Automatic soft‐tissue analysis on orthodontic frontal and lateral facial photographs based on deep learning
Orthodontics & Craniofacial Research · 2024-12 · 27 (6) · 893-902
DOI: 10.1111/ocr.12830 ↗At a glance
Journal article in Orthodontics & Craniofacial Research, published online on 2024-07-05. Written by Qiao Chang and 6 co-authors. Institution: Department of Orthodontics, School of Stomatology, Capital Medical University, Beijing, China. Major MEDLINE topics: Deep Learning, Face, Anatomic Landmarks. Cited 21 times so far (Crossref); 29 references. Funded by: Beijing Natural Science Foundation, Beijing Hospitals Authority Clinical Medicine Development of special funding support, Beijing Stomatological Hospital, Capital Medical University Young Scientist Program.
Abstract (original language)
Background
To establish the automatic soft‐tissue analysis model based on deep learning that performs landmark detection and measurement calculations on orthodontic facial photographs to achieve a more comprehensive quantitative evaluation of soft tissues.
Methods
A total of 578 frontal photographs and 450 lateral photographs of orthodontic patients were collected to construct datasets. All images were manually annotated by two orthodontists with 43 frontal‐image landmarks and 17 lateral‐image landmarks. Automatic landmark detection models were established, which consisted of a high‐resolution network, a feature fusion module based on depthwise separable convolution, and a prediction model based on pixel shuffle. Ten measurements for frontal images and eight measurements for lateral images were defined. Test sets were used to evaluate the model performance, respectively. The mean radial error of landmarks and measurement error were calculated and statistically analysed to evaluate their reliability.
Results
The mean radial error was 14.44 ± 17.20 pixels for the landmarks in the frontal images and 13.48 ± 17.12 pixels for the landmarks in the lateral images. There was no statistically significant difference between the model prediction and manual annotation measurements except for the mid facial‐lower facial height index. A total of 14 measurements had a high consistency.
Conclusion
Based on deep learning, we established automatic soft‐tissue analysis models for orthodontic facial photographs that can automatically detect 43 frontal‐image landmarks and 17 lateral‐image landmarks while performing comprehensive soft‐tissue measurements. The models can assist orthodontists in efficient and accurate quantitative soft‐tissue evaluation for clinical application.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Orthodontics, School of Stomatology, Capital Medical University, Beijing, China.
- Department of Engineering Physics, Tsinghua University, Beijing, China.
- LargeV Instrument Corporation Limited, Beijing, China.
ORCID profiles: Qiao Chang, Yuxing Bai, Shaofeng Wang, Fan Wang, Yajie Wang, Feifei Zuo, Xianju Xie
Funding
- Beijing Natural Science Foundation
- Beijing Hospitals Authority Clinical Medicine Development of special funding support
- Beijing Stomatological Hospital, Capital Medical University Young Scientist Program
- Natural Science Foundation of Beijing Municipality
Cite
APA
Chang, Q., Bai, Y., Wang, S., Wang, F., Wang, Y., Zuo, F., & Xie, X. (2024). Automatic soft‐tissue analysis on orthodontic frontal and lateral facial photographs based on deep learning. Orthodontics & Craniofacial Research, 27(6), 893-902. https://doi.org/10.1111/ocr.12830
Vancouver
Chang Q, Bai Y, Wang S, Wang F, Wang Y, Zuo F, et al. Automatic soft‐tissue analysis on orthodontic frontal and lateral facial photographs based on deep learning. Orthodontics & Craniofacial Research. 2024;27(6):893-902. doi:10.1111/ocr.12830
BibTeX
@article{Chang2024,
author = {Chang, Qiao and Bai, Yuxing and Wang, Shaofeng and Wang, Fan and Wang, Yajie and Zuo, Feifei and Xie, Xianju},
title = {Automatic soft‐tissue analysis on orthodontic frontal and lateral facial photographs based on deep learning},
journal = {Orthodontics & Craniofacial Research},
year = {2024},
volume = {27},
number = {6},
pages = {893--902},
doi = {10.1111/ocr.12830}
}
EUVIMED