A deep learning model for identifying diabetic retinopathy using optical coherence tomography angiography

Abstract As the prevalence of diabetes increases, millions of people need to be screened for diabetic retinopathy (DR). Remarkable advances in technology have made it possible to use artificial intelligence to screen DR from retinal images with high accuracy and reliability, resulting in reducing hu...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Gahyung Ryu, Kyungmin Lee, Donggeun Park, Sang Hyun Park, Min Sagong
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/ff73611e942b4f6ba17d9ea59c8045d2
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:ff73611e942b4f6ba17d9ea59c8045d2
record_format dspace
spelling oai:doaj.org-article:ff73611e942b4f6ba17d9ea59c8045d22021-11-28T12:17:14ZA deep learning model for identifying diabetic retinopathy using optical coherence tomography angiography10.1038/s41598-021-02479-62045-2322https://doaj.org/article/ff73611e942b4f6ba17d9ea59c8045d22021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-02479-6https://doaj.org/toc/2045-2322Abstract As the prevalence of diabetes increases, millions of people need to be screened for diabetic retinopathy (DR). Remarkable advances in technology have made it possible to use artificial intelligence to screen DR from retinal images with high accuracy and reliability, resulting in reducing human labor by processing large amounts of data in a shorter time. We developed a fully automated classification algorithm to diagnose DR and identify referable status using optical coherence tomography angiography (OCTA) images with convolutional neural network (CNN) model and verified its feasibility by comparing its performance with that of conventional machine learning model. Ground truths for classifications were made based on ultra-widefield fluorescein angiography to increase the accuracy of data annotation. The proposed CNN classifier achieved an accuracy of 91–98%, a sensitivity of 86–97%, a specificity of 94–99%, and an area under the curve of 0.919–0.976. In the external validation, overall similar performances were also achieved. The results were similar regardless of the size and depth of the OCTA images, indicating that DR could be satisfactorily classified even with images comprising narrow area of the macular region and a single image slab of retina. The CNN-based classification using OCTA is expected to create a novel diagnostic workflow for DR detection and referral.Gahyung RyuKyungmin LeeDonggeun ParkSang Hyun ParkMin SagongNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Gahyung Ryu
Kyungmin Lee
Donggeun Park
Sang Hyun Park
Min Sagong
A deep learning model for identifying diabetic retinopathy using optical coherence tomography angiography
description Abstract As the prevalence of diabetes increases, millions of people need to be screened for diabetic retinopathy (DR). Remarkable advances in technology have made it possible to use artificial intelligence to screen DR from retinal images with high accuracy and reliability, resulting in reducing human labor by processing large amounts of data in a shorter time. We developed a fully automated classification algorithm to diagnose DR and identify referable status using optical coherence tomography angiography (OCTA) images with convolutional neural network (CNN) model and verified its feasibility by comparing its performance with that of conventional machine learning model. Ground truths for classifications were made based on ultra-widefield fluorescein angiography to increase the accuracy of data annotation. The proposed CNN classifier achieved an accuracy of 91–98%, a sensitivity of 86–97%, a specificity of 94–99%, and an area under the curve of 0.919–0.976. In the external validation, overall similar performances were also achieved. The results were similar regardless of the size and depth of the OCTA images, indicating that DR could be satisfactorily classified even with images comprising narrow area of the macular region and a single image slab of retina. The CNN-based classification using OCTA is expected to create a novel diagnostic workflow for DR detection and referral.
format article
author Gahyung Ryu
Kyungmin Lee
Donggeun Park
Sang Hyun Park
Min Sagong
author_facet Gahyung Ryu
Kyungmin Lee
Donggeun Park
Sang Hyun Park
Min Sagong
author_sort Gahyung Ryu
title A deep learning model for identifying diabetic retinopathy using optical coherence tomography angiography
title_short A deep learning model for identifying diabetic retinopathy using optical coherence tomography angiography
title_full A deep learning model for identifying diabetic retinopathy using optical coherence tomography angiography
title_fullStr A deep learning model for identifying diabetic retinopathy using optical coherence tomography angiography
title_full_unstemmed A deep learning model for identifying diabetic retinopathy using optical coherence tomography angiography
title_sort deep learning model for identifying diabetic retinopathy using optical coherence tomography angiography
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/ff73611e942b4f6ba17d9ea59c8045d2
work_keys_str_mv AT gahyungryu adeeplearningmodelforidentifyingdiabeticretinopathyusingopticalcoherencetomographyangiography
AT kyungminlee adeeplearningmodelforidentifyingdiabeticretinopathyusingopticalcoherencetomographyangiography
AT donggeunpark adeeplearningmodelforidentifyingdiabeticretinopathyusingopticalcoherencetomographyangiography
AT sanghyunpark adeeplearningmodelforidentifyingdiabeticretinopathyusingopticalcoherencetomographyangiography
AT minsagong adeeplearningmodelforidentifyingdiabeticretinopathyusingopticalcoherencetomographyangiography
AT gahyungryu deeplearningmodelforidentifyingdiabeticretinopathyusingopticalcoherencetomographyangiography
AT kyungminlee deeplearningmodelforidentifyingdiabeticretinopathyusingopticalcoherencetomographyangiography
AT donggeunpark deeplearningmodelforidentifyingdiabeticretinopathyusingopticalcoherencetomographyangiography
AT sanghyunpark deeplearningmodelforidentifyingdiabeticretinopathyusingopticalcoherencetomographyangiography
AT minsagong deeplearningmodelforidentifyingdiabeticretinopathyusingopticalcoherencetomographyangiography
_version_ 1718408117411119104