Article Sidebar
Views PDF: 89
DEEP LEARNING-BASED METHOD FOR CRANIAL IMPLANT DESIGN
Main Article Content
Abstract
Objectives: To investigate methods to automatically design cranial implants for patients with craniofacial defects in skull surgery. Subjects and methods: Patients with craniofacial defects were scanned to get CT images. Then, the CT images will be processed using image processing and deep learning techniques to generate the implant design. The implant design will then be used by the doctor for consultation and surgical planning. The investigating methods include 2D slice-based skull completion and deep learning using augmentation via registration. Experiments were conducted on patient datasets having defects artificially inserted by image processing operations. Results and conclusion: Experimental results reveal the abilities of deep learning-based methods in generating high precision implants in a relatively short processing time. The generated implant can be helpful for doctors during consultation and surgical planning. It is an important step towards personalization for surgical implants.
Article Details
Keywords
Cranioplasty, AutoImplant, Deep learning, Cranial implant design
References
2. Chen, X., Xu, L., Li, X., Egger, J. (2017). Computer-aided implant design for the restoration of cranial defects. Sci. Rep; 7: 1-10. https://doi.org/10.1038/ s41598-017-04454-6.
3. Egger, J. (2017). Interactive reconstructions of cranial 3D implants under MeVisLab as an alternative to commercial planning software. PLoS ONE; 12: 20. https://doi.org/10.1371/ journal.pone.0172694.
4. Gall, M., Li, X., Chen, X., Schmalstieg, D., Egger, J. (2016). Computer-aided planning and reconstruction of cranial 3d implants. In: EMBC; 1179-1183 https://doi.org/ 10.1109/EMBC.2016.7590915.
5. Marzola, A., Governi, L., Genitori, L., Mussa, F., Volpe, Y., Furferi, R. (2019). A semiautomatic hybrid approach for defective skulls reconstruction. Comput. Aided Des; Appl. 17, 190-204. https://doi.org/10.14733/cadaps.2020.190-204.
6. Shi, H., Chen, X. (2020). Cranial implant design through multiaxial slice inpainting using deep learning. In: Li, J., Egger, J. (eds.) AutoImplant 2020. LNCS, vol. 12439, pp. 28-36. Springer, Cham https://doi.org/10.1007/978-3-030-64327-04.
7. D. G. Ellis, M. R. Aizenberg. (2020). “Deep learning using augmentation via registration: 1st place solution to the AutoImplant 2020 challenge” in Towards the Automatization of Cranial Implant Design in Cranioplasty, Cham, Switzerland. Springer; 47-55.
8. https://autoimplant2021.grand-challenge.org.
9. Marzola, A., Governi, L., Genitori, L., Mussa, F., Volpe, Y., Furferi, R. (2019). A semi-automatic hybrid approach for defective skulls reconstruction. Computer- Aided Design and Applications; 17: 190-204. https://doi.org/10.14733/cadaps. 2020.190-204.