Cargando…

Development of a Fundus Image-Based Deep Learning Diagnostic Tool for Various Retinal Diseases

Artificial intelligence (AI)-based diagnostic tools have been accepted in ophthalmology. The use of retinal images, such as fundus photographs, is a promising approach for the development of AI-based diagnostic platforms. Retinal pathologies usually occur in a broad spectrum of eye diseases, includi...

Descripción completa

Detalles Bibliográficos
Autores principales: Kim, Kyoung Min, Heo, Tae-Young, Kim, Aesul, Kim, Joohee, Han, Kyu Jin, Yun, Jaesuk, Min, Jung Kee
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8142986/
https://www.ncbi.nlm.nih.gov/pubmed/33918998
http://dx.doi.org/10.3390/jpm11050321
_version_ 1783696662067150848
author Kim, Kyoung Min
Heo, Tae-Young
Kim, Aesul
Kim, Joohee
Han, Kyu Jin
Yun, Jaesuk
Min, Jung Kee
author_facet Kim, Kyoung Min
Heo, Tae-Young
Kim, Aesul
Kim, Joohee
Han, Kyu Jin
Yun, Jaesuk
Min, Jung Kee
author_sort Kim, Kyoung Min
collection PubMed
description Artificial intelligence (AI)-based diagnostic tools have been accepted in ophthalmology. The use of retinal images, such as fundus photographs, is a promising approach for the development of AI-based diagnostic platforms. Retinal pathologies usually occur in a broad spectrum of eye diseases, including neovascular or dry age-related macular degeneration, epiretinal membrane, rhegmatogenous retinal detachment, retinitis pigmentosa, macular hole, retinal vein occlusions, and diabetic retinopathy. Here, we report a fundus image-based AI model for differential diagnosis of retinal diseases. We classified retinal images with three convolutional neural network models: ResNet50, VGG19, and Inception v3. Furthermore, the performance of several dense (fully connected) layers was compared. The prediction accuracy for diagnosis of nine classes of eight retinal diseases and normal control was 87.42% in the ResNet50 model, which added a dense layer with 128 nodes. Furthermore, our AI tool augments ophthalmologist’s performance in the diagnosis of retinal disease. These results suggested that the fundus image-based AI tool is applicable for the medical diagnosis process of retinal diseases.
format Online
Article
Text
id pubmed-8142986
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-81429862021-05-25 Development of a Fundus Image-Based Deep Learning Diagnostic Tool for Various Retinal Diseases Kim, Kyoung Min Heo, Tae-Young Kim, Aesul Kim, Joohee Han, Kyu Jin Yun, Jaesuk Min, Jung Kee J Pers Med Article Artificial intelligence (AI)-based diagnostic tools have been accepted in ophthalmology. The use of retinal images, such as fundus photographs, is a promising approach for the development of AI-based diagnostic platforms. Retinal pathologies usually occur in a broad spectrum of eye diseases, including neovascular or dry age-related macular degeneration, epiretinal membrane, rhegmatogenous retinal detachment, retinitis pigmentosa, macular hole, retinal vein occlusions, and diabetic retinopathy. Here, we report a fundus image-based AI model for differential diagnosis of retinal diseases. We classified retinal images with three convolutional neural network models: ResNet50, VGG19, and Inception v3. Furthermore, the performance of several dense (fully connected) layers was compared. The prediction accuracy for diagnosis of nine classes of eight retinal diseases and normal control was 87.42% in the ResNet50 model, which added a dense layer with 128 nodes. Furthermore, our AI tool augments ophthalmologist’s performance in the diagnosis of retinal disease. These results suggested that the fundus image-based AI tool is applicable for the medical diagnosis process of retinal diseases. MDPI 2021-04-21 /pmc/articles/PMC8142986/ /pubmed/33918998 http://dx.doi.org/10.3390/jpm11050321 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kim, Kyoung Min
Heo, Tae-Young
Kim, Aesul
Kim, Joohee
Han, Kyu Jin
Yun, Jaesuk
Min, Jung Kee
Development of a Fundus Image-Based Deep Learning Diagnostic Tool for Various Retinal Diseases
title Development of a Fundus Image-Based Deep Learning Diagnostic Tool for Various Retinal Diseases
title_full Development of a Fundus Image-Based Deep Learning Diagnostic Tool for Various Retinal Diseases
title_fullStr Development of a Fundus Image-Based Deep Learning Diagnostic Tool for Various Retinal Diseases
title_full_unstemmed Development of a Fundus Image-Based Deep Learning Diagnostic Tool for Various Retinal Diseases
title_short Development of a Fundus Image-Based Deep Learning Diagnostic Tool for Various Retinal Diseases
title_sort development of a fundus image-based deep learning diagnostic tool for various retinal diseases
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8142986/
https://www.ncbi.nlm.nih.gov/pubmed/33918998
http://dx.doi.org/10.3390/jpm11050321
work_keys_str_mv AT kimkyoungmin developmentofafundusimagebaseddeeplearningdiagnostictoolforvariousretinaldiseases
AT heotaeyoung developmentofafundusimagebaseddeeplearningdiagnostictoolforvariousretinaldiseases
AT kimaesul developmentofafundusimagebaseddeeplearningdiagnostictoolforvariousretinaldiseases
AT kimjoohee developmentofafundusimagebaseddeeplearningdiagnostictoolforvariousretinaldiseases
AT hankyujin developmentofafundusimagebaseddeeplearningdiagnostictoolforvariousretinaldiseases
AT yunjaesuk developmentofafundusimagebaseddeeplearningdiagnostictoolforvariousretinaldiseases
AT minjungkee developmentofafundusimagebaseddeeplearningdiagnostictoolforvariousretinaldiseases