Cross‐Site Generalization of CNN‐Based B1+ Mapping in UHF MRI
NMR in Biomedicine · 2026-05 · 39 (5)
DOI: 10.1002/nbm.70263 ↗Kurz gefasst
Fachartikel in der Zeitschrift NMR in Biomedicine, online erschienen am 06.04.2026. Verfasst von Kimon Hadjikiriakos und 13 weiteren Autor:innen. Beteiligte Einrichtung: Physikalisch-Technische Bundesanstalt, Berlin, Germany. Hauptthemen laut MEDLINE: Convolutional Neural Networks, Magnetic Resonance Imaging, Brain Mapping, Image Processing, Computer-Assisted. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft (DFG, German Research Foundation).
Abstract (Originalsprache)
Convolutional neural networks (CNNs) can rapidly predict channel‐wise maps from 7T localizer images, reducing acquisition time to seconds. This paper investigates if a CNN trained on one site's data can generalize to predict maps for brain imaging at unseen sites supporting the feasibility of a universal network for subject‐specific ‐ mapping. We evaluated a U‐Net CNN cross‐site generalization by training on datasets from two different 7T sites and testing its performance across three 7T sites (1 additional testing site) to assess robustness, adaptability, and generalization. The study design included both commercially same systems and the identical physical hardware unit transported between two sites, enabling a more insightful attribution of performance differences to either hardware issues or dataset‐specific variations. To assess prediction quality, we examined magnitude/phase images, error maps, correlation plots, Pearson coefficients, and residual spread plots. Quantitative evaluation included RMSE and SSIM scores. Finally, we calculated 4 kT‐points pulses with both on‐site and cross‐site CNNs to evaluate the effectiveness of the obtained maps for parallel‐transmission (pTx). While on‐site transversal magnitude RMSE scores were as low as 3.0% and 3.1% for the two CNNs, their respective transfer yielded 3.6% and 4.1%. The dynamic pTx‐application showed a CV of 6.5% when using maps predicted by a network trained on its own site. The transfer case, using a map predicted from a network trained on a different site, yielded an increased CV of 13.7%. Although cross‐site applications introduced larger deviations, the predicted maps remained qualitatively plausible and enabled practical use cases, such as calculating dynamic‐pTx. These findings support the potential of cross‐site training, suggesting CNNs trained at one site may generalize sufficiently to unseen sites without additional adjustments. This strengthens the feasibility of a transferable training approach where a single network could be deployed across different institutions without extensive retraining.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Physikalisch-Technische Bundesanstalt, Berlin, Germany.
- Medical Physics in Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany.
- Faculty of Physics and Astronomy, Heidelberg University, Heidelberg, Germany.
- Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, Minnesota, USA.
- Institute for Applied Medical Informatics, University Medical Center Hamburg-Eppendorf (UKE), Hamburg, Germany.
- Max Planck Research Group MR Physics, Max Planck Institute for Human Development, Berlin, Germany.
ORCID-Profile: Kimon Hadjikiriakos, Felix Krüger, Felix Frederik Zimmermann, Johannes A Grimm, Constantin Schorling, Max Lutz, Simon Schmidt, Layla Tabea Riemann, Katja Degenhardt, Tobias Schäffter, Mark E Ladd, Gregory J Metzger, Christoph Stefan Aigner, Sebastian Schmitter
Förderung
- Deutsche Forschungsgemeinschaft (DFG, German Research Foundation)
Zitieren
APA
Hadjikiriakos, K., Krüger, F., Zimmermann, F. F., Grimm, J. A., Schorling, C., Lutz, M., Schmidt, S., Riemann, L. T., Degenhardt, K., Schäffter, T., Ladd, M. E., Metzger, G. J., Aigner, C. S., & Schmitter, S. (2026). Cross‐Site Generalization of CNN‐Based B1+ Mapping in UHF MRI. NMR in Biomedicine, 39(5). https://doi.org/10.1002/nbm.70263
Vancouver
Hadjikiriakos K, Krüger F, Zimmermann FF, Grimm JA, Schorling C, Lutz M, et al. Cross‐Site Generalization of CNN‐Based B1+ Mapping in UHF MRI. NMR in Biomedicine. 2026;39(5). doi:10.1002/nbm.70263
BibTeX
@article{Hadjikiriakos2026,
author = {Hadjikiriakos, Kimon and Krüger, Felix and Zimmermann, Felix Frederik and Grimm, Johannes A and Schorling, Constantin and Lutz, Max and Schmidt, Simon and Riemann, Layla Tabea and Degenhardt, Katja and Schäffter, Tobias and Ladd, Mark E and Metzger, Gregory J and Aigner, Christoph Stefan and Schmitter, Sebastian},
title = {Cross‐Site Generalization of CNN‐Based B1+ Mapping in UHF MRI},
journal = {NMR in Biomedicine},
year = {2026},
volume = {39},
number = {5},
doi = {10.1002/nbm.70263}
}
EUVIMED