Academic Journal
Feasibility of predicting vertical cephalometric angles from panoramic radiographs using deep learning.
| Τίτλος: | Feasibility of predicting vertical cephalometric angles from panoramic radiographs using deep learning. |
|---|---|
| Συγγραφείς: | Ashkan A; Department of Orthodontics, School of Dentistry, Hamadan University of Medical Sciences, Hamadan, Iran., Behnaz M; Department of Orthodontics, School of dentistry, Shahid Beheshti University of medical sciences, Tehran, Iran., Taramsari AR; School of Health and Medical Sciences, City St George's, University of London, London, United Kingdom., Morvaridi Farimani R; Department of Rehabilitative and Reconstructive Dentistry, University of Louisville, Louisville, KY, United States of America., Radmard B; School of Health and Medical Sciences, City St George's, University of London, London, United Kingdom., Farhadian M; Department of Biostatistics, School of Public Health, Hamadan University of Medical Sciences, Hamadan, Iran., Motie P; Medical Image and Signal Processing Research Center, Medical University of Isfahan, Isfahan, Iran. Electronic address: Pm.motie@gmail.com. |
| Πηγή: | International orthodontics [Int Orthod] 2026 Sep; Vol. 24 (3), pp. 101156. Date of Electronic Publication: 2026 Feb 26. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Masson Country of Publication: France NLM ID: 101184882 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1879-680X (Electronic) Linking ISSN: 17617727 NLM ISO Abbreviation: Int Orthod Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: Paris : Masson, c2003- |
| Ιατρικοί όροι (MeSH): | Cephalometry*/methods , Radiography, Panoramic*/methods , Deep Learning*, Mandible/diagnostic imaging ; Humans ; Retrospective Studies ; Convolutional Neural Networks ; Feasibility Studies ; Female ; Male ; Adolescent |
| Περίληψη: | Introduction: Early identification of vertical skeletal discrepancies is essential for orthodontic diagnosis and treatment planning. Since panoramic radiographs (OPGs) are more routinely obtained than lateral cephalometric radiographs (LCR), this study evaluated whether artificial intelligence could predict vertical skeletal angles on OPGs. Methods: LCRs and OPGs of 715 patients were retrospectively collected from four imaging centre (2022-2025). LCRs were traced using WebCeph to obtain reference measurements of the Frankfort-mandibular plane angle (FMA), gonial angle, and Sum of Björk. Multiple convolutional neural network (CNN) architectures (EfficientNet-B3, DenseNet121/169, ResNet-50/101, VGG16/19) were trained to predict these parameters from corresponding OPGs. Ensemble averaging was also employed as a non-learned aggregation strategy. Model performance was evaluated using mean absolute error (MAE) and the coefficient of determination (R2). Wilcoxon signed-rank test assessed the differences in predictive performance. Inter-model agreement was quantified using intraclass correlation coefficients (ICC). Gradient-weighted Class Activation Mapping (Grad-CAM) was used for model interpretability. Results: Ensemble averaging achieved the highest predictive accuracy across all angular parameters, with MAE values of 2.53°±0.08 for FMA, 3.16°±0.10 for the gonial angle, and 3.04°±0.09 for the Sum of Björk. High agreement was observed among the CNN architectures for all measurements (P<0.001). Grad-CAM visualizations indicated that predictions primarily relied on the gonial angle region, followed by the condylar area and mandibular ramus. Conclusion: Deep learning demonstrates promising potential for estimating vertical angular measurements on OPGs. Although current prediction errors preclude replacement of cephalometric analysis, the incorporation of larger datasets, geometry-aware models, and external validation will help improving predictive accuracy. (Copyright © 2026 CEO. Published by Elsevier Masson SAS. All rights reserved.) |
| Competing Interests: | Disclosure of interest the authors declare that they have no competing interest. |
| Contributed Indexing: | Keywords: Artificial intelligence; Deep learning; Frankfort–mandibular plane angle; Gonial angle; Panoramic radiography; Sum of Björk; Vertical skeletal pattern |
| Entry Date(s): | Date Created: 20260226 Date Completed: 20260820 Latest Revision: 20260820 |
| Update Code: | 20260821 |
| DOI: | 10.1016/j.ortho.2026.101156 |
| PMID: | 41747359 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1879-680X |
|---|---|
| DOI: | 10.1016/j.ortho.2026.101156 |