% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Eberhardt:906178,
author = {Eberhardt, Boris and Poser, Benedikt A. and Shah, N. Jon
and Felder, Jörg},
title = {{B}1 field map synthesis with generative deep learning used
in the design of parallel-transmit {RF} pulses for
ultra-high field {MRI}},
journal = {Zeitschrift für medizinische Physik},
volume = {32},
number = {3},
issn = {0939-3889},
address = {Amsterdam},
publisher = {Elsevier, Urban $\&$ Fischer},
reportid = {FZJ-2022-01278},
pages = {334-345},
year = {2022},
abstract = {Spoke trajectory parallel transmit (pTX) excitation in
ultra-high field MRI enablesinhomogeneities arising from the
shortened RF wavelength in biological tissue to be
mitigated. To this end, current RF excitation pulse design
algorithms either employ the acquisition of field maps with
subsequent non-linear optimization or a universal approach
applying robust pre-computed pulses. We suggest and evaluate
an intermediate method that uses a subset of acquired field
maps combined with generative machine learning models to
reduce the pulse calibration time while offering more
tailored excitation than robust pulses (RP).The possibility
of employing image-to-image translation and semantic image
synthesis machine learning models based on generative
adversarial networks (GANs) to deduce the missing field maps
is examined. Additionally, an RF pulse design that employs a
predictive machine learning model to find solutions for the
non-linear (two-spokes) pulse design problem is
investigated.As a proof of concept, we present simulation
results obtained with the suggested machine learning
approaches that were trained on a limited data-set, acquired
in vivo. The achieved excitation homogeneity based on a
subset of half of themaps acquired in the calibration scans
and half of the maps synthesized with GANs is comparable
with state of the art pulse design methods when using the
full set of calibration data while halving the total
calibration time. By employing RP dictionaries or
machine-learning RF pulse predictions, the total calibration
time can be reduced significantly as these methods take only
seconds or milliseconds per slice, respectively.},
cin = {INM-4 / INM-11 / JARA-BRAIN},
ddc = {610},
cid = {I:(DE-Juel1)INM-4-20090406 / I:(DE-Juel1)INM-11-20170113 /
I:(DE-Juel1)VDB1046},
pnm = {5253 - Neuroimaging (POF4-525)},
pid = {G:(DE-HGF)POF4-5253},
typ = {PUB:(DE-HGF)16},
UT = {WOS:000878590000008},
doi = {10.1016/j.zemedi.2021.12.003},
url = {https://juser.fz-juelich.de/record/906178},
}