EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Zero‐Shot Self‐Supervised Learning of Single Breath‐Hold Magnetic Resonance Cholangiopancreatography ( MRCP ) Reconstruction

Jinho Kim iD, Marcel Dominik Nickel, Florian Knoll iD

Magnetic Resonance in Medicine · 2026-10 · 96 (4) · 1666-1681

DOI: 10.1002/mrm.70467 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, online erschienen am 12.06.2026. Verfasst von Jinho Kim und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany. Hauptthemen laut MEDLINE: Cholangiopancreatography, Magnetic Resonance, Breath Holding, Image Processing, Computer-Assisted, Supervised Machine Learning. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft, Friedrich-Alexadner-Universität Erlangen-Nürnberg, Federal Ministry of Education and Research (Bundesministerium für Bildung und Forschung - BMBF).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To investigate the feasibility of zero‐shot self‐supervised learning reconstruction for reducing breath‐hold times in magnetic resonance cholangiopancreatography (MRCP).

Methods

Breath‐hold MRCP was acquired from 11 healthy volunteers on 3T scanners using an incoherent k ‐space sampling pattern, leading to a 14‐s acquisition time and an acceleration factor of R = 25. Zero‐shot reconstruction was compared with parallel imaging of respiratory‐triggered MRCP (338 s, R = 3) and compressed sensing reconstruction. For two volunteers, breath‐hold scans (40 s, R = 6) were additionally acquired and retrospectively undersampled to R = 25 to compute peak signal‐to‐noise ratio (PSNR). To address long zero‐shot training time, the full stages of the zero‐shot learning were divided into two parts to reduce backpropagation depth during training: (1) frozen stages initialized with ‐stage pretrained network and (2) trainable stages initialized either randomly or ‐stage pretrained network. Efficiency of our approach was assessed by varying initialization strategies and the number of trainable stages using the retrospectively undersampled data.

Results

Zero‐shot reconstruction significantly improved visual image quality over compressed sensing, particularly in SNR and ductal delineation, and achieved image quality comparable to that of successful respiratory‐triggered acquisitions with regular breathing patterns. Improved initializations enhanced PSNR and reduced reconstruction time. Adjusting frozen/trainable configurations demonstrated that PSNR decreased only slightly from 38.25 dB (0/13) to 37.67 dB (12/1), while training time decreased up to 6.7‐fold.

Conclusion

Zero‐shot learning delivers high‐fidelity MRCP reconstructions with reduced breath‐hold times, and the proposed partially trainable approach offers a practical solution for translation into time‐constrained clinical workflows.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cholangiopancreatography, Magnetic ResonanceBreath HoldingImage Processing, Computer-AssistedSupervised Machine LearningHumansMaleFemaleAdultAlgorithmsSignal-To-Noise RatioHealthy VolunteersFeasibility Studies

Stichwörter der Autor:innen

MR cholangiopancreatographybreath‐hold MRCPdeep learning–based MRI reconstructionself‐supervised trainingzero‐shot learning

Autor:innen und Institutionen

  • Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany.
  • Research and Clinical Translation, Magnetic Resonance, Siemens Healthineers AG, Erlangen, Germany.

ORCID-Profile: Jinho Kim, Florian Knoll

Förderung

  • Deutsche Forschungsgemeinschaft
  • Friedrich-Alexadner-Universität Erlangen-Nürnberg
  • Federal Ministry of Education and Research (Bundesministerium für Bildung und Forschung - BMBF)

Zitieren

APA

Kim, J., Nickel, M. D., & Knoll, F. (2026). Zero‐Shot Self‐Supervised Learning of Single Breath‐Hold Magnetic Resonance Cholangiopancreatography ( MRCP ) Reconstruction. Magnetic Resonance in Medicine, 96(4), 1666-1681. https://doi.org/10.1002/mrm.70467

Vancouver

Kim J, Nickel MD, Knoll F. Zero‐Shot Self‐Supervised Learning of Single Breath‐Hold Magnetic Resonance Cholangiopancreatography ( MRCP ) Reconstruction. Magnetic Resonance in Medicine. 2026;96(4):1666-1681. doi:10.1002/mrm.70467

BibTeX
@article{Kim2026,
  author = {Kim, Jinho and Nickel, Marcel Dominik and Knoll, Florian},
  title = {Zero‐Shot Self‐Supervised Learning of Single Breath‐Hold Magnetic Resonance Cholangiopancreatography ( MRCP ) Reconstruction},
  journal = {Magnetic Resonance in Medicine},
  year = {2026},
  volume = {96},
  number = {4},
  pages = {1666--1681},
  doi = {10.1002/mrm.70467}
}
Kostenlos starten →