Related Experiment Video
Updated: Apr 14, 2026
05:49
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
1.7K
Quantitative Assessment of Third Molar Extraction Difficulty and Nerve Injury Risk Using Artificial Intelligence and
Jihyeong Ko1, Sasi Sooksatra1, Seungmin Kim1
1Department of Biomedical Engineering, Chonnam National University, Yeosu, 59626, Korea.
Annals of Biomedical Engineering
|April 12, 2026
Summary
This study developed an AI-powered system using panoramic X-rays to precisely assess third molar (3M) extraction difficulty and nerve damage risk. The new scoring system aids dentists in surgical planning for impacted teeth.
Area of Science:
- Dentistry
- Medical Imaging
- Artificial Intelligence
Background:
- Third molar (3M) extraction complexity is influenced by tooth position and surrounding tissues.
- Accurate assessment of 3M extraction difficulty is crucial for surgical planning and risk mitigation.
Purpose of the Study:
- To develop a novel, precise scoring system for third molar (3M) extraction difficulty.
- To leverage AI and image computational techniques on panoramic radiography for enhanced surgical assessment.
Main Methods:
- Utilized AI deep learning models to detect and segment the mandibular canal (MC), inner area of alveolar bone (IAAB), and 3M from panoramic X-rays.
- Developed algorithms to score 3M inclination, impaction depth, and proximity to the MC.
- Summed scores to create a difficulty index ranging from very easy to very difficult.
Main Results:
- High average precisions for 3M detection models (0.93-0.97).
- Accurate performance in classifying 3M inclination (0.8544), impaction depth (0.9515), and M3M-MC proximity (0.8991).
Conclusions:
- The AI-driven scoring model assists dentists in evaluating 3M extraction risks and planning surgeries.
- Further research with diverse data and improved AI models is needed for clinical application.
