EUVIMEDEUVIMED entdecken
Open Access

CoReg-Net: contrastive registration for structurally consistent one-shot medical image segmentation

Ziyi Xia, Yongzhi Huang iD, Feng Zhou, Hongwei Zhang, Yun Peng, Yong Liu, Liyun Tu iD

Journal of Medical Imaging · 13.08.2026 · 13 (04) · 1-18

DOI: 10.1117/1.jmi.13.4.044002 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Medical Imaging, erschienen am 13.08.2026. Verfasst von Ziyi Xia und 6 weiteren Autor:innen. Beteiligte Einrichtung: Beijing University of Posts and Telecommunications, School of Artificial Intelligence, Beijing, China. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Beijing Natural Science Foundation-Haidian Original Innovation Joint Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PurposeIn clinical scenarios where only a single labeled reference image is available for the target segmentation task, registration-based one-shot segmentation is a practical solution through anatomical label transfer. However, existing deep learning-based registration methods are often sensitive to appearance variations, which distort anatomical correspondence in the latent feature space and lead to structurally inconsistent deformation fields. This work aims to improve the structural consistency of deformable registration by explicitly aligning inter-subject anatomical representations.ApproachWe propose CoReg-Net, a contrastive registration framework that integrates an inter-subject contrastive learning (ISCL) module to enforce anatomically consistent feature representations by matching spatially corresponding regions across subjects. In parallel, a cascaded skip connection (CSC) mechanism is introduced to bridge the semantic gap between hierarchical encoder and decoder features, enabling more coherent reconstruction of fine-grained deformation details. These two components are jointly optimized to guide the network toward structurally meaningful and topologically regular deformation fields for robust label propagation.ResultsThe proposed method demonstrates robust and consistent one-shot segmentation performance across diverse anatomical structures and imaging modalities on the IXI, OASIS, and BCV datasets. Compared with state-of-the-art registration-based baselines, CoReg-Net generates deformation fields with higher structural similarity to target images, confirming the effectiveness of contrastive feature alignment. Atlas replacement experiments further verify the robustness of the proposed method under atlas variation. Moreover, the framework exhibits adaptive deformability, preserving topological regularity in brain tissues while accurately capturing large non-rigid deformations in abdominal organs.ConclusionsCoReg-Net shows that explicitly enforcing structural consistency through contrastive registration improves structural similarity and maintains segmentation accuracy. The proposed framework provides a reliable and generalizable solution for atlas-guided anatomical analysis across heterogeneous imaging modalities. Code is available at https://github.com/RelMono/CoRegNet.

Schlagwörter

Stichwörter der Autor:innen

contrastive learningimage registrationmedical image segmentationone-shot learningtransformer

Autor:innen und Institutionen

  • Beijing University of Posts and Telecommunications, School of Artificial Intelligence, Beijing, China.
  • Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, Department of Radiology, MOE Key Laboratory of Major Diseases in Children, Beijing, China.

ORCID-Profile: Yongzhi Huang, Liyun Tu

Förderung

  • Beijing Natural Science Foundation-Haidian Original Innovation Joint Fund

Zitieren

APA

Xia, Z., Huang, Y., Zhou, F., Zhang, H., Peng, Y., Liu, Y., & Tu, L. (2026). CoReg-Net: contrastive registration for structurally consistent one-shot medical image segmentation. Journal of Medical Imaging, 13(04), 1-18. https://doi.org/10.1117/1.jmi.13.4.044002

Vancouver

Xia Z, Huang Y, Zhou F, Zhang H, Peng Y, Liu Y, et al. CoReg-Net: contrastive registration for structurally consistent one-shot medical image segmentation. Journal of Medical Imaging. 2026;13(04):1-18. doi:10.1117/1.jmi.13.4.044002

BibTeX
@article{Xia2026,
  author = {Xia, Ziyi and Huang, Yongzhi and Zhou, Feng and Zhang, Hongwei and Peng, Yun and Liu, Yong and Tu, Liyun},
  title = {CoReg-Net: contrastive registration for structurally consistent one-shot medical image segmentation},
  journal = {Journal of Medical Imaging},
  year = {2026},
  volume = {13},
  number = {04},
  pages = {1--18},
  doi = {10.1117/1.jmi.13.4.044002}
}
Kostenlos starten →