Cargando…

Detection of Proximal Caries Lesions on Bitewing Radiographs Using Deep Learning Method

This study aimed to evaluate the validity of a deep learning-based convolutional neural network (CNN) for detecting proximal caries lesions on bitewing radiographs. A total of 978 bitewing radiographs, 10,899 proximal surfaces, were evaluated by two endodontists and a radiologist, of which 2,719 sur...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Xiaotong, Guo, Jiachang, Ye, Jiaxue, Zhang, Mingming, Liang, Yuhong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: S. Karger AG 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9932834/
https://www.ncbi.nlm.nih.gov/pubmed/36215971
http://dx.doi.org/10.1159/000527418
_version_ 1784889545066545152
author Chen, Xiaotong
Guo, Jiachang
Ye, Jiaxue
Zhang, Mingming
Liang, Yuhong
author_facet Chen, Xiaotong
Guo, Jiachang
Ye, Jiaxue
Zhang, Mingming
Liang, Yuhong
author_sort Chen, Xiaotong
collection PubMed
description This study aimed to evaluate the validity of a deep learning-based convolutional neural network (CNN) for detecting proximal caries lesions on bitewing radiographs. A total of 978 bitewing radiographs, 10,899 proximal surfaces, were evaluated by two endodontists and a radiologist, of which 2,719 surfaces were diagnosed and annotated with proximal caries and 8,180 surfaces were sound. The data were randomly divided into two datasets, with 818 bitewings in the training and validation dataset and 160 bitewings in the test dataset. Each annotation in the test set was then classified into 5 stages according to the extent of the lesion (E1, E2, D1, D2, D3). Faster R-CNN, a deep learning-based object detection method, was trained to detect proximal caries in the training and validation dataset and then was assessed on the test dataset. The diagnostic accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and receiver operating characteristic curve were calculated. The performance of the network in the overall and different stages of lesions was compared with that of postgraduate students on the test dataset. A total of 388 carious lesions and 1,435 sound surfaces were correctly identified by the neural network; hence, the accuracy was 0.87. Furthermore, 27.6% of lesions went undetected, and 7% of sound surfaces were misdiagnosed by the neural network. The sensitivity, specificity, PPV, and NPV of the neural network were 0.72, 0.93, 0.77, and 0.91, respectively. In contrast with the network, 52.8% of lesions went undetected by the students, yielding a sensitivity of only 0.47. The F1-score of the students was 0.57, while the F1-score of the network was 0.74 despite the accuracy of 0.82. A significant difference in the sensitivity was found between the model and the postgraduate students when detecting different stages of lesions (p < 0.05). For early lesions which limited in enamel and the outer third of dentin, the neural network had sensitivities all above or at 0.65, while students showed sensitivities below 0.40. From our results, we conclude that the CNN may be an assistant in detecting proximal caries on bitewings.
format Online
Article
Text
id pubmed-9932834
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher S. Karger AG
record_format MEDLINE/PubMed
spelling pubmed-99328342023-02-17 Detection of Proximal Caries Lesions on Bitewing Radiographs Using Deep Learning Method Chen, Xiaotong Guo, Jiachang Ye, Jiaxue Zhang, Mingming Liang, Yuhong Caries Res Research Article This study aimed to evaluate the validity of a deep learning-based convolutional neural network (CNN) for detecting proximal caries lesions on bitewing radiographs. A total of 978 bitewing radiographs, 10,899 proximal surfaces, were evaluated by two endodontists and a radiologist, of which 2,719 surfaces were diagnosed and annotated with proximal caries and 8,180 surfaces were sound. The data were randomly divided into two datasets, with 818 bitewings in the training and validation dataset and 160 bitewings in the test dataset. Each annotation in the test set was then classified into 5 stages according to the extent of the lesion (E1, E2, D1, D2, D3). Faster R-CNN, a deep learning-based object detection method, was trained to detect proximal caries in the training and validation dataset and then was assessed on the test dataset. The diagnostic accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and receiver operating characteristic curve were calculated. The performance of the network in the overall and different stages of lesions was compared with that of postgraduate students on the test dataset. A total of 388 carious lesions and 1,435 sound surfaces were correctly identified by the neural network; hence, the accuracy was 0.87. Furthermore, 27.6% of lesions went undetected, and 7% of sound surfaces were misdiagnosed by the neural network. The sensitivity, specificity, PPV, and NPV of the neural network were 0.72, 0.93, 0.77, and 0.91, respectively. In contrast with the network, 52.8% of lesions went undetected by the students, yielding a sensitivity of only 0.47. The F1-score of the students was 0.57, while the F1-score of the network was 0.74 despite the accuracy of 0.82. A significant difference in the sensitivity was found between the model and the postgraduate students when detecting different stages of lesions (p < 0.05). For early lesions which limited in enamel and the outer third of dentin, the neural network had sensitivities all above or at 0.65, while students showed sensitivities below 0.40. From our results, we conclude that the CNN may be an assistant in detecting proximal caries on bitewings. S. Karger AG 2023-02 2022-10-10 /pmc/articles/PMC9932834/ /pubmed/36215971 http://dx.doi.org/10.1159/000527418 Text en Copyright © 2022 by The Author(s). Published by S. Karger AG, Basel https://creativecommons.org/licenses/by-nc/4.0/This article is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC). Usage and distribution for commercial purposes requires written permission.
spellingShingle Research Article
Chen, Xiaotong
Guo, Jiachang
Ye, Jiaxue
Zhang, Mingming
Liang, Yuhong
Detection of Proximal Caries Lesions on Bitewing Radiographs Using Deep Learning Method
title Detection of Proximal Caries Lesions on Bitewing Radiographs Using Deep Learning Method
title_full Detection of Proximal Caries Lesions on Bitewing Radiographs Using Deep Learning Method
title_fullStr Detection of Proximal Caries Lesions on Bitewing Radiographs Using Deep Learning Method
title_full_unstemmed Detection of Proximal Caries Lesions on Bitewing Radiographs Using Deep Learning Method
title_short Detection of Proximal Caries Lesions on Bitewing Radiographs Using Deep Learning Method
title_sort detection of proximal caries lesions on bitewing radiographs using deep learning method
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9932834/
https://www.ncbi.nlm.nih.gov/pubmed/36215971
http://dx.doi.org/10.1159/000527418
work_keys_str_mv AT chenxiaotong detectionofproximalcarieslesionsonbitewingradiographsusingdeeplearningmethod
AT guojiachang detectionofproximalcarieslesionsonbitewingradiographsusingdeeplearningmethod
AT yejiaxue detectionofproximalcarieslesionsonbitewingradiographsusingdeeplearningmethod
AT zhangmingming detectionofproximalcarieslesionsonbitewingradiographsusingdeeplearningmethod
AT liangyuhong detectionofproximalcarieslesionsonbitewingradiographsusingdeeplearningmethod