Facial morphology prediction after complete denture restoration based on principal component analysis

Area of Science:

• Computer-aided surgery
• Biomedical engineering
• Dental restoration

Background:

• Accurate facial shape prediction is crucial for post-surgery treatment planning in complete denture restoration.
• Current methods rely on subjective judgment, lacking a quantitative basis for scientific analysis.

Purpose of the Study:

• To develop a quantitative, computer-based method for predicting facial morphology after dental restoration.
• To enhance treatment planning by providing interactive and personalized facial shape predictions.

Main Methods:

• Constructing a curvature feature template to represent facial deformation.
• Utilizing principal component analysis (PCA) to build an elastic deformation model for skin tissue.
• Applying Laplacian deformation technology for 3D facial model reconstruction.

Main Results:

• The proposed method allows interactive adjustment of facial deformation via shape parameters.
• Experimental results show interactive prediction of facial models.
• The average deviation between predicted and post-treatment models is within +/- 2.102 mm.

Conclusions:

• This PCA-based method offers an objective and quantitative approach to facial morphology prediction.
• The interactive nature of the model caters to diverse clinical needs and preferences.
• The technology provides an intuitive digital 3D model for improved surgical planning and patient outcomes.