PuSH - Publication Server of Helmholtz Zentrum München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Becker, M.* ; Lehmkuhl, S.* ; Kesselheim, S.* ; Korvink, J.G.* ; Jouda, M.*

Acquisitions with random shim values enhance AI-driven NMR shimming.

J. Magn. Reson. 345:107323 (2022)
DOI
Open Access Green as soon as Postprint is submitted to ZB.
Shimming is still an unavoidable, time-consuming and cumbersome burden that precedes NMR experiments, and aims to achieve a homogeneous magnetic field distribution, which is required for expressive spectroscopy measurements. This study presents multiple enhancements to AI-driven shimming. We achieve fast, quasi-iterative shimming on multiple shims simultaneously via a temporal history that combines spectra and past shim actions. Moreover, we enable efficient data collection by randomized dataset acquisition, allowing scalability to higher-order shims. Application at a low-field benchtop magnet reduces the linewidth in 87 of 100 random distortions from ∼ 4 Hz to below 1 Hz, within less than 10 NMR acquisitions. Compared to, and combined with, traditional methods, we significantly enhance both the speed and performance of shimming algorithms. In particular, AI-driven shimming needs roughly 1/3 acquisitions, and helps to avoid local minima in 96% of the cases. Our dataset and code is publicly available.
Impact Factor
Scopus SNIP
Web of Science
Times Cited
Altmetric
2.734
0.892
4
Tags
Annotations
Special Publikation
Hide on homepage

Edit extra information
Edit own tags
Private
Edit own annotation
Private
Hide on publication lists
on hompage
Mark as special
publikation
Publication type Article: Journal article
Document type Scientific Article
Keywords Ai-driven Nmr Shimming ; Automated Shimming ; Deep Learning ; Nuclear Magnetic Resonance; Magnetic-field; Networks
Language english
Publication Year 2022
HGF-reported in Year 2022
ISSN (print) / ISBN 1090-7807
e-ISSN 1096-0856
Journal Journal of Magnetic Resonance
Quellenangaben Volume: 345, Issue: , Pages: , Article Number: 107323 Supplement: ,
Publisher Elsevier
Publishing Place 525 B St, Ste 1900, San Diego, Ca 92101-4495 Usa
Reviewing status Peer reviewed
Institute(s) Helmholtz AI - KIT (HAI - KIT)
Helmholtz AI - FZJ (HAI - FZJ)
Grants European Research Council (ERC)
KIT-Publication Fund of the Karlsruhe Institute of Technology
ERC Synergy
Helmholtz Association's Initiative and Networking Fund through Helmholtz AI
Helmholtz Research Area Information, Program 3 Materials Systems Engineering
DOI 10.1016/j.jmr.2022.107323
WOS ID 000900743900011
WOS ID WOS:000900743900011
Scopus ID 85141447849
Erfassungsdatum 2022-11-21
[➜Report correction]