Comparison of Artificial Intelligence Models for Automatic Segmentation of the Mandibular Canals and Branches
3D UX-Net and Swin UNETR are superior to the UNETR for segmenting small dental structures. Between the two, 3D UX-Net demonstrated statistically significant improvements in overlap and recall. Furthermore, the performances of these models can be significantly enhanced by applying postprocessing strategies based on anatomical characteristics.
Authors
- Hanyang Man (ORCID: https://orcid.org/0000-0001-8327-9075)
- Jinlong Shao
- Hom-Lay Wang
- Shaohua Ge
- Shikun Ma
- Bing Wang
- Huifeng Luo
Institutions
- Shandong University (CN)
- University of Michigan (US)
- Michigan Medicine (US)
- Shandong University of Science and Technology (CN)
Publication Details
- Journal
- International Dental Journal
- Published
- 2026-02-06
- DOI
- https://doi.org/10.1016/j.identj.2026.109427
- Primary Topic
- Dental Radiography and Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00