Cargando…

An Assistive Role of a Machine Learning Network in Diagnosis of Middle Ear Diseases

The present study aimed to develop a machine learning network to diagnose middle ear diseases with tympanic membrane images and to identify its assistive role in the diagnostic process. The medical records of subjects who underwent ear endoscopy tests were reviewed. From these records, 2272 diagnost...

Descripción completa

Detalles Bibliográficos
Autores principales: Byun, Hayoung, Yu, Sangjoon, Oh, Jaehoon, Bae, Junwon, Yoon, Myeong Seong, Lee, Seung Hwan, Chung, Jae Ho, Kim, Tae Hyun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8347824/
https://www.ncbi.nlm.nih.gov/pubmed/34361982
http://dx.doi.org/10.3390/jcm10153198
_version_ 1783735188250951680
author Byun, Hayoung
Yu, Sangjoon
Oh, Jaehoon
Bae, Junwon
Yoon, Myeong Seong
Lee, Seung Hwan
Chung, Jae Ho
Kim, Tae Hyun
author_facet Byun, Hayoung
Yu, Sangjoon
Oh, Jaehoon
Bae, Junwon
Yoon, Myeong Seong
Lee, Seung Hwan
Chung, Jae Ho
Kim, Tae Hyun
author_sort Byun, Hayoung
collection PubMed
description The present study aimed to develop a machine learning network to diagnose middle ear diseases with tympanic membrane images and to identify its assistive role in the diagnostic process. The medical records of subjects who underwent ear endoscopy tests were reviewed. From these records, 2272 diagnostic tympanic membranes images were appropriately labeled as normal, otitis media with effusion (OME), chronic otitis media (COM), or cholesteatoma and were used for training. We developed the “ResNet18 + Shuffle” network and validated the model performance. Seventy-one representative cases were selected to test the final accuracy of the network and resident physicians. We asked 10 resident physicians to make diagnoses from tympanic membrane images with and without the help of the machine learning network, and the change of the diagnostic performance of resident physicians with the aid of the answers from the machine learning network was assessed. The devised network showed a highest accuracy of 97.18%. A five-fold validation showed that the network successfully diagnosed ear diseases with an accuracy greater than 93%. All resident physicians were able to diagnose middle ear diseases more accurately with the help of the machine learning network. The increase in diagnostic accuracy was up to 18% (1.4% to 18.4%). The machine learning network successfully classified middle ear diseases and was assistive to clinicians in the interpretation of tympanic membrane images.
format Online
Article
Text
id pubmed-8347824
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83478242021-08-08 An Assistive Role of a Machine Learning Network in Diagnosis of Middle Ear Diseases Byun, Hayoung Yu, Sangjoon Oh, Jaehoon Bae, Junwon Yoon, Myeong Seong Lee, Seung Hwan Chung, Jae Ho Kim, Tae Hyun J Clin Med Article The present study aimed to develop a machine learning network to diagnose middle ear diseases with tympanic membrane images and to identify its assistive role in the diagnostic process. The medical records of subjects who underwent ear endoscopy tests were reviewed. From these records, 2272 diagnostic tympanic membranes images were appropriately labeled as normal, otitis media with effusion (OME), chronic otitis media (COM), or cholesteatoma and were used for training. We developed the “ResNet18 + Shuffle” network and validated the model performance. Seventy-one representative cases were selected to test the final accuracy of the network and resident physicians. We asked 10 resident physicians to make diagnoses from tympanic membrane images with and without the help of the machine learning network, and the change of the diagnostic performance of resident physicians with the aid of the answers from the machine learning network was assessed. The devised network showed a highest accuracy of 97.18%. A five-fold validation showed that the network successfully diagnosed ear diseases with an accuracy greater than 93%. All resident physicians were able to diagnose middle ear diseases more accurately with the help of the machine learning network. The increase in diagnostic accuracy was up to 18% (1.4% to 18.4%). The machine learning network successfully classified middle ear diseases and was assistive to clinicians in the interpretation of tympanic membrane images. MDPI 2021-07-21 /pmc/articles/PMC8347824/ /pubmed/34361982 http://dx.doi.org/10.3390/jcm10153198 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
Byun, Hayoung
Yu, Sangjoon
Oh, Jaehoon
Bae, Junwon
Yoon, Myeong Seong
Lee, Seung Hwan
Chung, Jae Ho
Kim, Tae Hyun
An Assistive Role of a Machine Learning Network in Diagnosis of Middle Ear Diseases
title An Assistive Role of a Machine Learning Network in Diagnosis of Middle Ear Diseases
title_full An Assistive Role of a Machine Learning Network in Diagnosis of Middle Ear Diseases
title_fullStr An Assistive Role of a Machine Learning Network in Diagnosis of Middle Ear Diseases
title_full_unstemmed An Assistive Role of a Machine Learning Network in Diagnosis of Middle Ear Diseases
title_short An Assistive Role of a Machine Learning Network in Diagnosis of Middle Ear Diseases
title_sort assistive role of a machine learning network in diagnosis of middle ear diseases
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8347824/
https://www.ncbi.nlm.nih.gov/pubmed/34361982
http://dx.doi.org/10.3390/jcm10153198
work_keys_str_mv AT byunhayoung anassistiveroleofamachinelearningnetworkindiagnosisofmiddleeardiseases
AT yusangjoon anassistiveroleofamachinelearningnetworkindiagnosisofmiddleeardiseases
AT ohjaehoon anassistiveroleofamachinelearningnetworkindiagnosisofmiddleeardiseases
AT baejunwon anassistiveroleofamachinelearningnetworkindiagnosisofmiddleeardiseases
AT yoonmyeongseong anassistiveroleofamachinelearningnetworkindiagnosisofmiddleeardiseases
AT leeseunghwan anassistiveroleofamachinelearningnetworkindiagnosisofmiddleeardiseases
AT chungjaeho anassistiveroleofamachinelearningnetworkindiagnosisofmiddleeardiseases
AT kimtaehyun anassistiveroleofamachinelearningnetworkindiagnosisofmiddleeardiseases
AT byunhayoung assistiveroleofamachinelearningnetworkindiagnosisofmiddleeardiseases
AT yusangjoon assistiveroleofamachinelearningnetworkindiagnosisofmiddleeardiseases
AT ohjaehoon assistiveroleofamachinelearningnetworkindiagnosisofmiddleeardiseases
AT baejunwon assistiveroleofamachinelearningnetworkindiagnosisofmiddleeardiseases
AT yoonmyeongseong assistiveroleofamachinelearningnetworkindiagnosisofmiddleeardiseases
AT leeseunghwan assistiveroleofamachinelearningnetworkindiagnosisofmiddleeardiseases
AT chungjaeho assistiveroleofamachinelearningnetworkindiagnosisofmiddleeardiseases
AT kimtaehyun assistiveroleofamachinelearningnetworkindiagnosisofmiddleeardiseases