Automated cephalometric landmark detection with confidence regions using Bayesian convolutional neural networks
Abstract Background Despite the integral role of cephalometric analysis in orthodontics, there have been limitations regarding the reliability, accuracy, etc. of cephalometric landmarks tracing. Attempts on developing automatic plotting systems have continuously been made but they are insufficient f...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2020-10-01
|
Series: | BMC Oral Health |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s12903-020-01256-7 |
id |
doaj-afefdf9724c3499f8ceb3b2da99bc7dc |
---|---|
record_format |
Article |
spelling |
doaj-afefdf9724c3499f8ceb3b2da99bc7dc2020-11-25T03:42:10ZengBMCBMC Oral Health1472-68312020-10-0120111010.1186/s12903-020-01256-7Automated cephalometric landmark detection with confidence regions using Bayesian convolutional neural networksJeong-Hoon Lee0Hee-Jin Yu1Min-ji Kim2Jin-Woo Kim3Jongeun Choi4School of Mechanical Engineering, Yonsei UniversitySchool of Mechanical Engineering, Yonsei UniversityDepartment of Orthodontics, School of Medicine, Ewha Womans UniversityDepartment of Oral and Maxillofacial Surgery, School of Medicine, Ewha Womans UniversitySchool of Mechanical Engineering, Yonsei UniversityAbstract Background Despite the integral role of cephalometric analysis in orthodontics, there have been limitations regarding the reliability, accuracy, etc. of cephalometric landmarks tracing. Attempts on developing automatic plotting systems have continuously been made but they are insufficient for clinical applications due to low reliability of specific landmarks. In this study, we aimed to develop a novel framework for locating cephalometric landmarks with confidence regions using Bayesian Convolutional Neural Networks (BCNN). Methods We have trained our model with the dataset from the ISBI 2015 grand challenge in dental X-ray image analysis. The overall algorithm consisted of a region of interest (ROI) extraction of landmarks and landmarks estimation considering uncertainty. Prediction data produced from the Bayesian model has been dealt with post-processing methods with respect to pixel probabilities and uncertainties. Results Our framework showed a mean landmark error (LE) of 1.53 ± 1.74 mm and achieved a successful detection rate (SDR) of 82.11, 92.28 and 95.95%, respectively, in the 2, 3, and 4 mm range. Especially, the most erroneous point in preceding studies, Gonion, reduced nearly halves of its error compared to the others. Additionally, our results demonstrated significantly higher performance in identifying anatomical abnormalities. By providing confidence regions (95%) that consider uncertainty, our framework can provide clinical convenience and contribute to making better decisions. Conclusion Our framework provides cephalometric landmarks and their confidence regions, which could be used as a computer-aided diagnosis tool and education.http://link.springer.com/article/10.1186/s12903-020-01256-7Artificial neural networksBayesian methodCephalometryOrthodonticsMachine visionDeep learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jeong-Hoon Lee Hee-Jin Yu Min-ji Kim Jin-Woo Kim Jongeun Choi |
spellingShingle |
Jeong-Hoon Lee Hee-Jin Yu Min-ji Kim Jin-Woo Kim Jongeun Choi Automated cephalometric landmark detection with confidence regions using Bayesian convolutional neural networks BMC Oral Health Artificial neural networks Bayesian method Cephalometry Orthodontics Machine vision Deep learning |
author_facet |
Jeong-Hoon Lee Hee-Jin Yu Min-ji Kim Jin-Woo Kim Jongeun Choi |
author_sort |
Jeong-Hoon Lee |
title |
Automated cephalometric landmark detection with confidence regions using Bayesian convolutional neural networks |
title_short |
Automated cephalometric landmark detection with confidence regions using Bayesian convolutional neural networks |
title_full |
Automated cephalometric landmark detection with confidence regions using Bayesian convolutional neural networks |
title_fullStr |
Automated cephalometric landmark detection with confidence regions using Bayesian convolutional neural networks |
title_full_unstemmed |
Automated cephalometric landmark detection with confidence regions using Bayesian convolutional neural networks |
title_sort |
automated cephalometric landmark detection with confidence regions using bayesian convolutional neural networks |
publisher |
BMC |
series |
BMC Oral Health |
issn |
1472-6831 |
publishDate |
2020-10-01 |
description |
Abstract Background Despite the integral role of cephalometric analysis in orthodontics, there have been limitations regarding the reliability, accuracy, etc. of cephalometric landmarks tracing. Attempts on developing automatic plotting systems have continuously been made but they are insufficient for clinical applications due to low reliability of specific landmarks. In this study, we aimed to develop a novel framework for locating cephalometric landmarks with confidence regions using Bayesian Convolutional Neural Networks (BCNN). Methods We have trained our model with the dataset from the ISBI 2015 grand challenge in dental X-ray image analysis. The overall algorithm consisted of a region of interest (ROI) extraction of landmarks and landmarks estimation considering uncertainty. Prediction data produced from the Bayesian model has been dealt with post-processing methods with respect to pixel probabilities and uncertainties. Results Our framework showed a mean landmark error (LE) of 1.53 ± 1.74 mm and achieved a successful detection rate (SDR) of 82.11, 92.28 and 95.95%, respectively, in the 2, 3, and 4 mm range. Especially, the most erroneous point in preceding studies, Gonion, reduced nearly halves of its error compared to the others. Additionally, our results demonstrated significantly higher performance in identifying anatomical abnormalities. By providing confidence regions (95%) that consider uncertainty, our framework can provide clinical convenience and contribute to making better decisions. Conclusion Our framework provides cephalometric landmarks and their confidence regions, which could be used as a computer-aided diagnosis tool and education. |
topic |
Artificial neural networks Bayesian method Cephalometry Orthodontics Machine vision Deep learning |
url |
http://link.springer.com/article/10.1186/s12903-020-01256-7 |
work_keys_str_mv |
AT jeonghoonlee automatedcephalometriclandmarkdetectionwithconfidenceregionsusingbayesianconvolutionalneuralnetworks AT heejinyu automatedcephalometriclandmarkdetectionwithconfidenceregionsusingbayesianconvolutionalneuralnetworks AT minjikim automatedcephalometriclandmarkdetectionwithconfidenceregionsusingbayesianconvolutionalneuralnetworks AT jinwookim automatedcephalometriclandmarkdetectionwithconfidenceregionsusingbayesianconvolutionalneuralnetworks AT jongeunchoi automatedcephalometriclandmarkdetectionwithconfidenceregionsusingbayesianconvolutionalneuralnetworks |
_version_ |
1724526771946127360 |