Related Experiment Video
Updated: Jun 27, 2025
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
2.7K
Semi or fully automatic tooth segmentation in CBCT images: a review
Qianhan Zheng1, Yu Gao1, Mengqi Zhou1
1Stomatology Hospital, Zhejiang University School of Medicine, Hangzhou, China.
Peerj. Computer Science
|April 25, 2024
Summary
This review analyzes 55 studies on tooth segmentation from cone beam computed tomography (CBCT) data. It highlights advancements in automated methods, aiming to improve accuracy and reduce manual effort in dental workflows.
Area of Science:
- Dentistry
- Medical Imaging
- Computer Vision
Background:
- Cone beam computed tomography (CBCT) is essential in modern dentistry.
- Tooth segmentation is a critical step in digital dental workflows.
- Manual segmentation is time-consuming and labor-intensive.
Purpose of the Study:
- To review and analyze existing tooth segmentation methods from CBCT data.
- To discuss the effectiveness, advantages, and disadvantages of various approaches.
- To explore improvements for irregular morphology and fuzzy boundaries.
Main Methods:
- Comprehensive literature review of 55 articles.
- Classification and discussion of different tooth segmentation techniques.
- Analysis of image segmentation algorithms for refinement.
Main Results:
- Identified various fast and accurate automated tooth segmentation methods.
- Evaluated the strengths and weaknesses of existing approaches.
- Highlighted potential for improving accuracy and robustness.
Conclusions:
- Automated tooth segmentation methods show promise for reducing manual effort.
- Refinement of algorithms can address challenges like irregular morphology.
- Further research is needed to overcome existing challenges and enhance future directions.
