Comparison of Autonomous AS-OCT Deep Learning Algorithm and Clinical Dry Eye Tests in Diagnosis of Dry Eye Disease

Collin Chase,1 Amr Elsawy,2 Taher Eleiwa,3 Eyup Ozcan,4 Mohamed Tolba,2 Mohamed Abou Shousha2 1Morsani College of Medicine, University of South Florida, Tampa, FL, USA; 2Cornea Department, Bascom Palmer Eye Institute, Miller School of Medicine, University of Miami, Miami, FL, USA; 3Department of Oph...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Chase C, Elsawy A, Eleiwa T, Ozcan E, Tolba M, Abou Shousha M
Formato:	article
Lenguaje:	EN
Publicado:	Dove Medical Press 2021
Materias:	dry eye disease artificial intelligence optical coherence tomography Ophthalmology RE1-994
Acceso en línea:	https://doaj.org/article/cf9b8e9baa154d3f9f79a9b37139f575
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:cf9b8e9baa154d3f9f79a9b37139f575
record_format	dspace
spelling	oai:doaj.org-article:cf9b8e9baa154d3f9f79a9b37139f5752021-12-02T19:26:56ZComparison of Autonomous AS-OCT Deep Learning Algorithm and Clinical Dry Eye Tests in Diagnosis of Dry Eye Disease1177-5483https://doaj.org/article/cf9b8e9baa154d3f9f79a9b37139f5752021-10-01T00:00:00Zhttps://www.dovepress.com/comparison-of-autonomous-as-oct-deep-learning-algorithm-and-clinical-d-peer-reviewed-fulltext-article-OPTHhttps://doaj.org/toc/1177-5483Collin Chase,1 Amr Elsawy,2 Taher Eleiwa,3 Eyup Ozcan,4 Mohamed Tolba,2 Mohamed Abou Shousha2 1Morsani College of Medicine, University of South Florida, Tampa, FL, USA; 2Cornea Department, Bascom Palmer Eye Institute, Miller School of Medicine, University of Miami, Miami, FL, USA; 3Department of Ophthalmology, Faculty of Medicine, Benha University, Benha, Egypt; 4Department of Ophthalmology, Net Eye Medical Center, Gaziantep, TurkeyCorrespondence: Mohamed Abou ShoushaCornea Department, Bascom Palmer Eye Institute, Miller School of Medicine, University of Miami, 900 NW 17th Street, Miami, FL, 33136, USATel +1 305-326-6000Email Mshousha@med.miami.eduObjective: To evaluate a deep learning-based method to autonomously detect dry eye disease (DED) in anterior segment optical coherence tomography (AS-OCT) images compared to common clinical dry eye tests.Methods: In this study, 27,180 AS-OCT images were prospectively collected from 151 eyes of 91 patients. Images were used to train and test the deep learning model. Masked cornea specialist ophthalmologist diagnoses were used as the gold standard. Clinical dry eye tests were performed on patients in the DED group to compare the results of the model. The dry eye tests performed were tear break-up time (TBUT), Schirmer’s test, corneal staining, conjunctival staining, and Ocular Surface Disease Index (OSDI).Results: Our deep learning model achieved an accuracy of 84.62%, sensitivity of 86.36%, and specificity of 82.35% in the diagnosis of DED. The positive likelihood ratio was 4.89, and the negative likelihood ratio was 0.17. The mean DED probability score was 0.81 ± 0.23 in the DED group and 0.20 ± 0.27 in the healthy group (P < 0.01). The deep learning model accuracy in the diagnosis of DED was significantly better than that of corneal staining, conjunctival staining, and Schirmer’s test (P < 0.05). There was no significant difference between the deep learning diagnostic accuracy and that of the OSDI and TBUT.Conclusion: Based on preliminary results, reliable autonomous diagnosis of DED with our deep learning model was achieved, when compared with standard dry eye clinical tests that correlated significantly more or similarly to diagnoses made by cornea specialist ophthalmologists.Keywords: dry eye disease, artificial intelligence, optical coherence tomographyChase CElsawy AEleiwa TOzcan ETolba MAbou Shousha MDove Medical Pressarticledry eye diseaseartificial intelligenceoptical coherence tomographyOphthalmologyRE1-994ENClinical Ophthalmology, Vol Volume 15, Pp 4281-4289 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	dry eye disease artificial intelligence optical coherence tomography Ophthalmology RE1-994
spellingShingle	dry eye disease artificial intelligence optical coherence tomography Ophthalmology RE1-994 Chase C Elsawy A Eleiwa T Ozcan E Tolba M Abou Shousha M Comparison of Autonomous AS-OCT Deep Learning Algorithm and Clinical Dry Eye Tests in Diagnosis of Dry Eye Disease
description	Collin Chase,1 Amr Elsawy,2 Taher Eleiwa,3 Eyup Ozcan,4 Mohamed Tolba,2 Mohamed Abou Shousha2 1Morsani College of Medicine, University of South Florida, Tampa, FL, USA; 2Cornea Department, Bascom Palmer Eye Institute, Miller School of Medicine, University of Miami, Miami, FL, USA; 3Department of Ophthalmology, Faculty of Medicine, Benha University, Benha, Egypt; 4Department of Ophthalmology, Net Eye Medical Center, Gaziantep, TurkeyCorrespondence: Mohamed Abou ShoushaCornea Department, Bascom Palmer Eye Institute, Miller School of Medicine, University of Miami, 900 NW 17th Street, Miami, FL, 33136, USATel +1 305-326-6000Email Mshousha@med.miami.eduObjective: To evaluate a deep learning-based method to autonomously detect dry eye disease (DED) in anterior segment optical coherence tomography (AS-OCT) images compared to common clinical dry eye tests.Methods: In this study, 27,180 AS-OCT images were prospectively collected from 151 eyes of 91 patients. Images were used to train and test the deep learning model. Masked cornea specialist ophthalmologist diagnoses were used as the gold standard. Clinical dry eye tests were performed on patients in the DED group to compare the results of the model. The dry eye tests performed were tear break-up time (TBUT), Schirmer’s test, corneal staining, conjunctival staining, and Ocular Surface Disease Index (OSDI).Results: Our deep learning model achieved an accuracy of 84.62%, sensitivity of 86.36%, and specificity of 82.35% in the diagnosis of DED. The positive likelihood ratio was 4.89, and the negative likelihood ratio was 0.17. The mean DED probability score was 0.81 ± 0.23 in the DED group and 0.20 ± 0.27 in the healthy group (P < 0.01). The deep learning model accuracy in the diagnosis of DED was significantly better than that of corneal staining, conjunctival staining, and Schirmer’s test (P < 0.05). There was no significant difference between the deep learning diagnostic accuracy and that of the OSDI and TBUT.Conclusion: Based on preliminary results, reliable autonomous diagnosis of DED with our deep learning model was achieved, when compared with standard dry eye clinical tests that correlated significantly more or similarly to diagnoses made by cornea specialist ophthalmologists.Keywords: dry eye disease, artificial intelligence, optical coherence tomography
format	article
author	Chase C Elsawy A Eleiwa T Ozcan E Tolba M Abou Shousha M
author_facet	Chase C Elsawy A Eleiwa T Ozcan E Tolba M Abou Shousha M
author_sort	Chase C
title	Comparison of Autonomous AS-OCT Deep Learning Algorithm and Clinical Dry Eye Tests in Diagnosis of Dry Eye Disease
title_short	Comparison of Autonomous AS-OCT Deep Learning Algorithm and Clinical Dry Eye Tests in Diagnosis of Dry Eye Disease
title_full	Comparison of Autonomous AS-OCT Deep Learning Algorithm and Clinical Dry Eye Tests in Diagnosis of Dry Eye Disease
title_fullStr	Comparison of Autonomous AS-OCT Deep Learning Algorithm and Clinical Dry Eye Tests in Diagnosis of Dry Eye Disease
title_full_unstemmed	Comparison of Autonomous AS-OCT Deep Learning Algorithm and Clinical Dry Eye Tests in Diagnosis of Dry Eye Disease
title_sort	comparison of autonomous as-oct deep learning algorithm and clinical dry eye tests in diagnosis of dry eye disease
publisher	Dove Medical Press
publishDate	2021
url	https://doaj.org/article/cf9b8e9baa154d3f9f79a9b37139f575
work_keys_str_mv	AT chasec comparisonofautonomousasoctdeeplearningalgorithmandclinicaldryeyetestsindiagnosisofdryeyedisease AT elsawya comparisonofautonomousasoctdeeplearningalgorithmandclinicaldryeyetestsindiagnosisofdryeyedisease AT eleiwat comparisonofautonomousasoctdeeplearningalgorithmandclinicaldryeyetestsindiagnosisofdryeyedisease AT ozcane comparisonofautonomousasoctdeeplearningalgorithmandclinicaldryeyetestsindiagnosisofdryeyedisease AT tolbam comparisonofautonomousasoctdeeplearningalgorithmandclinicaldryeyetestsindiagnosisofdryeyedisease AT aboushousham comparisonofautonomousasoctdeeplearningalgorithmandclinicaldryeyetestsindiagnosisofdryeyedisease
_version_	1718376526102134784

Comparison of Autonomous AS-OCT Deep Learning Algorithm and Clinical Dry Eye Tests in Diagnosis of Dry Eye Disease

Ejemplares similares