Model Adaptive Tooth Segmentation

Ruizhe Chen, Jianfei Yang, YANG FENG, Jin Hao, Zuozhu Liu
Medical Imaging with Deep Learning, PMLR 227:775-798, 2024.

Abstract

Automatic 3-dimensional tooth segmentation on intraoral scans (IOS) plays a pivotal role in computer-aided orthodontic treatments. In practice, deploying existing well-trained models to different medical centers suffers from two main problems: (1) the data distribution shifts between existing and new centers, (2) the data in the existing center is usually not allowed to share while annotating additional data in the new center is time-consuming and expensive. In this paper, we propose a Model Adaptive Tooth Segmentation (MATS) framework to alleviate these issues. Taking the trained model from a source center as input, MATS adapts it to different target centers without data transmission or additional annotations, as inspired by the source data-free domain adaptation (SFDA) paradigm. The model adaptation in MATS is realized by a tooth-level feature prototype learning module, a progressive pseudo-labeling module and a tooth-prior regularized information maximization loss. Experiments on a dataset with tooth abnormalities and a real-world cross-center dataset show that MATS can consistently surpass existing baselines. The effectiveness is further verified with extensive ablation studies and statistical analysis, demonstrating its applicability for privacy-preserving tooth segmentation in real-world digital dentistry.

Cite this Paper

BibTeX
@InProceedings{pmlr-v227-chen24b, title = {Model Adaptive Tooth Segmentation}, author = {Chen, Ruizhe and Yang, Jianfei and FENG, YANG and Hao, Jin and Liu, Zuozhu}, booktitle = {Medical Imaging with Deep Learning}, pages = {775--798}, year = {2024}, editor = {Oguz, Ipek and Noble, Jack and Li, Xiaoxiao and Styner, Martin and Baumgartner, Christian and Rusu, Mirabela and Heinmann, Tobias and Kontos, Despina and Landman, Bennett and Dawant, Benoit}, volume = {227}, series = {Proceedings of Machine Learning Research}, month = {10--12 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v227/chen24b/chen24b.pdf}, url = {https://proceedings.mlr.press/v227/chen24b.html}, abstract = {Automatic 3-dimensional tooth segmentation on intraoral scans (IOS) plays a pivotal role in computer-aided orthodontic treatments. In practice, deploying existing well-trained models to different medical centers suffers from two main problems: (1) the data distribution shifts between existing and new centers, (2) the data in the existing center is usually not allowed to share while annotating additional data in the new center is time-consuming and expensive. In this paper, we propose a Model Adaptive Tooth Segmentation (MATS) framework to alleviate these issues. Taking the trained model from a source center as input, MATS adapts it to different target centers without data transmission or additional annotations, as inspired by the source data-free domain adaptation (SFDA) paradigm. The model adaptation in MATS is realized by a tooth-level feature prototype learning module, a progressive pseudo-labeling module and a tooth-prior regularized information maximization loss. Experiments on a dataset with tooth abnormalities and a real-world cross-center dataset show that MATS can consistently surpass existing baselines. The effectiveness is further verified with extensive ablation studies and statistical analysis, demonstrating its applicability for privacy-preserving tooth segmentation in real-world digital dentistry.} }
Endnote
%0 Conference Paper %T Model Adaptive Tooth Segmentation %A Ruizhe Chen %A Jianfei Yang %A YANG FENG %A Jin Hao %A Zuozhu Liu %B Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ipek Oguz %E Jack Noble %E Xiaoxiao Li %E Martin Styner %E Christian Baumgartner %E Mirabela Rusu %E Tobias Heinmann %E Despina Kontos %E Bennett Landman %E Benoit Dawant %F pmlr-v227-chen24b %I PMLR %P 775--798 %U https://proceedings.mlr.press/v227/chen24b.html %V 227 %X Automatic 3-dimensional tooth segmentation on intraoral scans (IOS) plays a pivotal role in computer-aided orthodontic treatments. In practice, deploying existing well-trained models to different medical centers suffers from two main problems: (1) the data distribution shifts between existing and new centers, (2) the data in the existing center is usually not allowed to share while annotating additional data in the new center is time-consuming and expensive. In this paper, we propose a Model Adaptive Tooth Segmentation (MATS) framework to alleviate these issues. Taking the trained model from a source center as input, MATS adapts it to different target centers without data transmission or additional annotations, as inspired by the source data-free domain adaptation (SFDA) paradigm. The model adaptation in MATS is realized by a tooth-level feature prototype learning module, a progressive pseudo-labeling module and a tooth-prior regularized information maximization loss. Experiments on a dataset with tooth abnormalities and a real-world cross-center dataset show that MATS can consistently surpass existing baselines. The effectiveness is further verified with extensive ablation studies and statistical analysis, demonstrating its applicability for privacy-preserving tooth segmentation in real-world digital dentistry.
APA
Chen, R., Yang, J., FENG, Y., Hao, J. & Liu, Z.. (2024). Model Adaptive Tooth Segmentation. Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 227:775-798 Available from https://proceedings.mlr.press/v227/chen24b.html.

Related Material