Deep learning for early dental caries detection in bitewing radiographs

Abstract The early detection of initial dental caries enables preventive treatment, and bitewing radiography is a good diagnostic tool for posterior initial caries. In medical imaging, the utilization of deep learning with convolutional neural networks (CNNs) to process various types of images has b...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shinae Lee, Sang-il Oh, Junik Jo, Sumi Kang, Yooseok Shin, Jeong-won Park
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/c0171c20667a4e448a01dbd9f8246ed4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c0171c20667a4e448a01dbd9f8246ed4
record_format	dspace
spelling	oai:doaj.org-article:c0171c20667a4e448a01dbd9f8246ed42021-12-02T17:08:23ZDeep learning for early dental caries detection in bitewing radiographs10.1038/s41598-021-96368-72045-2322https://doaj.org/article/c0171c20667a4e448a01dbd9f8246ed42021-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-96368-7https://doaj.org/toc/2045-2322Abstract The early detection of initial dental caries enables preventive treatment, and bitewing radiography is a good diagnostic tool for posterior initial caries. In medical imaging, the utilization of deep learning with convolutional neural networks (CNNs) to process various types of images has been actively researched, with promising performance. In this study, we developed a CNN model using a U-shaped deep CNN (U-Net) for caries detection on bitewing radiographs and investigated whether this model can improve clinicians’ performance. The research complied with relevant ethical regulations. In total, 304 bitewing radiographs were used to train the CNN model and 50 radiographs for performance evaluation. The diagnostic performance of the CNN model on the total test dataset was as follows: precision, 63.29%; recall, 65.02%; and F1-score, 64.14%, showing quite accurate performance. When three dentists detected caries using the results of the CNN model as reference data, the overall diagnostic performance of all three clinicians significantly improved, as shown by an increased sensitivity ratio (D1, 85.34%; D1′, 92.15%; D2, 85.86%; D2′, 93.72%; D3, 69.11%; D3′, 79.06%; p < 0.05). These increases were especially significant (p < 0.05) in the initial and moderate caries subgroups. The deep learning model may help clinicians to diagnose dental caries more accurately.Shinae LeeSang-il OhJunik JoSumi KangYooseok ShinJeong-won ParkNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-8 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Shinae Lee Sang-il Oh Junik Jo Sumi Kang Yooseok Shin Jeong-won Park Deep learning for early dental caries detection in bitewing radiographs
description	Abstract The early detection of initial dental caries enables preventive treatment, and bitewing radiography is a good diagnostic tool for posterior initial caries. In medical imaging, the utilization of deep learning with convolutional neural networks (CNNs) to process various types of images has been actively researched, with promising performance. In this study, we developed a CNN model using a U-shaped deep CNN (U-Net) for caries detection on bitewing radiographs and investigated whether this model can improve clinicians’ performance. The research complied with relevant ethical regulations. In total, 304 bitewing radiographs were used to train the CNN model and 50 radiographs for performance evaluation. The diagnostic performance of the CNN model on the total test dataset was as follows: precision, 63.29%; recall, 65.02%; and F1-score, 64.14%, showing quite accurate performance. When three dentists detected caries using the results of the CNN model as reference data, the overall diagnostic performance of all three clinicians significantly improved, as shown by an increased sensitivity ratio (D1, 85.34%; D1′, 92.15%; D2, 85.86%; D2′, 93.72%; D3, 69.11%; D3′, 79.06%; p < 0.05). These increases were especially significant (p < 0.05) in the initial and moderate caries subgroups. The deep learning model may help clinicians to diagnose dental caries more accurately.
format	article
author	Shinae Lee Sang-il Oh Junik Jo Sumi Kang Yooseok Shin Jeong-won Park
author_facet	Shinae Lee Sang-il Oh Junik Jo Sumi Kang Yooseok Shin Jeong-won Park
author_sort	Shinae Lee
title	Deep learning for early dental caries detection in bitewing radiographs
title_short	Deep learning for early dental caries detection in bitewing radiographs
title_full	Deep learning for early dental caries detection in bitewing radiographs
title_fullStr	Deep learning for early dental caries detection in bitewing radiographs
title_full_unstemmed	Deep learning for early dental caries detection in bitewing radiographs
title_sort	deep learning for early dental caries detection in bitewing radiographs
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/c0171c20667a4e448a01dbd9f8246ed4
work_keys_str_mv	AT shinaelee deeplearningforearlydentalcariesdetectioninbitewingradiographs AT sangiloh deeplearningforearlydentalcariesdetectioninbitewingradiographs AT junikjo deeplearningforearlydentalcariesdetectioninbitewingradiographs AT sumikang deeplearningforearlydentalcariesdetectioninbitewingradiographs AT yooseokshin deeplearningforearlydentalcariesdetectioninbitewingradiographs AT jeongwonpark deeplearningforearlydentalcariesdetectioninbitewingradiographs
_version_	1718381581766230016

Deep learning for early dental caries detection in bitewing radiographs

Ejemplares similares