DentalSegmentator nnU-Net pretrained model for CBCT image segmentation

This repository contains the nnU-Net v2.2 network parameters for the segmentation of dento-maxillo-facial CBCT and CT scans with DentalSegmentator model. 

The evaluation of this model has been published here: DentalSegmentator: robust deep learning-based CBCT image segmentation

Please cite our paper and nnU-Net if you use this model for your research : 

Dot G, et al. DentalSegmentator: robust open source deep learning-based CT and CBCT image segmentation. Journal of Dentistry (2024) doi:10.1016/j.jdent.2024.105130

Isensee F, Jaeger PF, Kohl SAA, Petersen J, Maier-Hein KH. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2021;18(2):203-211. doi:10.1038/s41592-020-01008-z

Label numbers correspond to the following classes (please refer to the publication for more details) : 

1. upper skull
2. mandible
3. upper teeth
4. lower teeth
5. mandibular canal

Instructions for how to use the model are provided at: https://github.com/MIC-DKFZ/nnUNet. 

A 3D Slicer implementation of this model is also available: https://github.com/gaudot/SlicerDentalSegmentator