Automatic tooth segmentation of dental mesh using a transverse plane

Area of Science:

• Computer-aided dentistry
• Medical image analysis
• Geometric modeling

Background:

• Accurate segmentation of dental structures is crucial for digital dentistry applications.
• Manual segmentation is time-consuming and prone to inaccuracies.
• Existing automated methods often require user input or lack robustness.

Purpose of the Study:

• To develop a fully automatic method for segmenting gingiva and individual teeth from dental meshes.
• To preserve the shape of individual teeth during segmentation.
• To demonstrate the robustness of the proposed method across various dental models.

Main Methods:

• Defining a transverse plane to create a cross-section of tooth surfaces.
• Projecting and partitioning upper vertices onto the transverse plane for individual tooth separation.
• Utilizing region growing for segmenting remaining non-classified mesh parts.
• Ensuring no user interaction is needed for feature point or boundary identification.

Main Results:

• Successful automatic separation of gingiva and individual teeth from dental meshes.
• Preservation of individual tooth shapes throughout the segmentation process.
• Demonstrated robustness of the method on multiple dental mesh datasets.
• Elimination of the need for manual feature point or boundary marker input.

Conclusions:

• The proposed automatic segmentation method effectively separates teeth and gingiva from dental meshes.
• The technique preserves tooth morphology, crucial for accurate digital dental applications.
• This fully automated approach enhances efficiency and consistency in dental digital workflows.