Tooth and Alveolar Bone Segmentation From Dental Computed Tomography Images

Area of Science:

• Biomedical Imaging
• Orthodontics
• Computer-Aided Design

Background:

• Accurate 3D models of the tooth-alveolar bone complex are crucial for computer-aided orthodontic treatment planning and simulation.
• Previous segmentation methods primarily focused on teeth, neglecting alveolar bone, which can lead to undesired treatment side effects.

Purpose of the Study:

• To develop and validate a novel method for segmenting both teeth and alveolar bone from dental computed tomography (CT) images.
• To enable the reconstruction of accurate 3D models of the tooth-alveolar bone complex for enhanced orthodontic applications.

Main Methods:

• A global convex level set model was employed to extract the connected region of teeth and alveolar bone from CT images.
• Individual tooth and alveolar bone components were separated using Radon transform and a local level set model.

Main Results:

• The proposed method successfully segmented both teeth and alveolar bone from dental CT images.
• The segmentation accuracy outperformed existing state-of-the-art tooth segmentation techniques.

Conclusions:

• The developed method provides accurate segmentation of the tooth-alveolar bone complex.
• This advancement facilitates precise 3D model reconstruction for improved computer-aided orthodontic treatment planning and simulation.