyeonlee deeplearningmodelsforscreeningofhighmyopiausingopticalcoherencetomography AT dongyounglee deeplearningmodelsforscreeningofhighmyopiausingopticalcoherencetomography AT sewoongkang deeplearningmodelsforscreeningofhighmyopiausingopticalcoherencetomography AT baekhwancho deeplearningmodelsforscreeningofhighmyopiausingopticalcoherencetomography AT sangjinkim deeplearningmodelsforscreeningofhighmyopiausingopticalcoherencetomography
_version_	1718442524131983360

Deep learning models for screening of high myopia using optical coherence tomography

Ejemplares similares