Cargando…

Detecting Proximal Caries on Periapical Radiographs Using Convolutional Neural Networks with Different Training Strategies on Small Datasets

The present study aimed to evaluate the performance of convolutional neural networks (CNNs) that were trained with small datasets using different strategies in the detection of proximal caries at different levels of severity on periapical radiographs. Small datasets containing 800 periapical radiogr...

Descripción completa

Detalles Bibliográficos
Autores principales: Lin, Xiujiao, Hong, Dengwei, Zhang, Dong, Huang, Mingyi, Yu, Hao
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9139265/
https://www.ncbi.nlm.nih.gov/pubmed/35626203
http://dx.doi.org/10.3390/diagnostics12051047
_version_ 1784714818938208256
author Lin, Xiujiao
Hong, Dengwei
Zhang, Dong
Huang, Mingyi
Yu, Hao
author_facet Lin, Xiujiao
Hong, Dengwei
Zhang, Dong
Huang, Mingyi
Yu, Hao
author_sort Lin, Xiujiao
collection PubMed
description The present study aimed to evaluate the performance of convolutional neural networks (CNNs) that were trained with small datasets using different strategies in the detection of proximal caries at different levels of severity on periapical radiographs. Small datasets containing 800 periapical radiographs were randomly categorized into a training and validation dataset (n = 600) and a test dataset (n = 200). A pretrained Cifar-10Net CNN was used in the present study. Different training strategies were used to train the CNN model independently; these strategies were defined as image recognition (IR), edge extraction (EE), and image segmentation (IS). Different metrics, such as sensitivity and area under the receiver operating characteristic curve (AUC), for the trained CNN and human observers were analysed to evaluate the performance in detecting proximal caries. IR, EE, and IS recognition modes and human eyes achieved AUCs of 0.805, 0.860, 0.549, and 0.767, respectively, with the EE recognition mode having the highest values (p all < 0.05). The EE recognition mode was significantly more sensitive in detecting both enamel and dentin caries than human eyes (p all < 0.05). The CNN trained with the EE strategy, the best performer in the present study, showed potential utility in detecting proximal caries on periapical radiographs when using small datasets.
format Online
Article
Text
id pubmed-9139265
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-91392652022-05-28 Detecting Proximal Caries on Periapical Radiographs Using Convolutional Neural Networks with Different Training Strategies on Small Datasets Lin, Xiujiao Hong, Dengwei Zhang, Dong Huang, Mingyi Yu, Hao Diagnostics (Basel) Article The present study aimed to evaluate the performance of convolutional neural networks (CNNs) that were trained with small datasets using different strategies in the detection of proximal caries at different levels of severity on periapical radiographs. Small datasets containing 800 periapical radiographs were randomly categorized into a training and validation dataset (n = 600) and a test dataset (n = 200). A pretrained Cifar-10Net CNN was used in the present study. Different training strategies were used to train the CNN model independently; these strategies were defined as image recognition (IR), edge extraction (EE), and image segmentation (IS). Different metrics, such as sensitivity and area under the receiver operating characteristic curve (AUC), for the trained CNN and human observers were analysed to evaluate the performance in detecting proximal caries. IR, EE, and IS recognition modes and human eyes achieved AUCs of 0.805, 0.860, 0.549, and 0.767, respectively, with the EE recognition mode having the highest values (p all < 0.05). The EE recognition mode was significantly more sensitive in detecting both enamel and dentin caries than human eyes (p all < 0.05). The CNN trained with the EE strategy, the best performer in the present study, showed potential utility in detecting proximal caries on periapical radiographs when using small datasets. MDPI 2022-04-21 /pmc/articles/PMC9139265/ /pubmed/35626203 http://dx.doi.org/10.3390/diagnostics12051047 Text en © 2022 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
Lin, Xiujiao
Hong, Dengwei
Zhang, Dong
Huang, Mingyi
Yu, Hao
Detecting Proximal Caries on Periapical Radiographs Using Convolutional Neural Networks with Different Training Strategies on Small Datasets
title Detecting Proximal Caries on Periapical Radiographs Using Convolutional Neural Networks with Different Training Strategies on Small Datasets
title_full Detecting Proximal Caries on Periapical Radiographs Using Convolutional Neural Networks with Different Training Strategies on Small Datasets
title_fullStr Detecting Proximal Caries on Periapical Radiographs Using Convolutional Neural Networks with Different Training Strategies on Small Datasets
title_full_unstemmed Detecting Proximal Caries on Periapical Radiographs Using Convolutional Neural Networks with Different Training Strategies on Small Datasets
title_short Detecting Proximal Caries on Periapical Radiographs Using Convolutional Neural Networks with Different Training Strategies on Small Datasets
title_sort detecting proximal caries on periapical radiographs using convolutional neural networks with different training strategies on small datasets
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9139265/
https://www.ncbi.nlm.nih.gov/pubmed/35626203
http://dx.doi.org/10.3390/diagnostics12051047
work_keys_str_mv AT linxiujiao detectingproximalcariesonperiapicalradiographsusingconvolutionalneuralnetworkswithdifferenttrainingstrategiesonsmalldatasets
AT hongdengwei detectingproximalcariesonperiapicalradiographsusingconvolutionalneuralnetworkswithdifferenttrainingstrategiesonsmalldatasets
AT zhangdong detectingproximalcariesonperiapicalradiographsusingconvolutionalneuralnetworkswithdifferenttrainingstrategiesonsmalldatasets
AT huangmingyi detectingproximalcariesonperiapicalradiographsusingconvolutionalneuralnetworkswithdifferenttrainingstrategiesonsmalldatasets
AT yuhao detectingproximalcariesonperiapicalradiographsusingconvolutionalneuralnetworkswithdifferenttrainingstrategiesonsmalldatasets