Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 23, 2025European journal of medical researchOpen Access

Accuracy and reliability of 3D cephalometric landmark detection with deep learning

View Full Paper
Ask AI
Bookmark
Share

Authors

BLBoyan LiuCLChang LiuYXYutao Xiong

Discussion

Loading...

Member takes

Overview

Observational analysis improved detection accuracy in craniofacial growth, suggesting deep learning may aid orthodontic procedures.

Key Points

  • The model achieved high precision with a mean radial error consistently below 1.3 mm across complex conditions, including malocclusion.
  • Comparison tests showed no significant differences in detection rates between SCT and CBCT, with bone landmarks exhibiting higher accuracy than dental landmarks.
  • Application of the 3D U-Net architecture enabled a 15.9% and 28.9% enhancement in proficiency for senior and junior specialists in landmark localization.
  • Results indicate the AI-driven model's potential as a computer-aided tool for improving landmark detection in orthodontic and orthognathic procedures.

Cite This Study

Liu et al. (2025) studied this question.

synapsesocial.com/papers/68fa32a40df2e6cd2f742042https://doi.org/10.1186/s40001-025-03198-8
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Clinical accuracy of cephalometric analysis using deep learning–based automated landmark identification on CBCT in class I and class II malocclusions2026 · 7 citations
  2. 2An Automated Approach for Anatomical Landmark Detection in Clinical 3D Facial Images using Convolutional Neural Networks2025
  3. 3Deep learning for 3D cephalometric landmarking with heterogeneous multi-center CBCT dataset2024 · 19 citations
  4. 4Artificial-Intelligence-Based Cephalometric Landmark Detection in Lateral Cephalograms2026
  5. 5Attention-Base deep learning for 3D craniofacial soft tissue landmark detection and diagnosis in orthodontics2025 · 3 citations