Using deep learning to predict temporomandibular joint disc perforation based on magnetic resonance imaging

Abstract The goal of this study was to develop a deep learning-based algorithm to predict temporomandibular joint (TMJ) disc perforation based on the findings of magnetic resonance imaging (MRI) and to validate its performance through comparison with previously reported results. The study objects we...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jae-Young Kim, Dongwook Kim, Kug Jin Jeon, Hwiyoung Kim, Jong-Ki Huh
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/0c831ad0ec5346e79d1d58c39859400a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0c831ad0ec5346e79d1d58c39859400a
record_format	dspace
spelling	oai:doaj.org-article:0c831ad0ec5346e79d1d58c39859400a2021-12-02T17:04:36ZUsing deep learning to predict temporomandibular joint disc perforation based on magnetic resonance imaging10.1038/s41598-021-86115-32045-2322https://doaj.org/article/0c831ad0ec5346e79d1d58c39859400a2021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-86115-3https://doaj.org/toc/2045-2322Abstract The goal of this study was to develop a deep learning-based algorithm to predict temporomandibular joint (TMJ) disc perforation based on the findings of magnetic resonance imaging (MRI) and to validate its performance through comparison with previously reported results. The study objects were obtained by reviewing medical records from January 2005 to June 2018. 299 joints from 289 patients were divided into perforated and non-perforated groups based on the existence of disc perforation confirmed during surgery. Experienced observers interpreted the TMJ MRI images to extract features. Data containing those features were applied to build and validate prediction models using random forest and multilayer perceptron (MLP) techniques, the latter using the Keras framework, a recent deep learning architecture. The area under the receiver operating characteristic (ROC) curve (AUC) was used to compare the performances of the models. MLP produced the best performance (AUC 0.940), followed by random forest (AUC 0.918) and disc shape alone (AUC 0.791). The MLP and random forest were also superior to previously reported results using MRI (AUC 0.808) and MRI-based nomogram (AUC 0.889). Implementing deep learning showed superior performance in predicting disc perforation in TMJ compared to conventional methods and previous reports.Jae-Young KimDongwook KimKug Jin JeonHwiyoung KimJong-Ki HuhNature 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 Jae-Young Kim Dongwook Kim Kug Jin Jeon Hwiyoung Kim Jong-Ki Huh Using deep learning to predict temporomandibular joint disc perforation based on magnetic resonance imaging
description	Abstract The goal of this study was to develop a deep learning-based algorithm to predict temporomandibular joint (TMJ) disc perforation based on the findings of magnetic resonance imaging (MRI) and to validate its performance through comparison with previously reported results. The study objects were obtained by reviewing medical records from January 2005 to June 2018. 299 joints from 289 patients were divided into perforated and non-perforated groups based on the existence of disc perforation confirmed during surgery. Experienced observers interpreted the TMJ MRI images to extract features. Data containing those features were applied to build and validate prediction models using random forest and multilayer perceptron (MLP) techniques, the latter using the Keras framework, a recent deep learning architecture. The area under the receiver operating characteristic (ROC) curve (AUC) was used to compare the performances of the models. MLP produced the best performance (AUC 0.940), followed by random forest (AUC 0.918) and disc shape alone (AUC 0.791). The MLP and random forest were also superior to previously reported results using MRI (AUC 0.808) and MRI-based nomogram (AUC 0.889). Implementing deep learning showed superior performance in predicting disc perforation in TMJ compared to conventional methods and previous reports.
format	article
author	Jae-Young Kim Dongwook Kim Kug Jin Jeon Hwiyoung Kim Jong-Ki Huh
author_facet	Jae-Young Kim Dongwook Kim Kug Jin Jeon Hwiyoung Kim Jong-Ki Huh
author_sort	Jae-Young Kim
title	Using deep learning to predict temporomandibular joint disc perforation based on magnetic resonance imaging
title_short	Using deep learning to predict temporomandibular joint disc perforation based on magnetic resonance imaging
title_full	Using deep learning to predict temporomandibular joint disc perforation based on magnetic resonance imaging
title_fullStr	Using deep learning to predict temporomandibular joint disc perforation based on magnetic resonance imaging
title_full_unstemmed	Using deep learning to predict temporomandibular joint disc perforation based on magnetic resonance imaging
title_sort	using deep learning to predict temporomandibular joint disc perforation based on magnetic resonance imaging
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/0c831ad0ec5346e79d1d58c39859400a
work_keys_str_mv	AT jaeyoungkim usingdeeplearningtopredicttemporomandibularjointdiscperforationbasedonmagneticresonanceimaging AT dongwookkim usingdeeplearningtopredicttemporomandibularjointdiscperforationbasedonmagneticresonanceimaging AT kugjinjeon usingdeeplearningtopredicttemporomandibularjointdiscperforationbasedonmagneticresonanceimaging AT hwiyoungkim usingdeeplearningtopredicttemporomandibularjointdiscperforationbasedonmagneticresonanceimaging AT jongkihuh usingdeeplearningtopredicttemporomandibularjointdiscperforationbasedonmagneticresonanceimaging
_version_	1718381832072855552

Using deep learning to predict temporomandibular joint disc perforation based on magnetic resonance imaging

Ejemplares similares