EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

From Unsupervised to Zero-Shot: 3D Domain Adaptation for Cryo-Electron Tomography Segmentation

Haoran Li, Xingjian Li, Huan Wang, Jiahua Shi, Huaming Chen, Bo Du, Johan Barthelemy, Daisuke Kihara, Jun Shen iD, Min Xu

International Journal of Computer Vision · 2026-05 · 134 (5)

DOI: 10.1007/s11263-026-02802-6 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 07.04.2026. Verfasst von Haoran Li und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Computing and Information Technology, University of Wollongong, Wollongong, Australia. Die Arbeit nennt 100 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, The University of Wollongong.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the refinement of 3D imaging modality, cryo-electron tomography (cryo-ET) has emerged as a powerful technique for the structural analysis of macromolecular complexes at near-atomic resolution. Recent advancements in volumetric segmentation methods applied to cryo-ET datasets have garnered significant attention within the biomedical sector. However, existing methods rely heavily on manually labeled data, which demands highly specialized expertise, making fully supervised approaches less feasible for cryo-ET images. To address this, a number of unsupervised domain adaptation (UDA) techniques have been developed to improve segmentation network performance using unlabeled data. Nevertheless, directly applying these methods to cryo-ET image segmentation presents two major challenges: 1) the source dataset, usually obtained through simulation, contains a fixed level of noise, while the target dataset, being directly collected from raw-data from the real-world scenario, has unpredictable noise levels; 2) the source data used for training typically consists of known macromolecules, in contrast, the target domain data are often unknown, causing the model to be biased towards those known macromolecules, leading to a domain shift problem. To address such challenges, in this paper, we introduce a voxel-wise unsupervised domain adaptation approach, termed Vox-UDA, specifically for cryo-ET subtomogram segmentation. Vox-UDA incorporates a noise generation module to simulate target-like noises in the source dataset for cross-noise level adaptation, and a denoised pseudo-labeling strategy based on the improved bilateral filter to alleviate the domain shift problem. Additionally, we further consider a scenario that is more in line with the real world, where the target (experimental) dataset might not be accessible during training or has a very small sample size, and we present a voxel-wise zero-shot domain adaptation (ZSDA) approach, named Vox-ZSDA. In Vox-ZSDA, we introduce a self-supervised graph learning strategy to eliminate any dependency on the target data, accompanied by a dynamic graph contrastive learning technique to enhance the model’s sensitivity to macromolecular structures to boost the segmentation performance. More importantly, we construct the first UDA and ZSDA cryo-ET subtomogram segmentation benchmark on three experimental datasets. Extensive experimental results on multiple benchmarks and newly curated real-world datasets demonstrate the superiority of our proposed approach compared to state-of-the-art UDA and ZSDA methods.

Schlagwörter

Stichwörter der Autor:innen

3D image segmentationCryo-Electron TomographyGraph LearningUnsupervised domain adaptationZero-shot domain adaptation

Autor:innen und Institutionen

  • School of Computing and Information Technology, University of Wollongong, Wollongong, Australia.
  • ARC Training Centre for Innovative Composites for the Future of Sustainable Mining, University of Wollongong, Wollongong, Australia.
  • Centre for Nutrition and Food Sciences, The University of Queensland, Brisbane, Australia.
  • Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University, Pittsburgh, USA.
  • School of Electrical and Computer Engineering, University of Sydney, Sydney, Australia.
  • Department of Management, Griffith University, Queensland, Australia.

ORCID-Profile: Jun Shen

Förderung

  • NIGMS NIH HHS
  • The University of Wollongong

Zitieren

APA

Li, H., Li, X., Wang, H., Shi, J., Chen, H., Du, B., Barthelemy, J., Kihara, D., Shen, J., & Xu, M. (2026). From Unsupervised to Zero-Shot: 3D Domain Adaptation for Cryo-Electron Tomography Segmentation. International Journal of Computer Vision, 134(5). https://doi.org/10.1007/s11263-026-02802-6

Vancouver

Li H, Li X, Wang H, Shi J, Chen H, Du B, et al. From Unsupervised to Zero-Shot: 3D Domain Adaptation for Cryo-Electron Tomography Segmentation. International Journal of Computer Vision. 2026;134(5). doi:10.1007/s11263-026-02802-6

BibTeX
@article{Li2026,
  author = {Li, Haoran and Li, Xingjian and Wang, Huan and Shi, Jiahua and Chen, Huaming and Du, Bo and Barthelemy, Johan and Kihara, Daisuke and Shen, Jun and Xu, Min},
  title = {From Unsupervised to Zero-Shot: 3D Domain Adaptation for Cryo-Electron Tomography Segmentation},
  journal = {International Journal of Computer Vision},
  year = {2026},
  volume = {134},
  number = {5},
  doi = {10.1007/s11263-026-02802-6}
}
Kostenlos starten →