This work is licensed under a Creative Commons Attribution 4.0 International License.
The gathered data set consists of 5803 CBCT slices in total, out of which 4243 contain tooth annotations. The images contain significant structural variations in relation to the teeth position, the number of teeth, restorations, implants, appliances, and the size of jaws. We strongly believe this work is a valuable and desired asset to share in public for computer-aided tooth image research. Our goal is to collect and annotate a 3D tooth dataset, implement an open-source tooth volume segmentation library of state of the art 3D deep neural networks in PyTorch.
[Update] This conference paper has been accepted on 2022 ICIRA.
[Update] We will release our dental dataset CTooth and more data samples later in these two months. Please follow us and watch this Github repository for releases to be notified.
Please send an email to acw499@qmul.ac.uk requesting access to the CTooth dataset after reading the Data_requisition.md. Our updates will be announced later on a Wechat group or via our Github account.
Please see the attention based tooth segmentation benckmark here
- On the fly 3D total volume visualization
- Tensorboard and PyTorch 1.4+ support to track training progress
- Code cleanup and packages creation
- Evaluation visualization
If you really like this repository and find it useful, please consider (★) starring it, so that it can reach a broader audience of like-minded people. It would be highly appreciated :) !
If you find a bug, create a GitHub issue, or even better, submit a pull request. Similarly, if you have questions, simply post them as GitHub issues. More info on the contribute directory.
Please advice the LICENSE.md file. For usage of third party libraries and repositories please advise the respective distributed terms. It would be nice to cite the original models and datasets. If you want, you can also cite this work as:
@ARTICLE{2022arXiv220608778C,
author = {{Cui}, Weiwei and {Wang}, Yaqi and {Zhang}, Qianni and {Zhou}, Huiyu and {Song}, Dan and {Zuo}, Xingyong and {Jia}, Gangyong and {Zeng}, Liaoyuan},
title = "{CTooth: A Fully Annotated 3D Dataset and Benchmark for Tooth Volume Segmentation on Cone Beam Computed Tomography Images}",
journal = {arXiv e-prints},
keywords = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence},
year = 2022,
month = jun,
eid = {arXiv:2206.08778},
pages = {arXiv:2206.08778},
archivePrefix = {arXiv},
eprint = {2206.08778},
primaryClass = {cs.CV},
adsurl = {https://ui.adsabs.harvard.edu/abs/2022arXiv220608778C},
adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}
The work was supported by the National Natural Science Foundation of China under Grant No. U20A20386. Thanks for the data support on the University of Electronic Science and Technology of China and its Hospital.