Evaluation of synthetic training data for 3D intraoral reconstruction of cleft patients from single images
Our results demonstrate that synthetic training data are viable for training models to predict 2D landmarks and reconstruct 3D meshes in patients with cleft lip and palate. This approach offers an accessible, low-cost alternative to traditional methods, using smartphone technology for noninvasive, rapid, and accurate 3D reconstructions in clinical settings.
Authors
- Benito K. Benitez (ORCID: https://orcid.org/0000-0003-4459-6603)
- Yoriko Lill (ORCID: https://orcid.org/0000-0003-3553-7601)
- Markus Groß (ORCID: https://orcid.org/0009-0003-9324-779X)
- Lasse Lingens
- Andreas Mueller (ORCID: https://orcid.org/0000-0002-1973-9281)
- Barbara Solenthaler (ORCID: https://orcid.org/0000-0001-7494-8660)
- Prasad Nalabothu (ORCID: https://orcid.org/0000-0003-2442-7618)
Institutions
- University Hospital of Basel (CH)
- ETH Zurich (CH)
- University Children’s Hospital Basel (CH)
Publication Details
- Journal
- International Journal of Computer Assisted Radiology and Surgery
- Published
- 2025-05-24
- DOI
- https://doi.org/10.1007/s11548-025-03396-z
- Citations
- 3
- Primary Topic
- Cleft Lip and Palate Research
- Type
- article
- Field-Weighted Citation Impact
- 5.45
Funders
- Eidgenössische Technische Hochschule Zürich
- Botnar Research Centre for Child Health, University of Basel