Related Experiment Video
Updated: Jun 25, 2025
05:49
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
824
Evaluating tooth segmentation accuracy and time efficiency in CBCT images using artificial intelligence: A systematic
Bilu Xiang1, Jiayi Lu2, Jiayi Yu2
1School of Dentistry, Shenzhen University Medical School, Shenzhen University, Shenzhen 518000, China.
Journal of Dentistry
|May 20, 2024
Summary
Artificial intelligence (AI) accurately segments teeth in 3D cone-beam computed tomography (CBCT) images, significantly reducing segmentation time. This enhances dental procedures like treatment planning and implant placement.
Area of Science:
- Dental Imaging
- Artificial Intelligence
- Medical Image Analysis
Background:
- Accurate tooth segmentation is crucial for various dental procedures.
- Manual segmentation is time-consuming and prone to variability.
- Advancements in AI offer potential for automated and efficient segmentation.
Purpose of the Study:
- To systematically review and meta-analyze the performance of AI-based tooth segmentation in 3D CBCT images.
- To compare the accuracy and efficiency of AI methods against manual segmentation.
- To identify the most effective AI models for this task.
Main Methods:
- Comprehensive literature search across major scientific databases (PubMed, Embase, Scopus, Web of Science, IEEE Explore).
- Inclusion of 35 studies in the systematic review after screening 5642 entries.
- Meta-analysis focused on Dice Similarity Coefficient (DSC) for accuracy and time efficiency.
Main Results:
- AI models, particularly U-net convolutional neural networks, are widely used.
- Pooled DSC score for AI-based tooth segmentation was 0.95 (95% CI 0.94-0.96), indicating high accuracy.
- AI segmentation time ranged from 1.5 seconds to 3.4 minutes, significantly faster than manual methods.
Conclusions:
- AI demonstrates high accuracy and efficiency for tooth segmentation in CBCT images.
- AI reduces processing time, improving clinical workflow.
- Future research should address metal artifact correction and segmentation across different imaging modalities.
