EUVIMEDEUVIMED entdecken
Crossref

Bidirectional multi-scale implicit neural representation network for topology-aware lung 4D-CT registration

Xinyu Liu, Zhijia Wang, Xing Chen, Ying Wei iD

Physics in Medicine & Biology · 28.11.2026 · 71 (22) · 225005

DOI: 10.1088/1361-6560/aebd5e ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physics in Medicine & Biology, online erschienen am 17.11.2026. Verfasst von Xinyu Liu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Control Science and Engineering, Shandong University, Jinan, Shandong Province, People's Republic of China. Hauptthemen laut MEDLINE: Four-Dimensional Computed Tomography, Image Processing, Computer-Assisted, Lung, Neural Networks, Computer. Die Arbeit nennt 66 Literaturangaben. Gefördert von: Taishan Scholars Program, National Key Research and Development Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective. Precise lung 4D-CT registration is extremely challenging due to large respiratory excursions. To capture such large-magnitude motion, existing deep learning methods typically adopt a unidirectional coarse-to-fine cascade strategy, which is vulnerable to error propagation because uncorrected coarse-level misalignments degrade subsequent finer-scale stages and often lead to spatially inconsistent deformations. While implicit neural representations (INRs) support continuous coordinate-based deformation modeling, traditional instance-specific INRs lack clinical efficiency and struggle to converge on global large deformations because of the absence of multi-scale semantic guidance. This study aims to bridge these gaps by developing a bidirectional multi-scale INR network that jointly handles large deformation modeling and localized structural fidelity. Approach. We propose a bidirectional multi-scale INR network. First, a generalized conditional INR framework is introduced to enable continuous deformation modeling without the need for retraining. Crucially, a bidirectional feature feedback mechanism built upon Swin Transformer injects high-level semantic priors into low-resolution streams, correcting coarse-level biases through top-down interaction. Furthermore, an anatomy-aware structural constraint is incorporated to promote anatomical consistency and local boundary alignment. Main results. Under the within-subject phase-held-out DIR-Lab protocol, the proposed method achieved a mean TRE of 1.28 mm and a folding rate of 0.0090%. A leave-one-case-out evaluation assessed subject-independent generalization, yielding a mean TRE of 1.53 mm and a folding rate of 0.0195%. On the independent POPI dataset, the method achieved a mean TRE of 1.84 mm and a folding rate of 0.0806%, demonstrating competitive cross-center performance. Inference took 0.33 s per case. Significance. The proposed framework effectively combines continuous coordinate modeling with deep learning efficiency, overcoming error propagation inherent in discrete coarse-to-fine strategies and preserving both global deformation consistency and local anatomical precision. Its sub-second inference and performance under leave-one-case-out and independent external testing support its potential for efficient image-guided radiation therapy workflows.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Four-Dimensional Computed TomographyImage Processing, Computer-AssistedLungNeural Networks, ComputerHumans

Stichwörter der Autor:innen

anatomy-aware structural constraintdeep learningdeformable registrationimplicit neural representationlung 4D-CT registrationmulti-scale

Autor:innen und Institutionen

  • School of Control Science and Engineering, Shandong University, Jinan, Shandong Province, People's Republic of China.
  • Shandong Research Institute of Industrial Technology, Jinan, Shandong Province, People's Republic of China.

ORCID-Profile: Ying Wei

Förderung

  • Taishan Scholars Program
  • National Key Research and Development Program of China

Zitieren

APA

Liu, X., Wang, Z., Chen, X., & Wei, Y. (2026). Bidirectional multi-scale implicit neural representation network for topology-aware lung 4D-CT registration. Physics in Medicine & Biology, 71(22), 225005. https://doi.org/10.1088/1361-6560/aebd5e

Vancouver

Liu X, Wang Z, Chen X, Wei Y. Bidirectional multi-scale implicit neural representation network for topology-aware lung 4D-CT registration. Physics in Medicine & Biology. 2026;71(22):225005. doi:10.1088/1361-6560/aebd5e

BibTeX
@article{Liu2026,
  author = {Liu, Xinyu and Wang, Zhijia and Chen, Xing and Wei, Ying},
  title = {Bidirectional multi-scale implicit neural representation network for topology-aware lung 4D-CT registration},
  journal = {Physics in Medicine & Biology},
  year = {2026},
  volume = {71},
  number = {22},
  pages = {225005},
  doi = {10.1088/1361-6560/aebd5e}
}
Kostenlos starten →