EUVIMEDEUVIMED entdecken
Crossref

Translation Consistent Semi-Supervised Segmentation for 3D Medical Images

Yuyuan Liu, Yu Tian, Chong Wang, Yuanhong Chen, Fengbei Liu, Vasileios Belagiannis, Gustavo Carneiro

IEEE Transactions on Medical Imaging · 2025-02 · 44 (2) · 952-968

DOI: 10.1109/tmi.2024.3468896 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2025-02. Verfasst von Yuyuan Liu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 85 Literaturangaben. Gefördert von: Australian Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

3D medical image segmentation methods have been successful, but their dependence on large amounts of voxel-level annotated data is a disadvantage that needs to be addressed given the high cost to obtain such annotation. Semi-supervised learning (SSL) solves this issue by training models with a large unlabelled and a small labelled dataset. The most successful SSL approaches are based on consistency learning that minimises the distance between model responses obtained from perturbed views of the unlabelled data. These perturbations usually keep the spatial input context between views fairly consistent, which may cause the model to learn segmentation patterns from the spatial input contexts instead of the foreground objects. In this paper, we introduce the Translation Consistent Co-training (TraCoCo) which is a consistency learning SSL method that perturbs the input data views by varying their spatial input context, allowing the model to learn segmentation patterns from foreground objects. Furthermore, we propose a new Confident Regional Cross entropy (CRC) loss, which improves training convergence and keeps the robustness to co-training pseudo-labelling mistakes. Our method yields state-of-the-art (SOTA) results for several 3D data benchmarks, such as the Left Atrium (LA), Pancreas-CT (Pancreas), and Brain Tumor Segmentation (BraTS19). Our method also attains best results on a 2D-slice benchmark, namely the Automated Cardiac Diagnosis Challenge (ACDC), further demonstrating its effectiveness. Our code, training logs and checkpoints are available at https://github.com/yyliu01/ TraCoCo.

Förderung

  • Australian Research Council

Zitieren

APA

Liu, Y., Tian, Y., Wang, C., Chen, Y., Liu, F., Belagiannis, V., & Carneiro, G. (2025). Translation Consistent Semi-Supervised Segmentation for 3D Medical Images. IEEE Transactions on Medical Imaging, 44(2), 952-968. https://doi.org/10.1109/tmi.2024.3468896

Vancouver

Liu Y, Tian Y, Wang C, Chen Y, Liu F, Belagiannis V, et al. Translation Consistent Semi-Supervised Segmentation for 3D Medical Images. IEEE Transactions on Medical Imaging. 2025;44(2):952-968. doi:10.1109/tmi.2024.3468896

BibTeX
@article{Liu2025,
  author = {Liu, Yuyuan and Tian, Yu and Wang, Chong and Chen, Yuanhong and Liu, Fengbei and Belagiannis, Vasileios and Carneiro, Gustavo},
  title = {Translation Consistent Semi-Supervised Segmentation for 3D Medical Images},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2025},
  volume = {44},
  number = {2},
  pages = {952--968},
  doi = {10.1109/tmi.2024.3468896}
}
Kostenlos starten →