Development of a diagnostic classification model for lateral cephalograms based on multitask learning

Abstract Objectives This study aimed to develop a cephalometric classification method based on multitask learning for eight diagnostic classifications. Methods This study was retrospective. A total of 3,310 lateral cephalograms were collected to construct a dataset. Eight clinical classifications we...

Full description

Saved in:
Bibliographic Details
Main Authors: Qiao Chang, Shaofeng Wang, Fan Wang, Beiwen Gong, Yajie Wang, Feifei Zuo, Xianju Xie, Yuxing Bai
Format: Article
Language:English
Published: BMC 2025-02-01
Series:BMC Oral Health
Subjects:
Online Access:https://doi.org/10.1186/s12903-025-05588-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850087163353366528
author Qiao Chang
Shaofeng Wang
Fan Wang
Beiwen Gong
Yajie Wang
Feifei Zuo
Xianju Xie
Yuxing Bai
author_facet Qiao Chang
Shaofeng Wang
Fan Wang
Beiwen Gong
Yajie Wang
Feifei Zuo
Xianju Xie
Yuxing Bai
author_sort Qiao Chang
collection DOAJ
description Abstract Objectives This study aimed to develop a cephalometric classification method based on multitask learning for eight diagnostic classifications. Methods This study was retrospective. A total of 3,310 lateral cephalograms were collected to construct a dataset. Eight clinical classifications were employed, including sagittal and vertical skeletal facial patterns, maxillary and mandibular anteroposterior positions, inclinations of upper and lower incisors, as well as their anteroposterior positions. The images were manually annotated for initially classification, which was verified by senior orthodontists. The data were randomly divided into training, validation, and test sets at a ratio of approximately 8:1:1. The multitask learning classification model was constructed based on the ResNeXt50_32 × 4d network and consisted of shared layers and task-specific layers. The performance of the model was evaluated using classification accuracy, precision, sensitivity, specificity and area under the curve (AUC). Results This model could perform eight clinical diagnostic classifications on cephalograms within an average of 0.0096 s. The accuracy of the six classifications was 0.8–0.9, and the accuracy of the two classifications was 0.75-0.8. The overall AUC values for each classification exceeded 0.9. Conclusions An automatic diagnostic classification model for lateral cephalograms was established based on multitask learning to achieve simultaneous classification of eight common clinical diagnostic items. The multitask learning model achieved better classification performance and reduced the computational costs, providing a novel perspective and reference for addressing such problems.
format Article
id doaj-art-b6fb125cd79148f19fca1f12f09b7fb5
institution DOAJ
issn 1472-6831
language English
publishDate 2025-02-01
publisher BMC
record_format Article
series BMC Oral Health
spelling doaj-art-b6fb125cd79148f19fca1f12f09b7fb52025-08-20T02:43:16ZengBMCBMC Oral Health1472-68312025-02-0125111310.1186/s12903-025-05588-0Development of a diagnostic classification model for lateral cephalograms based on multitask learningQiao Chang0Shaofeng Wang1Fan Wang2Beiwen Gong3Yajie Wang4Feifei Zuo5Xianju Xie6Yuxing Bai7Department of Orthodontics, Beijing Stomatological Hospital, Capital Medical UniversityDepartment of Orthodontics, Beijing Stomatological Hospital, Capital Medical UniversityDepartment of Orthodontics, Beijing Stomatological Hospital, Capital Medical UniversityDepartment of Orthodontics, Beijing Stomatological Hospital, Capital Medical UniversityDepartment of Engineering Physics, Tsinghua UniversityLargeV Instrument Corporation LimitedDepartment of Orthodontics, Beijing Stomatological Hospital, Capital Medical UniversityDepartment of Orthodontics, Beijing Stomatological Hospital, Capital Medical UniversityAbstract Objectives This study aimed to develop a cephalometric classification method based on multitask learning for eight diagnostic classifications. Methods This study was retrospective. A total of 3,310 lateral cephalograms were collected to construct a dataset. Eight clinical classifications were employed, including sagittal and vertical skeletal facial patterns, maxillary and mandibular anteroposterior positions, inclinations of upper and lower incisors, as well as their anteroposterior positions. The images were manually annotated for initially classification, which was verified by senior orthodontists. The data were randomly divided into training, validation, and test sets at a ratio of approximately 8:1:1. The multitask learning classification model was constructed based on the ResNeXt50_32 × 4d network and consisted of shared layers and task-specific layers. The performance of the model was evaluated using classification accuracy, precision, sensitivity, specificity and area under the curve (AUC). Results This model could perform eight clinical diagnostic classifications on cephalograms within an average of 0.0096 s. The accuracy of the six classifications was 0.8–0.9, and the accuracy of the two classifications was 0.75-0.8. The overall AUC values for each classification exceeded 0.9. Conclusions An automatic diagnostic classification model for lateral cephalograms was established based on multitask learning to achieve simultaneous classification of eight common clinical diagnostic items. The multitask learning model achieved better classification performance and reduced the computational costs, providing a novel perspective and reference for addressing such problems.https://doi.org/10.1186/s12903-025-05588-0CephalometryDeep learningImage classificationMultitask learning
spellingShingle Qiao Chang
Shaofeng Wang
Fan Wang
Beiwen Gong
Yajie Wang
Feifei Zuo
Xianju Xie
Yuxing Bai
Development of a diagnostic classification model for lateral cephalograms based on multitask learning
BMC Oral Health
Cephalometry
Deep learning
Image classification
Multitask learning
title Development of a diagnostic classification model for lateral cephalograms based on multitask learning
title_full Development of a diagnostic classification model for lateral cephalograms based on multitask learning
title_fullStr Development of a diagnostic classification model for lateral cephalograms based on multitask learning
title_full_unstemmed Development of a diagnostic classification model for lateral cephalograms based on multitask learning
title_short Development of a diagnostic classification model for lateral cephalograms based on multitask learning
title_sort development of a diagnostic classification model for lateral cephalograms based on multitask learning
topic Cephalometry
Deep learning
Image classification
Multitask learning
url https://doi.org/10.1186/s12903-025-05588-0
work_keys_str_mv AT qiaochang developmentofadiagnosticclassificationmodelforlateralcephalogramsbasedonmultitasklearning
AT shaofengwang developmentofadiagnosticclassificationmodelforlateralcephalogramsbasedonmultitasklearning
AT fanwang developmentofadiagnosticclassificationmodelforlateralcephalogramsbasedonmultitasklearning
AT beiwengong developmentofadiagnosticclassificationmodelforlateralcephalogramsbasedonmultitasklearning
AT yajiewang developmentofadiagnosticclassificationmodelforlateralcephalogramsbasedonmultitasklearning
AT feifeizuo developmentofadiagnosticclassificationmodelforlateralcephalogramsbasedonmultitasklearning
AT xianjuxie developmentofadiagnosticclassificationmodelforlateralcephalogramsbasedonmultitasklearning
AT yuxingbai developmentofadiagnosticclassificationmodelforlateralcephalogramsbasedonmultitasklearning