EUVIMEDEUVIMED entdecken
Crossref

Deep-Learning-Based Metal Artefact Reduction With Unsupervised Domain Adaptation Regularization for Practical CT Images

Muge Du, Kaichao Liang, Li Zhang, Hewei Gao, Yinong Liu, Yuxiang Xing

IEEE Transactions on Medical Imaging · 2023-08 · 42 (8) · 2133-2145

DOI: 10.1109/tmi.2023.3244252 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2023-08. Verfasst von Muge Du und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Artifacts, Deep Learning. Die Arbeit wurde bisher 52-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

CT metal artefact reduction (MAR) methods based on supervised deep learning are often troubled by domain gap between simulated training dataset and real-application dataset, i.e., methods trained on simulation cannot generalize well to practical data. Unsupervised MAR methods can be trained directly on practical data, but they learn MAR with indirect metrics and often perform unsatisfactorily. To tackle the domain gap problem, we propose a novel MAR method called UDAMAR based on unsupervised domain adaptation (UDA). Specifically, we introduce a UDA regularization loss into a typical image-domain supervised MAR method, which mitigates the domain discrepancy between simulated and practical artefacts by feature-space alignment. Our adversarial-based UDA focuses on a low-level feature space where the domain difference of metal artefacts mainly lies. UDAMAR can simultaneously learn MAR from simulated data with known labels and extract critical information from unlabeled practical data. Experiments on both clinical dental and torso datasets show the superiority of UDAMAR by outperforming its supervised backbone and two state-of-the-art unsupervised methods. We carefully analyze UDAMAR by both experiments on simulated metal artefacts and various ablation studies. On simulation, its close performance to the supervised methods and advantages over the unsupervised methods justify its efficacy. Ablation studies on the influence from the weight of UDA regularization loss, UDA feature layers, and the amount of practical data used for training further demonstrate the robustness of UDAMAR. UDAMAR provides a simple and clean design and is easy to implement. These advantages make it a very feasible solution for practical CT MAR.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ArtifactsDeep LearningComputer SimulationTomography, X-Ray Computed

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Du, M., Liang, K., Zhang, L., Gao, H., Liu, Y., & Xing, Y. (2023). Deep-Learning-Based Metal Artefact Reduction With Unsupervised Domain Adaptation Regularization for Practical CT Images. IEEE Transactions on Medical Imaging, 42(8), 2133-2145. https://doi.org/10.1109/tmi.2023.3244252

Vancouver

Du M, Liang K, Zhang L, Gao H, Liu Y, Xing Y. Deep-Learning-Based Metal Artefact Reduction With Unsupervised Domain Adaptation Regularization for Practical CT Images. IEEE Transactions on Medical Imaging. 2023;42(8):2133-2145. doi:10.1109/tmi.2023.3244252

BibTeX
@article{Du2023,
  author = {Du, Muge and Liang, Kaichao and Zhang, Li and Gao, Hewei and Liu, Yinong and Xing, Yuxiang},
  title = {Deep-Learning-Based Metal Artefact Reduction With Unsupervised Domain Adaptation Regularization for Practical CT Images},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2023},
  volume = {42},
  number = {8},
  pages = {2133--2145},
  doi = {10.1109/tmi.2023.3244252}
}
Kostenlos starten →