PuSH - Publikationsserver des Helmholtz Zentrums München

Spieker, V. ; Eichhorn, H. ; Huang, W.* ; Stelter, J.K.* ; Catalan, T.* ; Braren, R.F.* ; Rueckert, D.* ; Sahli Costabal, F.* ; Hammernik, K.* ; Karampinos, D.C.* ; Prieto, C.* ; Schnabel, J.A.

PISCO: Self-supervised k-space regularization for improved neural implicit k-space representations of dynamic MRI.

Med. Image Anal. 109:103890 (2025)
Verlagsversion Forschungsdaten DOI PMC
Open Access Hybrid
Creative Commons Lizenzvertrag
Neural implicit k-space representations (NIK) have shown promising results for dynamic magnetic resonance imaging (MRI) at high temporal resolutions. Yet, reducing acquisition time, and thereby available training data, results in severe performance drops due to overfitting. To address this, we introduce a novel self-supervised k-space loss function LPISCO, applicable for regularization of NIK-based reconstructions. The proposed loss function is based on the concept of parallel imaging-inspired self-consistency (PISCO), enforcing a consistent global k-space neighborhood relationship without requiring additional data. Quantitative and qualitative evaluations on static and dynamic MR reconstructions show that integrating PISCO significantly improves NIK representations, making it a competitive dynamic reconstruction method without constraining the temporal resolution. Particularly at high acceleration factors (R ≥ 50), NIK with PISCO can avoid temporal oversmoothing of state-of-the-art methods and achieves superior spatio-temporal reconstruction quality. Furthermore, an extensive analysis of the loss assumptions and stability shows PISCO's potential as versatile self-supervised k-space loss function for further applications and architectures. Code is available at: https://github.com/compai-lab/2025-pisco-spieker.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Schlagwörter Dynamic Mri Reconstruction ; K-space Refinement ; Neural Implicit Representations ; Non-uniform Sampling ; Parallel Imaging ; Self-supervised Learning
ISSN (print) / ISBN 1361-8415
e-ISSN 1361-8415
Zeitschrift Medical Image Analysis
Quellenangaben Band: 109, Heft: , Seiten: , Artikelnummer: 103890 Supplement: ,
Verlag Elsevier
Begutachtungsstatus Peer reviewed
Institut(e) Institute for Machine Learning in Biomed Imaging (IML)