Implant Model Generation Method for Mandibular Defect Based on Improved 3D Unet
Source abstract
Abstract
The accurate reconstruction of a defective part of the mandible is a time-consuming task in maxillofacial surgery. In order to design accurate 3D implants quickly, a method for generating a mandibular defect implant model based on deep learning was proposed. First, an algorithm for generating a defective mandible 3D model randomly from a complete mandible 3D model was proposed due to the insufficiency of 3D models. Then a mandible 3D model dataset that consists of defective mandible 3D models and a complete mandible 3D model was constructed. An improved 3D Unet network that combines residual structure and dilated convolution was designed to generate a repaired mandibular model automatically. Finally, a mandibular defect implant model was generated using the reconstruction–subtraction strategy and was validated on the constructed dataset. Compared with the other three networks (3D Unet, 3D RUnet, and 3D DUnet), the proposed method obtained the best results. The Dice, IoU, PPV, and Recall for mandible repair reached 0.9873, 0.9750, 0.9850, and 0.9897, respectively, while those for implants reached 0.8018, 0.6731, 0.7782, and 0.8330. Statistical analysis was carried out on the experimental results. Compared with other methods, the P value of the method proposed in this paper was less than 0.05 for most indicators, which is a significant improvement.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Anatomy and Medical Technology · Medical Imaging and Analysis · Dental Implant Techniques and Outcomes
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education, Guizhou University, Guiyang 550025, China
Funding
Guizhou Science and Technology Support Program · Guizhou Science and Technology Plan Project
References (29)
Show source-provided references
1. Oral manifestations in paediatric patients with hepatobiliary diseases: A review
2. Analysis of the pattern of Oral and Maxillofacial Trauma in the world: A Systematic Review and Meta-Analysis
3. 3D-printed PEEK implant for mandibular defects repair-a new method10.1016/j.jmbbm.2021.104335 ↗
4. Critical-size bone defects: Is there a consensus for diagnosis and treatment?10.1097/BOT.0000000000001115 ↗
5. Valenti, C., Federici, M.I., Masciotti, F., Marinucci, L., Xhimitiku, I., Cianetti, S., and Pagano, S. Mechanical properties of 3D-printed prosthetic materials compared with milled and conventional processing: A systematic review and meta-analysis of in vitro studies, J. Prosthet. Dent., in press.
6. Cheng, K.J. (2019). Optimal Design and Fabrication of a Hybrid Structures Implant for Surgical Mandibular Reconstruction. [Ph.D. Thesis, Zhejiang University of Technology].
7. Computer-assisted surgery for reconstruction of complex mandibular defects using os-teomyocutaneous microvascular fibular free flaps: Use of a skin paddle-outlining guide for soft-tissue reconstruction. A technical report10.1016/j.jcms.2018.11.018 ↗
8. Prakoso, A.T., Basri, H., Adanta, D., Yani, I., Ammarullah, M.I., Akbar, I., Ghazali, F.A., Syahrom, A., and Kamarul, T. (2023). The Effect of Tortuosity on Permeability of Porous Scaffold. Biomedicines, 11.10.3390/biomedicines11020427 ↗
9. Huang, S.-N., Shie, M.-Y., Shen, Y.-W., Hsu, J.-T., Huang, H.-L., and Fuh, L.-J. (2019). Biomechanical assessment of design parameters on a self-developed 3D-printed titanium-alloy reconstruction/prosthetic implant for mandibular segmental osteotomy defect. Metals, 9.10.3390/met9050597 ↗
10. Use of a 3-dimensional custom-made porous titanium prosthesis for mandibular body reconstruction with prosthetic dental rehabilitation and lipofilling10.1016/j.joms.2018.12.026 ↗
11. A semi-automatic hybrid approach for defective skulls reconstruction10.14733/cadaps.2020.190-204 ↗
12. Planning of skull reconstruction based on a statistical shape model combined with geometric morphometrics10.1007/s11548-017-1674-6 ↗
13. Analysis of contact pressure in a 3D model of dual-mobility hip joint prosthesis under a gait cycle10.1038/s41598-023-30725-6 ↗
14. Automatic skull defect restoration and cranial implant generation for cranioplasty10.1016/j.media.2021.102171 ↗
15. Sakr, N.M., Youssef, B.A.B., Hassan, Y.F., and Atta, E.H. (2018, January 6–8). An effective method for hole filling in 3D triangular meshes. Proceedings of the 2018 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), Louisville, KY, USA.10.1109/ISSPIT.2018.8705096 ↗
16. Stutz, D., and Geiger, A. (2018, January 18–23). Learning 3d shape completion from laser scan data with weak supervision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00209 ↗
17. Litany, O., Bronstein, A., Bronstein, M., and Makadia, A. (2018, January 18–23). Deformable shape completion with graph convolutional autoencoders. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00202 ↗
18. Short-term prediction method of blood glucose based on temporal multi-head attention mechanism for diabetic patients10.1016/j.bspc.2022.104552 ↗
19. The impact of pre-and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis10.1016/j.compbiomed.2020.104129 ↗
20. Automated computer-aided design of cranial implants using a deep volumetric convolutional denoising autoencoder
21. Li, J., Pepe, A., Gsaxner, C., von Campe, G., and Egger, J. (2020). Multimodal Learning for Clinical Decision Support and Clinical Image-Based Procedures, Proceedings of 10th International Workshop, ML-CDS 2020, and 9th International Workshop, CLIP 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, 4–8 October 2020, Proceedings 9, Springer.
22. Shi, H., and Chen, X. (2020). Towards the Automatization of Cranial Implant Design in Cranioplasty, Proceedings of First Challenge, AutoImplant 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, 8 October 2020, Proceedings 1, Springer.
23. Matzkin, F., Newcombe, V., Stevenson, S., Khetani, A., Newman, T., Digby, R., Stevens, A., Glocker, B., and Ferrante, E. (2020). Medical Image Computing and Computer Assisted Intervention–MICCAI 2020, Proceedings of 23rd International Conference, Lima, Peru, 4–8 October 2020, Proceedings, Part II 23, Springer.
24. Research on three-dimensional skull repair by combining residual and informer attention
25. Three-dimensional deep learning to automatically generate cranial implant geometry10.1038/s41598-022-06606-9 ↗
26. Neural network-based repairing skull defects: An initial assessment of performance and feasibility10.1142/S0219519421400121 ↗
27. Functionally superior new classification of mandibular defects (COM) and its clinical application
28. Review on Applications of U-Net and its Variants in Medical Image Segmentation
29. Jamari, J., Ammarullah, M.I., Saad, A.P.M., Syahrom, A., Uddin, M., van der Heide, E., and Basri, H. (2021). The effect of bottom profile dimples on the femoral head on wear in metal-on-metal total hip arthroplasty. J. Funct. Biomater., 12.10.3390/jfb12020038 ↗