Classification of Approximal Caries in Bitewing Radiographs Using Convolutional Neural Networks
Dental caries is an extremely common problem in dentistry that affects a significant part of the population. Approximal caries are especially difficult to identify because their position makes clinical analysis difficult. Radiographic evaluation—more specifically, bitewing images—are mostly used in...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-07-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/15/5192 |
id |
doaj-9284ae7f18634e18abe0eb221f31a33e |
---|---|
record_format |
Article |
spelling |
doaj-9284ae7f18634e18abe0eb221f31a33e2021-08-06T15:31:43ZengMDPI AGSensors1424-82202021-07-01215192519210.3390/s21155192Classification of Approximal Caries in Bitewing Radiographs Using Convolutional Neural NetworksMaira Moran0Marcelo Faria1Gilson Giraldi2Luciana Bastos3Larissa Oliveira4Aura Conci5Policlínica Piquet Carneiro, Universidade do Estado do Rio de Janeiro, Rio de Janeiro 20950-003, BrazilPoliclínica Piquet Carneiro, Universidade do Estado do Rio de Janeiro, Rio de Janeiro 20950-003, BrazilLaboratório Nacional de Computação Científica, Petrópolis 25651-076, BrazilPoliclínica Piquet Carneiro, Universidade do Estado do Rio de Janeiro, Rio de Janeiro 20950-003, BrazilPoliclínica Piquet Carneiro, Universidade do Estado do Rio de Janeiro, Rio de Janeiro 20950-003, BrazilInstituto de Computação, Universidade Federal Fluminense, Niterói 24210-310, BrazilDental caries is an extremely common problem in dentistry that affects a significant part of the population. Approximal caries are especially difficult to identify because their position makes clinical analysis difficult. Radiographic evaluation—more specifically, bitewing images—are mostly used in such cases. However, incorrect interpretations may interfere with the diagnostic process. To aid dentists in caries evaluation, computational methods and tools can be used. In this work, we propose a new method that combines image processing techniques and convolutional neural networks to identify approximal dental caries in bitewing radiographic images and classify them according to lesion severity. For this study, we acquired 112 bitewing radiographs. From these exams, we extracted individual tooth images from each exam, applied a data augmentation process, and used the resulting images to train CNN classification models. The tooth images were previously labeled by experts to denote the defined classes. We evaluated classification models based on the Inception and ResNet architectures using three different learning rates: 0.1, 0.01, and 0.001. The training process included 2000 iterations, and the best results were achieved by the Inception model with a 0.001 learning rate, whose accuracy on the test set was 73.3%. The results can be considered promising and suggest that the proposed method could be used to assist dentists in the evaluation of bitewing images, and the definition of lesion severity and appropriate treatments.https://www.mdpi.com/1424-8220/21/15/5192bitewing radiographyneural networksartificial intelligencecariesdental radiographydiagnosis |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Maira Moran Marcelo Faria Gilson Giraldi Luciana Bastos Larissa Oliveira Aura Conci |
spellingShingle |
Maira Moran Marcelo Faria Gilson Giraldi Luciana Bastos Larissa Oliveira Aura Conci Classification of Approximal Caries in Bitewing Radiographs Using Convolutional Neural Networks Sensors bitewing radiography neural networks artificial intelligence caries dental radiography diagnosis |
author_facet |
Maira Moran Marcelo Faria Gilson Giraldi Luciana Bastos Larissa Oliveira Aura Conci |
author_sort |
Maira Moran |
title |
Classification of Approximal Caries in Bitewing Radiographs Using Convolutional Neural Networks |
title_short |
Classification of Approximal Caries in Bitewing Radiographs Using Convolutional Neural Networks |
title_full |
Classification of Approximal Caries in Bitewing Radiographs Using Convolutional Neural Networks |
title_fullStr |
Classification of Approximal Caries in Bitewing Radiographs Using Convolutional Neural Networks |
title_full_unstemmed |
Classification of Approximal Caries in Bitewing Radiographs Using Convolutional Neural Networks |
title_sort |
classification of approximal caries in bitewing radiographs using convolutional neural networks |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2021-07-01 |
description |
Dental caries is an extremely common problem in dentistry that affects a significant part of the population. Approximal caries are especially difficult to identify because their position makes clinical analysis difficult. Radiographic evaluation—more specifically, bitewing images—are mostly used in such cases. However, incorrect interpretations may interfere with the diagnostic process. To aid dentists in caries evaluation, computational methods and tools can be used. In this work, we propose a new method that combines image processing techniques and convolutional neural networks to identify approximal dental caries in bitewing radiographic images and classify them according to lesion severity. For this study, we acquired 112 bitewing radiographs. From these exams, we extracted individual tooth images from each exam, applied a data augmentation process, and used the resulting images to train CNN classification models. The tooth images were previously labeled by experts to denote the defined classes. We evaluated classification models based on the Inception and ResNet architectures using three different learning rates: 0.1, 0.01, and 0.001. The training process included 2000 iterations, and the best results were achieved by the Inception model with a 0.001 learning rate, whose accuracy on the test set was 73.3%. The results can be considered promising and suggest that the proposed method could be used to assist dentists in the evaluation of bitewing images, and the definition of lesion severity and appropriate treatments. |
topic |
bitewing radiography neural networks artificial intelligence caries dental radiography diagnosis |
url |
https://www.mdpi.com/1424-8220/21/15/5192 |
work_keys_str_mv |
AT mairamoran classificationofapproximalcariesinbitewingradiographsusingconvolutionalneuralnetworks AT marcelofaria classificationofapproximalcariesinbitewingradiographsusingconvolutionalneuralnetworks AT gilsongiraldi classificationofapproximalcariesinbitewingradiographsusingconvolutionalneuralnetworks AT lucianabastos classificationofapproximalcariesinbitewingradiographsusingconvolutionalneuralnetworks AT larissaoliveira classificationofapproximalcariesinbitewingradiographsusingconvolutionalneuralnetworks AT auraconci classificationofapproximalcariesinbitewingradiographsusingconvolutionalneuralnetworks |
_version_ |
1721217608992161792 |