Related Experiment Video
Updated: Aug 24, 2025
09:10
Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
Published on: August 5, 2021
1.8K
[Virtual reconstruction and clinical verification of maxillary defect based on deep learning]
1Department of Oral and Maxillofacial Surgery, West China Hospital of Stomatology, Sichuan University & State Key Laboratory of Oral Diseases & National Clinical Research Center for Oral Diseases, Chengdu 610041, China.
Summary
This study developed a generative adversarial network (GAN) model for virtual reconstruction of maxillary defects. The GAN method demonstrated superior accuracy for unilateral defects compared to mirroring and enabled reconstruction of midspan defects.
Area of Science:
- Oral and Maxillofacial Surgery
- Medical Imaging
- Artificial Intelligence in Medicine
Context:
- Maxillary defects pose significant challenges in reconstructive surgery.
- Accurate virtual reconstruction is crucial for pre-surgical planning and implant design.
- Existing methods like mirroring have limitations, especially for complex defects.
Purpose:
- To develop and validate a generative adversarial network (GAN) model for virtual reconstruction of maxillary defects.
- To compare the efficacy of GAN-based reconstruction with traditional mirroring techniques.
- To provide a clinical reference for reconstructing both unilateral and midspan maxillary defects.
Summary:
- A GAN model was trained using CT data from healthy and defected maxillas.
- The GAN method showed significantly better quantitative (Dice similarity coefficient, Hausdorff distance) and qualitative results for unilateral defects compared to mirroring.
- The model successfully performed virtual reconstruction for midspan maxillary defects, a capability lacking in the mirroring technique.
Impact:
- Establishes a novel, effective virtual reconstruction method for complex maxillary defects.
- Offers a potential improvement over conventional mirroring techniques in pre-surgical planning.
- Enhances the ability to reconstruct challenging midspan maxillary defects, improving patient outcomes.
