Accuracy of cephalometric landmark and cephalometric analysis from lateral facial photograph by using CNN-based algorithm

Abstract Cephalometric analysis is the primary diagnosis method in orthodontics. In our previous study, the algorithm was developed to estimate cephalometric landmarks from lateral facial photographs of patients with normal occlusion. This study evaluates the estimation accuracy by the algorithm tra...

Full description

Saved in:
Bibliographic Details
Main Authors: Yui Shimamura, Chie Tachiki, Kaisei Takahashi, Satoru Matsunaga, Takashi Takaki, Masafumi Hagiwara, Yasushi Nishii
Format: Article
Language:English
Published: Nature Portfolio 2024-12-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-82230-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850103339247730688
author Yui Shimamura
Chie Tachiki
Kaisei Takahashi
Satoru Matsunaga
Takashi Takaki
Masafumi Hagiwara
Yasushi Nishii
author_facet Yui Shimamura
Chie Tachiki
Kaisei Takahashi
Satoru Matsunaga
Takashi Takaki
Masafumi Hagiwara
Yasushi Nishii
author_sort Yui Shimamura
collection DOAJ
description Abstract Cephalometric analysis is the primary diagnosis method in orthodontics. In our previous study, the algorithm was developed to estimate cephalometric landmarks from lateral facial photographs of patients with normal occlusion. This study evaluates the estimation accuracy by the algorithm trained on a dataset of 2320 patients with added malocclusion patients and the analysis values. The landmarks were estimated from the input of lateral facial photographs as training data using trained CNN-based algorithms. The success detection rate (SDR) was calculated based on the mean radial error (MRE) of the distance between the estimated and actual coordinates. Furthermore, the estimated landmarks were used to measure angles and distances as a cephalometric analysis. In the skeletal Class II malocclusion, MRE was 0.42 ± 0.15 mm, and in the skeletal Class III malocclusion, MRE was 0.46 ± 0.16 mm. We conducted a cephalometric analysis using the estimated landmarks and examined the differences with actual data. In both groups, no significant differences were observed for any of the data. Our new algorithm for estimating the landmarks from lateral facial photographs of malocclusion patients resulted in an error of less than 0.5 mm; the error in cephalometric analysis was less than 0.5°. Therefore, the algorithm can be clinically valuable.
format Article
id doaj-art-6b94dd63b41b4fd28bd78d6078d9af4b
institution DOAJ
issn 2045-2322
language English
publishDate 2024-12-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-6b94dd63b41b4fd28bd78d6078d9af4b2025-08-20T02:39:34ZengNature PortfolioScientific Reports2045-23222024-12-0114111510.1038/s41598-024-82230-zAccuracy of cephalometric landmark and cephalometric analysis from lateral facial photograph by using CNN-based algorithmYui Shimamura0Chie Tachiki1Kaisei Takahashi2Satoru Matsunaga3Takashi Takaki4Masafumi Hagiwara5Yasushi Nishii6Department of Orthodontics, Tokyo Dental CollegeDepartment of Orthodontics, Tokyo Dental CollegeDepartment of Information and Computer Science, Faculty of Science and Technology, Keio UniversityOral Health Science Center, Tokyo Dental CollegeDepartment of Oral and Maxillofacial Surgery, Tokyo Dental CollegeDepartment of Information and Computer Science, Faculty of Science and Technology, Keio UniversityDepartment of Orthodontics, Tokyo Dental CollegeAbstract Cephalometric analysis is the primary diagnosis method in orthodontics. In our previous study, the algorithm was developed to estimate cephalometric landmarks from lateral facial photographs of patients with normal occlusion. This study evaluates the estimation accuracy by the algorithm trained on a dataset of 2320 patients with added malocclusion patients and the analysis values. The landmarks were estimated from the input of lateral facial photographs as training data using trained CNN-based algorithms. The success detection rate (SDR) was calculated based on the mean radial error (MRE) of the distance between the estimated and actual coordinates. Furthermore, the estimated landmarks were used to measure angles and distances as a cephalometric analysis. In the skeletal Class II malocclusion, MRE was 0.42 ± 0.15 mm, and in the skeletal Class III malocclusion, MRE was 0.46 ± 0.16 mm. We conducted a cephalometric analysis using the estimated landmarks and examined the differences with actual data. In both groups, no significant differences were observed for any of the data. Our new algorithm for estimating the landmarks from lateral facial photographs of malocclusion patients resulted in an error of less than 0.5 mm; the error in cephalometric analysis was less than 0.5°. Therefore, the algorithm can be clinically valuable.https://doi.org/10.1038/s41598-024-82230-zEstimation cephalometric landmarksLateral facial photographCNN-based algorithmCephalometric analysisMalocclusion dataCephalometric landmarks
spellingShingle Yui Shimamura
Chie Tachiki
Kaisei Takahashi
Satoru Matsunaga
Takashi Takaki
Masafumi Hagiwara
Yasushi Nishii
Accuracy of cephalometric landmark and cephalometric analysis from lateral facial photograph by using CNN-based algorithm
Scientific Reports
Estimation cephalometric landmarks
Lateral facial photograph
CNN-based algorithm
Cephalometric analysis
Malocclusion data
Cephalometric landmarks
title Accuracy of cephalometric landmark and cephalometric analysis from lateral facial photograph by using CNN-based algorithm
title_full Accuracy of cephalometric landmark and cephalometric analysis from lateral facial photograph by using CNN-based algorithm
title_fullStr Accuracy of cephalometric landmark and cephalometric analysis from lateral facial photograph by using CNN-based algorithm
title_full_unstemmed Accuracy of cephalometric landmark and cephalometric analysis from lateral facial photograph by using CNN-based algorithm
title_short Accuracy of cephalometric landmark and cephalometric analysis from lateral facial photograph by using CNN-based algorithm
title_sort accuracy of cephalometric landmark and cephalometric analysis from lateral facial photograph by using cnn based algorithm
topic Estimation cephalometric landmarks
Lateral facial photograph
CNN-based algorithm
Cephalometric analysis
Malocclusion data
Cephalometric landmarks
url https://doi.org/10.1038/s41598-024-82230-z
work_keys_str_mv AT yuishimamura accuracyofcephalometriclandmarkandcephalometricanalysisfromlateralfacialphotographbyusingcnnbasedalgorithm
AT chietachiki accuracyofcephalometriclandmarkandcephalometricanalysisfromlateralfacialphotographbyusingcnnbasedalgorithm
AT kaiseitakahashi accuracyofcephalometriclandmarkandcephalometricanalysisfromlateralfacialphotographbyusingcnnbasedalgorithm
AT satorumatsunaga accuracyofcephalometriclandmarkandcephalometricanalysisfromlateralfacialphotographbyusingcnnbasedalgorithm
AT takashitakaki accuracyofcephalometriclandmarkandcephalometricanalysisfromlateralfacialphotographbyusingcnnbasedalgorithm
AT masafumihagiwara accuracyofcephalometriclandmarkandcephalometricanalysisfromlateralfacialphotographbyusingcnnbasedalgorithm
AT yasushinishii accuracyofcephalometriclandmarkandcephalometricanalysisfromlateralfacialphotographbyusingcnnbasedalgorithm