Related Experiment Video
Updated: Aug 12, 2026
A Finite Element Approach for Locating the Center of Resistance of Maxillary Teeth
Published on: April 8, 2020
A level-set based approach for anterior teeth segmentation in cone beam computed tomography images
Dong Xu Ji1, Sim Heng Ong2, Kelvin Weng Chiong Foong3
1NUS Graduate School for Integrative Sciences and Engineering, National University of Singapore, Singapore; Department of Electrical and Computer Engineering, National University of Singapore, Singapore; Faculty of Dentistry, National University of Singapore, Singapore.
This study presents an improved level-set method for accurate tooth segmentation from cone beam CT (CBCT) dental images. The novel approach enhances 3D dental imaging by incorporating shape and thickness constraints for precise tooth extraction.
Area of Science:
- Dentistry
- Medical Imaging
- Computer Vision
Background:
- Cone beam CT (CBCT) is widely used in dentistry for 3D imaging due to high resolution and lower radiation than multi-slice CT (MSCT).
- Segmenting teeth from CBCT is challenging due to lower bone signal-to-noise ratios compared to MSCT.
Purpose of the Study:
- To develop an advanced level-set method for accurate tooth shape extraction from CBCT images.
- To address the complexities of tooth segmentation in CBCT data.
Main Methods:
- A variational level-set framework was enhanced with three novel energy terms.
- Dual intensity distribution models were used to differentiate tooth and surrounding regions.
- A robust shape prior and tooth dentine wall thickness constraint were implemented.
Main Results:
- The proposed level-set method demonstrated improved segmentation accuracy compared to existing techniques.
- The novel energy terms effectively handled challenges like leakage and shrinkage during segmentation.
- Accurate extraction of tooth shape from CBCT images was achieved.
Conclusions:
- The enhanced level-set method provides a more accurate and robust solution for tooth segmentation in CBCT imaging.
- This technique has the potential to improve 3D dental diagnostics and treatment planning.
- The incorporation of shape and thickness constraints is crucial for reliable CBCT tooth segmentation.
