EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CTCF: A Three-Level Coarse-to-Fine Cascade for Unsupervised Deformable Medical Image Registration

Daniil Pasenko, Roman Davydov

Machine Learning and Knowledge Extraction · 02.05.2026 · 8 (5) · 122

DOI: 10.3390/make8050122 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning and Knowledge Extraction, online erschienen am 02.05.2026. Verfasst von Daniil Pasenko und 1 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deformable medical image registration aims to spatially align anatomical structures across volumetric scans. Recent transformer-based methods achieve high overlap accuracy but often produce deformation fields with topological violations. We propose CTCF, a Cascade Transformer for Coarse-to-Fine registration that wraps a lightweight coarse-and-refined envelope around a core registration module. Level 1 provides a coarse displacement estimate at quarter resolution, Level 2 performs the main registration via a Swin Transformer encoder with deformable cross-attention and a learned super-resolution decoder, and Level 3 applies error-driven flow refinement at half resolution. The two outer levels add only 3.0% parameter overhead yet improve registration accuracy while maintaining competitive deformation regularity relative to external baselines. The model is trained end-to-end with a composite unsupervised loss combining local normalized cross-correlation, diffusion regularization, inverse-consistency, and Jacobian-based topology preservation. On the OASIS brain MRI benchmark, CTCF achieves the highest Dice score of 0.8208 among the compared unsupervised methods while maintaining competitive SDlogJ, with all Dice improvements statistically significant at p

Zitieren

APA

Pasenko, D., & Davydov, R. (2026). CTCF: A Three-Level Coarse-to-Fine Cascade for Unsupervised Deformable Medical Image Registration. Machine Learning and Knowledge Extraction, 8(5), 122. https://doi.org/10.3390/make8050122

Vancouver

Pasenko D, Davydov R. CTCF: A Three-Level Coarse-to-Fine Cascade for Unsupervised Deformable Medical Image Registration. Machine Learning and Knowledge Extraction. 2026;8(5):122. doi:10.3390/make8050122

BibTeX
@article{Pasenko2026,
  author = {Pasenko, Daniil and Davydov, Roman},
  title = {CTCF: A Three-Level Coarse-to-Fine Cascade for Unsupervised Deformable Medical Image Registration},
  journal = {Machine Learning and Knowledge Extraction},
  year = {2026},
  volume = {8},
  number = {5},
  pages = {122},
  doi = {10.3390/make8050122}
}
Kostenlos starten →