%0 Journal Article
%A Becker, Moritz
%A Lehmkuhl, Sören
%A Kesselheim, Stefan
%A Korvink, Jan G.
%A Jouda, Mazin
%T Acquisitions with random shim values enhance AI-driven NMR shimming
%J Journal of magnetic resonance
%V 345
%@ 1090-7807
%C Amsterdam [u.a.]
%I Elsevier
%M FZJ-2023-00303
%P 107323 -
%D 2022
%X 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  of the cases. Our dataset and code is publicly available.
%F PUB:(DE-HGF)16
%9 Journal Article
%$ 36375285
%U <Go to ISI:>//WOS:000900743900011
%R 10.1016/j.jmr.2022.107323
%U https://juser.fz-juelich.de/record/917058