Cross‐Site Generalization of CNN‐Based B1+ Mapping in UHF MRI

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.

Authors

Institutions

Publication Details

Journal
NMR in Biomedicine
Published
2026-04-06
DOI
https://doi.org/10.1002/nbm.70263
Primary Topic
Functional Brain Connectivity Studies
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Cross‐Site Generalization of CNN‐Based B1+ Mapping in UHF MRI

Felix Frederik Zimmermann, Sebastian Schmitter, Layla Tabea Riemann, Max Lutz et al.
NMR in Biomedicine
Functional Brain Connectivity Studies
article

Cross‐Site Generalization of CNN‐Based B1+ Mapping in UHF MRI

Felix Frederik Zimmermann, Sebastian Schmitter, Layla Tabea Riemann, Max Lutz, Mark E. Ladd, Johannes A. Grimm, S Schmidt, Katja Degenhardt, Gregory J. Metzger, Kimon Hadjikiriakos, Christoph Stefan Aigner, Felix Krüger, Tobias Schäffter, Constantin Schorling
article en

Abstract

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.

NMR in BiomedicineVol. 39(5)
Physikalisch-Technische Bundesanstalt (DE), University of Minnesota (US), Universität Hamburg (DE), German Cancer Research Center (DE), Heidelberg University (DE), University Medical Center Hamburg-Eppendorf (DE), Max Planck Institute for Human Development (DE), Resonance Research (United States) (US)
Deutsche Forschungsgemeinschaft
Openalex Percentile: Top 25%
Functional Brain Connectivity Studies
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.