Extraction of Tooth Cusps based on DBSCAN Density Clustering and Neighborhood Search Algorithm

Area of Science:

• Computer-aided dentistry
• Computational geometry
• Medical imaging analysis

Background:

• Accurate tooth cusp extraction is crucial for virtual tooth surgery and cosmetic dental work evaluation.
• Existing methods may lack precision or efficiency in identifying key dental landmarks.

Purpose of the Study:

• To develop and validate a new tooth cusp extraction method for 3D tooth models.
• To enhance the accuracy and speed of cusp extraction for virtual dental applications.

Main Methods:

• Integrated DBSCAN (density-based spatial clustering of applications with noise) with a neighborhood search algorithm.
• Utilized point cloud height and curvature for initial screening.
• Employed DBSCAN for feature region segmentation and neighborhood search for apex localization.

Main Results:

• The proposed method demonstrated superior recall and accuracy rates compared to watershed algorithm-based methods.
• Achieved higher extraction speed and precision than manual extraction techniques.
• Successfully extracted tooth cusps from 3D cloud-point tooth models.

Conclusions:

• The novel tooth cusp extraction method is effective and efficient for virtual dental surgery.
• This approach offers significant improvements over traditional and manual techniques.
• Enhances the potential for precise cosmetic dental work evaluation.