Related Experiment Video
Updated: Aug 24, 2025
10:23
Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
Published on: September 8, 2023
3.0K
Artificial intelligence system for automated landmark localization and analysis of cephalometry
Fulin Jiang, Yutong Guo1, Cai Yang1
1Department of Orthodontics, State Key Laboratory of Oral Diseases, West China School of Stomatology, West China Hospital of Stomatology, Sichuan University, Chengdu, China.
Dento Maxillo Facial Radiology
|October 24, 2022
Summary
This study developed an artificial intelligence (AI) system for automated cephalometric analysis, achieving high accuracy in landmark localization. The AI system enhances diagnostic efficiency for orthodontic and orthognathic procedures.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Orthodontics
Background:
- Cephalometric analysis is crucial for orthodontic diagnosis and treatment planning.
- Current AI systems for cephalometric analysis face limitations due to diverse patient malocclusions and limited training data.
Purpose of the Study:
- To develop a robust and clinically applicable artificial intelligence (AI) system for automatic cephalometric analysis.
- To improve the accuracy and efficiency of landmark localization and classification in cephalograms.
Main Methods:
- Collected 9870 cephalograms from 20 institutions, featuring diverse malocclusions and radiography machines.
- Trained a two-stage convolutional neural network (CNN) AI system with manually annotated landmarks.
- Involved over 100 orthodontists to refine AI landmark predictions and retrain the system.
Main Results:
- Achieved an average landmark prediction error of 0.94 ± 0.74 mm.
- Attained an average classification accuracy of 89.33% for cephalometric measurements.
Conclusions:
- An AI system based on CNN was developed for automatic landmark localization and cephalometric measurement classification.
- The system demonstrates significant potential for enhancing diagnostic efficiency in clinical orthodontic settings.
