Related Experiment Video
Updated: Sep 13, 2025
09:10
Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
Published on: August 5, 2021
1.9K
Automatic restoration and reconstruction of defective tooth based on deep learning technology
Juhao Wu1, Yuanchang Huang1, Jiayan He1
1School of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou, 510006, China.
BMC Oral Health
|August 3, 2025
Summary
This study introduces a deep learning framework for automatic tooth restoration and 3D reconstruction. The novel method significantly improves accuracy and efficiency in creating detailed dental models.
Area of Science:
- Biomedical Engineering
- Computer Vision
- Dental Technology
Background:
- Accurate tooth morphology restoration is vital for dentistry and forensic science.
- Traditional methods like manual wax modeling and CAD lack accuracy, personalization, and efficiency.
- A novel deep learning framework addresses these limitations for automatic tooth reconstruction.
Purpose of the Study:
- To develop an innovative and efficient deep learning-based framework for automatic tooth morphology restoration and reconstruction.
- To overcome the limitations of traditional methods in accuracy, personalization, and efficiency.
Main Methods:
- Input an RGB image of a defective tooth into a restoration network to fill missing regions.
- Convert the restored RGB image to grayscale for preprocessing.
- Utilize a 3D reconstruction network with the grayscale image to generate a detailed 3D mesh model.
Main Results:
- The deep learning framework demonstrates superior restoration quality, reconstruction accuracy, generalization, and inference speed (12s/image).
- An improved ResNet50-based Pixel2Mesh enhanced average F-Score, CD, and EMD by 26.5%, 34.7%, and 22.3%, respectively, compared to the original.
- The method achieves high performance in reconstructing detailed 3D tooth models.
Conclusions:
- The proposed deep learning approach offers a personalized, intelligent, and efficient solution for tooth restoration and reconstruction.
- This technology provides a valuable tool for dental diagnostics and treatment planning.
- The framework represents a significant advancement in automated dental modeling.
