Related Experiment Video
Updated: Sep 29, 2025
10:23
Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
Published on: September 8, 2023
3.1K
Effectiveness of Human-Artificial Intelligence Collaboration in Cephalometric Landmark Detection
Van Nhat Thang Le1,2,3,4, Junhyeok Kang5, Il-Seok Oh5
1Department of Pediatric Dentistry and Institute of Oral Bioscience, School of Dentistry, Jeonbuk National University, Jeonju 54896, Korea.
Journal of Personalized Medicine
|March 25, 2022
Summary
Human-AI collaboration enhances cephalometric landmark detection for orthodontic diagnosis. Combining beginner dental students with artificial intelligence improved accuracy and success rates in identifying key facial points.
Area of Science:
- Dentistry
- Artificial Intelligence
- Medical Imaging
Background:
- Cephalometric landmark detection is crucial for orthodontic diagnosis and malocclusion analysis.
- Previous research primarily focused on comparing AI and human accuracy in landmark identification.
- The impact of human-AI collaboration on cephalometric landmark detection remains unevaluated.
Purpose of the Study:
- To evaluate the effectiveness of human-AI collaboration in identifying cephalometric landmarks.
- To assess the impact of artificial intelligence assistance on beginner dental students' landmark detection performance.
Main Methods:
- Trained a deep anatomical context feature learning (DACFL) model on 1193 cephalograms for 41 target landmarks.
- Evaluated the DACFL model's performance using mean radial error (MRE) and successful detection rate (SDR).
- Assessed the effect of beginner-AI collaboration on 10 test images involving 20 dental students.
Main Results:
- The DACFL model achieved an average MRE of 1.87 ± 2.04 mm and an SDR of 73.17% within a 2 mm threshold.
- Beginner-AI collaboration significantly improved the SDR by 5.33% and the successful classification rate (SCR) by 8.38% compared to beginners alone.
- The collaboration demonstrated a positive impact on the accuracy and reliability of landmark detection.
Conclusions:
- Beginner-AI collaboration is effective for improving cephalometric landmark detection in orthodontics.
- This approach offers a promising tool to enhance diagnostic accuracy for dental professionals.
- Further research is recommended to explore the benefits of collaboration between orthodontists and AI.
