Abstract
This study aimed to perform three-dimensional (3D) cephalometric analysis based on automatically identified landmarks, to evaluate their clinical accuracy, and to investigate the relationship between algorithmic precision, measured by mean radial error (MRE), and clinical validity. Retrospective cone-beam computed tomography (CBCT) scans representing diverse dentition stages and malocclusion types were used to develop an automated landmark identification model incorporating an optimized U-Net architecture with an Efficient Global Attention module. Seventy-one 3D cephalometric measurements derived from manually annotated landmarks and AI-generated landmarks were compared across 75 randomly selected CBCT scans of Class I/II malocclusion patients. Statistical analyses included paired t-tests/wilcoxon signed-rank test, intraclass correlation coefficients (ICC), and Bland–Altman analysis. Analysis revealed that 9 out of the 71 measurements (12.68%) showed statistically significant differences; however, all mean differences between AI-derived and ground truth measurements were clinically negligible (≤ 1 mm/°). ICC analysis demonstrated excellent agreement overall, with only two parameters (PP–HF–MSP and Me–MSP; 2.82%) showing ICC values below 0.90. Bland–Altman analysis indicated that 59.15% of AI-based cephalometric measurements achieved clinical interchangeability with ground truth, defined by limits of agreement within ± 2.0 mm/°. Among 36 linear measurements, all 26 parameters associated with landmarks exhibiting an MRE below 2 mm fell within clinically acceptable limits, whereas angle-based measurements did not demonstrate a clear correlation with MRE. The precision of automated 3D cephalometry is contingent upon the magnitude and directional vector of landmarking error. Angular measurements are particularly susceptible to unconstrained directional errors. Consequently, the MRE metric alone is insufficient to comprehensively evaluate the accuracy of automated cephalometric analysis, particularly in regions lacking definitive anatomical contours. Clinically applicable automated 3D cephalometry may therefore benefit from minor manual refinement at specific landmarks, such as the gonion and incisor root apex, particularly in patients with mixed dentition.
Data availability
The datasets generated and/or analysed during the current study are not publicly available due to privacy concerns but are available from the corresponding author on reasonable request.
References
Kapetanović, A., Oosterkamp, B., Lamberts, A. A. & Schols, J. Orthodontic radiology: Development of a clinical practice guideline. Radiol. Med. 126, 72–82 (2021).
Bagdy-Bálint, R. et al. Accuracy of automated analysis in cephalometry. J. Dent. Sci. 20, 830–843 (2025).
Hendrickx, J. et al. Can artificial intelligence-driven cephalometric analysis replace manual tracing? A systematic review and meta-analysis. Eur. J. Orthod. 46, cjae029 (2024).
de Queiroz Tavares Borges Mesquita, G. et al. Artificial Intelligence for detecting cephalometric landmarks: A systematic review and meta-analysis. J. Digit. Imaging. 36, 1158–1179 (2023).
Sam, A., Currie, K., Oh, H., Flores-Mir, C. & Lagravére-Vich, M. Reliability of different three-dimensional cephalometric landmarks in cone-beam computed tomography : A systematic review. Angle Orthod. 89, 317–332 (2019).
Gaêta-Araujo, H., Leite, A. F., Vasconcelos, K. F. & Jacobs, R. Two decades of research on CBCT imaging in DMFR - an appraisal of scientific evidence. Dentomaxillofac. Radiol. 50, 20200367 (2021).
Ayupova, I. O. et al. Capabilities of cephalometric methods to study X-rays in three-dimensional space (Review). Sovrem. Tehnol. Med. 16, 62–73 (2024).
Polizzi, A. & Leonardi, R. Automatic cephalometric landmark identification with artificial intelligence: An umbrella review of systematic reviews. J. Dent. 146, 105056 (2024).
Polizzi, A., Boato, M., Serra, S., D’Antò, V. & Leonardi, R. Applications of artificial intelligence in orthodontics: A bibliometric and visual analysis. Clin. Oral Investig. 29, 65 (2025).
Gill, A. et al. Artificial Intelligence user interface preferences in radiology: A scoping review. J. Med. Imaging Radiat. Sci. 56, 101866 (2025).
Jiang, Y. et al. Automatic identification of hard and soft tissue landmarks in cone-beam computed tomography via deep learning with diversity datasets: A methodological study. BMC Oral Health 25, 505 (2025).
Gupta, A., Kharbanda, O. P., Sardana, V., Balachandran, R. & Sardana, H. K. A knowledge-based algorithm for automatic detection of cephalometric landmarks on CBCT images. Int. J. Comput. Assist. Radiol. Surg. 10, 1737–1752 (2015).
Dot, G. et al. Accuracy and reliability of automatic three-dimensional cephalometric landmarking. Int. J. Oral Maxillofac. Surg. 49, 1367–1378 (2020).
Dot, G. et al. Three-dimensional cephalometric landmarking and Frankfort Horizontal Plane construction: Reproducibility of conventional and novel landmarks. J. Clin. Med. 10, 5303 (2021).
Ghowsi, A. et al. Automated landmark identification on cone-beam computed tomography: Accuracy and reliability. Angle Orthod. 92, 642–654 (2022).
Baldini, B., Cavagnetto, D., Baselli, G., Sforza, C. & Tartaglia, G. M. Cephalometric measurements performed on CBCT and reconstructed lateral cephalograms: A cross-sectional study providing a quantitative approach of differences and bias. BMC Oral Health 22, 98 (2022).
Dot, G. et al. Automatic 3-dimensional cephalometric landmarking via deep learning. J. Dent. Res. 101, 1380–1387 (2022).
Gupta, A., Kharbanda, O. P., Sardana, V., Balachandran, R. & Sardana, H. K. Accuracy of 3D cephalometric measurements based on an automatic knowledge-based landmark detection algorithm. Int. J. Comput. Assist. Radiol. Surg. 11, 1297–1309 (2016).
Park, J. et al. Clinical validity and precision of deep learning-based cone-beam computed tomography automatic landmarking algorithm. Imaging Sci. Dent. 54, 240–250 (2024).
Jung, Y. E., Suh, H., Park, J. & Oh, H. Accuracy and reliability of automated landmark identification and cephalometric measurements on cone beam computed tomography using Invivo software. Angle Orthod. 95, 362–370 (2025).
Tao, L. et al. Automatic craniomaxillofacial landmarks detection in CT images of individuals with dentomaxillofacial deformities by a two-stage deep learning model. BMC Oral Health 23, 876 (2023).
Wang, C. W. et al. A benchmark for comparison of dental radiography analysis algorithms. Med. Image Anal. 31, 63–76 (2016).
Santos, R., De Martino, J. M., Haiter Neto, F. & Passeri, L. A. Influence of different setups of the Frankfort horizontal plane on 3-dimensional cephalometric measurements. Am. J. Orthod. Dentofacial Orthop. 152, 242–249 (2017).
Santos, R., De Martino, J. M., Haiter Neto, F. & Passeri, L. A. Cone beam computed tomography-based cephalometric norms for Brazilian adults. Int. J. Oral Maxillofac. Surg. 47, 64–71 (2018).
Ajmera, D. H., Singh, P., Leung, Y. Y., Khambay, B. S. & Gu, M. Establishment of the mid-sagittal reference plane for three-dimensional assessment of facial asymmetry: A systematic review : Establishment of the mid-sagittal reference plane: A systematic review. Clin. Oral Investig. 28, 242 (2024).
Tao, L. et al. Craniomaxillofacial landmarks detection in CT scans with limited labeled data via semi-supervised learning. Heliyon 10, e34583 (2024).
SHAPIRO, S. S. An Analysis of Variance Test for Normality (Complete Samples). BIOMETRIKA 52, 591–611 (1965).
Bland, J. M. & Altman, D. G. Measuring agreement in method comparison studies. Stat. Methods Med. Res. 8, 135–160 (1999).
Raj, G., Raj, M. & Saigo, L. Accuracy of conventional versus cone-beam CT-synthesised lateral cephalograms for cephalometric analysis: A systematic review. J. Orthod. 51, 160–176 (2024).
van Bunningen, R. H. et al. Precision of orthodontic cephalometric measurements on ultra low dose-low dose CBCT reconstructed cephalograms. Clin. Oral Investig. 26, 1543–1550 (2022).
Naji, P., Alsufyani, N. A. & Lagravère, M. O. Reliability of anatomic structures as landmarks in three-dimensional cephalometric analysis using CBCT. Angle Orthod. 84, 762–772 (2014).
Koo, T. K. & Li, M. Y. A guideline of selecting and reporting intraclass correlation coefficients for reliability research. J. Chiropr. Med. 15, 155–163 (2016).
Shrout, P. E. & Fleiss, J. L. Intraclass correlations: Uses in assessing rater reliability. Psychol. Bull. 86, 420–428 (1979).
Alt, S., Gajny, L., Tilotta, F., Schouman, T. & Dot, G. Automated landmark-based mid-sagittal plane: Reliability for 3-dimensional mandibular asymmetry assessment on head CT scans. Clin. Oral Investig. 29, 311 (2025).
Lagravère, M. O. et al. Intraexaminer and interexaminer reliabilities of landmark identification on digitized lateral cephalograms and formatted 3-dimensional cone-beam computerized tomography images. Am. J. Orthod. Dentofacial Orthop. 137, 598–604 (2010).
Kim, D. H., Li, Y. & Lee, K. C. Three-dimensional cephalometric evaluation of the craniofacial morphology in Korean population utilizing cone-beam computed tomography. Korean J. Orthod. 55, 254–265 (2025).
Park, J. et al. Reliability of 3D dental and skeletal landmarks on CBCT images. Angle Orthod. 89, 758–767 (2019).
Hartoonian, S., Hosseini, M., Yousefi, I., Mahdian, M. & Ghazizadeh Ahsaie, M. Applications of artificial intelligence in dentomaxillofacial imaging: A systematic review. Oral Surg. Oral Med. Oral Pathol. Oral Radiol. 138, 641–655 (2024).
Khanehmasjedi, M., Naseri, M. A. & Khanehmasjedi, S. Comparison of the soft tissue orthodontic analysis measurements between conventional lateral cephalograms and CBCT derived lateral cephalograms. Allied Academies. 28, 1087–1090 (2017).
Acknowledgements
The authors thank the participants of this study for their willingness to participate and their insightful contributions.
Funding
This study was supported by the Joint Funds for the innovation of science And Technology of Fujian province (Grant number:2024Y9154); Science and Technology Achievement Transformation Fund of The First Affiliated Hospital of Fujian Medical University (Grant number: 2025FY-ZH-09); Fujian Provincial Health Technology Project (Grant number: 2025GGA044); Fujian Medical University 2024 Undergraduate Education and Teaching Research Project (Grant number: J24043);
Author information
Authors and Affiliations
Contributions
Yan Jiang contributed to conceptualization, data curation, investigation, methodology, and original draft preparation; Rana and Canyang Jiang contributed to data curation and original draft preparation; You Wu contributed to data curation and formal analysis; Jianping Huang, Xinghao Wang and Xiaojing Zhang contributed to resources and software; Xiaohong Huang, Bin Shi and Lisong Lin contributed to resources; Yan Jiang and Li Huang contributed to conceptualization, project administration, and manuscript review and editing.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Jiang, Y., AL-Mohana, R.A.A.M., Jiang, C. et al. Clinical accuracy of cephalometric analysis using deep learning–based automated landmark identification on CBCT in class I and class II malocclusions. Sci Rep (2026). https://doi.org/10.1038/s41598-026-41408-3
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-41408-3
