What question did this study set out to answer?

This research aims to evaluate the clinical accuracy of automated cephalometric analysis and its relationship with algorithmic precision.

February 26, 2026Scientific ReportsOpen Access

Clinical accuracy of cephalometric analysis using deep learning–based automated landmark identification on CBCT in class I and class II malocclusions

View Full Paper

Ask AI

Bookmark

Authors

YJYan JiangFujian Medical University RARana A. A. M. AL-MohanaFujian Medical University CJCanyang JiangFujian Medical University

Discussion

Member takes

Implication

Retrospective analysis demonstrates deep learning improves cephalometric measurements in class I and II malocclusions, suggesting clinical applicability with minor manual refinement.

Key Points

This research aims to evaluate the clinical accuracy of automated cephalometric analysis and its relationship with algorithmic precision.
Used retrospective cone-beam computed tomography (CBCT) scans for analysis.
Developed an automated landmark identification model with a U-Net architecture.
Compared 71 cephalometric measurements from AI-generated landmarks with manually annotated landmarks in 75 CBCT scans.
Performed statistical analyses including paired t-tests, intraclass correlation coefficients, and Bland–Altman analysis.
9 out of 71 measurements showed significant differences, but all were clinically negligible (≤ 1 mm/°).
59.15% of AI-based measurements achieved clinical interchangeability with ground truth within ± 2.0 mm/°.
All 26 parameters with MRE below 2 mm were within clinically acceptable limits, while angular measurements lacked correlation with MRE.

Cite This Study

Jiang et al. (2026) studied this question.

synapsesocial.com/papers/699f95ba1bc9fecf3dab3c95 https://doi.org/10.1038/s41598-026-41408-3

View Full Paper

Ask AI

Bookmark

Implication

Retrospective analysis demonstrates deep learning improves cephalometric measurements in class I and II malocclusions, suggesting clinical applicability with minor manual refinement.

Clinical accuracy of cephalometric analysis using deep learning–based automated landmark identification on CBCT in class I and class II malocclusions

Discussion

Member takes

Implication

Key Points

Cite This Study

Clinical accuracy of cephalometric analysis using deep learning–based automated landmark identification on CBCT in class I and class II malocclusions

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider