Home > Publications database > B1 field map synthesis with generative deep learning used in the design of parallel-transmit RF pulses for ultra-high field MRI > print

001     906178
005     20230217124246.0
024 7 _ |a 10.1016/j.zemedi.2021.12.003
|2 doi
024 7 _ |a 0040-5973
|2 ISSN
024 7 _ |a 0939-3889
|2 ISSN
024 7 _ |a 1876-4436
|2 ISSN
024 7 _ |a 2128/31907
|2 Handle
024 7 _ |a WOS:000878590000008
|2 WOS
037 _ _ |a FZJ-2022-01278
082 _ _ |a 610
100 1 _ |a Eberhardt, Boris
|0 P:(DE-Juel1)166296
|b 0
245 _ _ |a B1 field map synthesis with generative deep learning used in the design of parallel-transmit RF pulses for ultra-high field MRI
260 _ _ |a Amsterdam
|c 2022
|b Elsevier, Urban & Fischer
264 _ 1 |3 print
|2 Crossref
|b Elsevier BV
|c 2022-08-01
264 _ 1 |3 print
|2 Crossref
|b Elsevier BV
|c 2022-08-01
336 7 _ |a article
|2 DRIVER
336 7 _ |a Output Types/Journal article
|2 DataCite
336 7 _ |a Journal Article
|b journal
|m journal
|0 PUB:(DE-HGF)16
|s 1664264235_9370
|2 PUB:(DE-HGF)
336 7 _ |a ARTICLE
|2 BibTeX
336 7 _ |a JOURNAL_ARTICLE
|2 ORCID
336 7 _ |a Journal Article
|0 0
|2 EndNote
520 _ _ |a 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.
536 _ _ |a 5253 - Neuroimaging (POF4-525)
|0 G:(DE-HGF)POF4-5253
|c POF4-525
|f POF IV
|x 0
542 _ _ |i 2022-08-01
|2 Crossref
|u https://www.elsevier.com/tdm/userlicense/1.0/
542 _ _ |i 2021-12-28
|2 Crossref
|u http://creativecommons.org/licenses/by-nc-nd/4.0/
588 _ _ |a Dataset connected to CrossRef, Journals: juser.fz-juelich.de
700 1 _ |a Poser, Benedikt A.
|0 0000-0001-8190-4367
|b 1
700 1 _ |a Shah, N. Jon
|0 P:(DE-Juel1)131794
|b 2
|u fzj
700 1 _ |a Felder, Jörg
|0 P:(DE-Juel1)131761
|b 3
|e Corresponding author
773 1 8 |a 10.1016/j.zemedi.2021.12.003
|b Elsevier BV
|d 2022-08-01
|n 3
|p 334-345
|3 journal-article
|2 Crossref
|t Zeitschrift für Medizinische Physik
|v 32
|y 2022
|x 0939-3889
773 _ _ |a 10.1016/j.zemedi.2021.12.003
|g p. S0939388921001161
|0 PERI:(DE-600)2231492-1
|n 3
|p 334-345
|t Zeitschrift für medizinische Physik
|v 32
|y 2022
|x 0939-3889
856 4 _ |u https://juser.fz-juelich.de/record/906178/files/1-s2.0-S0939388921001161-main.pdf
|y OpenAccess
909 C O |o oai:juser.fz-juelich.de:906178
|p openaire
|p open_access
|p VDB
|p driver
|p dnbdelivery
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 0
|6 P:(DE-Juel1)166296
910 1 _ |a External Institute
|0 I:(DE-HGF)0
|k Extern
|b 1
|6 0000-0001-8190-4367
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 2
|6 P:(DE-Juel1)131794
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 3
|6 P:(DE-Juel1)131761
913 1 _ |a DE-HGF
|b Key Technologies
|l Natural, Artificial and Cognitive Information Processing
|1 G:(DE-HGF)POF4-520
|0 G:(DE-HGF)POF4-525
|3 G:(DE-HGF)POF4
|2 G:(DE-HGF)POF4-500
|4 G:(DE-HGF)POF
|v Decoding Brain Organization and Dysfunction
|9 G:(DE-HGF)POF4-5253
|x 0
914 1 _ |y 2022
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0200
|2 StatID
|b SCOPUS
915 _ _ |a Creative Commons Attribution-NonCommercial-NoDerivs CC BY-NC-ND 4.0
|0 LIC:(DE-HGF)CCBYNCND4
|2 HGFVOC
915 _ _ |a JCR
|0 StatID:(DE-HGF)0100
|2 StatID
|b Z MED PHYS : 2015
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0150
|2 StatID
|b Web of Science Core Collection
915 _ _ |a WoS
|0 StatID:(DE-HGF)0111
|2 StatID
|b Science Citation Index Expanded
915 _ _ |a IF < 5
|0 StatID:(DE-HGF)9900
|2 StatID
915 _ _ |a OpenAccess
|0 StatID:(DE-HGF)0510
|2 StatID
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0300
|2 StatID
|b Medline
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0199
|2 StatID
|b Thomson Reuters Master Journal List
920 1 _ |0 I:(DE-Juel1)INM-4-20090406
|k INM-4
|l Physik der Medizinischen Bildgebung
|x 0
920 1 _ |0 I:(DE-Juel1)INM-11-20170113
|k INM-11
|l Jara-Institut Quantum Information
|x 1
920 1 _ |0 I:(DE-Juel1)VDB1046
|k JARA-BRAIN
|l Jülich-Aachen Research Alliance - Translational Brain Medicine
|x 2
980 _ _ |a journal
980 _ _ |a VDB
980 _ _ |a UNRESTRICTED
980 _ _ |a I:(DE-Juel1)INM-4-20090406
980 _ _ |a I:(DE-Juel1)INM-11-20170113
980 _ _ |a I:(DE-Juel1)VDB1046
980 1 _ |a FullTexts
999 C 5 |a 10.1097/RMR.0000000000000204
|9 -- missing cx lookup --
|1 Deniz
|p 159 -
|2 Crossref
|t Top Magn Reson Imaging
|v 28
|y 2019
999 C 5 |a 10.1002/mrm.20708
|9 -- missing cx lookup --
|1 Van de Moortele
|p 1503 -
|2 Crossref
|t Magn Reson Med
|v 54
|y 2005
999 C 5 |a 10.1002/mrm.21073
|9 -- missing cx lookup --
|1 Vaughan
|p 1274 -
|2 Crossref
|t Magn Reson Med
|v 56
|y 2006
999 C 5 |a 10.1002/mrm.10353
|9 -- missing cx lookup --
|1 Katscher
|p 144 -
|2 Crossref
|t Magn Reson Med
|v 49
|y 2003
999 C 5 |a 10.1002/mrm.20011
|9 -- missing cx lookup --
|1 Zhu
|p 775 -
|2 Crossref
|t Magn Reson Med
|v 51
|y 2004
999 C 5 |a 10.1002/mrm.20840
|9 -- missing cx lookup --
|1 Saekho
|p 719 -
|2 Crossref
|t Magn Reson Med
|v 55
|y 2006
999 C 5 |a 10.1002/mrm.26512
|9 -- missing cx lookup --
|1 Grissom
|p 1352 -
|2 Crossref
|t Magn Reson Med
|v 78
|y 2017
999 C 5 |a 10.1002/mrm.21513
|9 -- missing cx lookup --
|1 Setsompop
|p 908 -
|2 Crossref
|t Magn Reson Med
|v 59
|y 2008
999 C 5 |a 10.1002/mrm.28820
|1 Paez
|y 2021
|2 Crossref
|t Magn Reson Med
|9 -- missing cx lookup --
999 C 5 |a 10.1016/j.jmr.2015.03.013
|9 -- missing cx lookup --
|1 Dupas
|p 59 -
|2 Crossref
|t J Magn Reson
|v 255
|y 2015
999 C 5 |a 10.1109/TMI.2020.3013982
|9 -- missing cx lookup --
|1 Eberhardt
|p 4225 -
|2 Crossref
|t IEEE Trans Med Imaging
|v 39
|y 2020
999 C 5 |a 10.1002/mrm.24800
|9 -- missing cx lookup --
|1 Guerin
|p 1446 -
|2 Crossref
|t Magn Reson Med
|v 71
|y 2014
999 C 5 |a 10.1002/mrm.26491
|9 -- missing cx lookup --
|1 Gras
|p 1009 -
|2 Crossref
|t Magn Reson Med
|v 78
|y 2017
999 C 5 |a 10.1002/mrm.26148
|9 -- missing cx lookup --
|1 Gras
|p 635 -
|2 Crossref
|t Magn Reson Med
|v 77
|y 2017
999 C 5 |a 10.1002/mrm.27001
|9 -- missing cx lookup --
|1 Gras
|p 53 -
|2 Crossref
|t Magn Reson Med
|v 80
|y 2018
999 C 5 |a 10.1002/mrm.28643
|9 -- missing cx lookup --
|1 Herrler
|p 3140 -
|2 Crossref
|t Magn Reson Med
|v 85
|y 2021
999 C 5 |a 10.1038/nature14539
|9 -- missing cx lookup --
|1 LeCun
|p 436 -
|2 Crossref
|t Nature
|v 521
|y 2015
999 C 5 |1 Ng
|y 2002
|2 Crossref
|o Ng 2002
999 C 5 |a 10.1109/TPAMI.2019.2910523
|9 -- missing cx lookup --
|1 Lathuilière
|p 2065 -
|2 Crossref
|t IEEE Trans Pattern Anal Mach Intell
|v 42
|y 2020
999 C 5 |a 10.1561/2200000056
|9 -- missing cx lookup --
|1 Kingma
|p 307 -
|2 Crossref
|t Found Trends® Mach Learn
|v 12
|y 2019
999 C 5 |1 Dupont
|y 2021
|2 Crossref
|o Dupont 2021
999 C 5 |1 Kingma
|y 2014
|2 Crossref
|o Kingma 2014
999 C 5 |1 Goodfellow
|y 2014
|2 Crossref
|o Goodfellow 2014
999 C 5 |a 10.1002/mrm.27192
|9 -- missing cx lookup --
|1 Ianni
|p 1871 -
|2 Crossref
|t Magn Reson Med
|v 80
|y 2018
999 C 5 |a 10.1002/mrm.22978
|9 -- missing cx lookup --
|1 Cloos
|p 72 -
|2 Crossref
|t Magn Reson Med
|v 67
|y 2012
999 C 5 |a 10.1002/mrm.27870
|1 Tomi-Tricot
|y 2019
|2 Crossref
|t Magn Reson Med
|9 -- missing cx lookup --
999 C 5 |a 10.1002/mrm.28667
|9 -- missing cx lookup --
|1 Vinding
|p 3308 -
|2 Crossref
|t Magn Reson Med
|v 85
|y 2021
999 C 5 |1 Tavaf
|y 2021
|2 Crossref
|o Tavaf 2021
999 C 5 |1 Zbontar
|y 2019
|2 Crossref
|o Zbontar 2019
999 C 5 |a 10.1002/mrm.28819
|9 -- missing cx lookup --
|1 Lan
|p 1718 -
|2 Crossref
|t Magn Reson Med
|v 86
|y 2021
999 C 5 |a 10.1002/mrm.27948
|9 -- missing cx lookup --
|1 Meliadò
|p 695 -
|2 Crossref
|t Magn Reson Med
|v 83
|y 2020
999 C 5 |a 10.1109/TMI.2020.3022968
|9 -- missing cx lookup --
|1 Lei
|p 105 -
|2 Crossref
|t IEEE Trans Med Imaging
|v 40
|y 2021
999 C 5 |a 10.1002/mrm.28590
|9 -- missing cx lookup --
|1 Abbasi-Rad
|p 2462 -
|2 Crossref
|t Magn Reson Med
|v 85
|y 2021
999 C 5 |a 10.1002/mrm.25689
|9 -- missing cx lookup --
|1 Wu
|p 1444 -
|2 Crossref
|t Magn Reson Med
|v 75
|y 2016
999 C 5 |1 Wang
|y 2018
|2 Crossref
|o Wang 2018
999 C 5 |1 Park
|y 2019
|2 Crossref
|o Park 2019
999 C 5 |1 Kassakian
|y 2006
|2 Crossref
|o Kassakian 2006
999 C 5 |1 Isola
|y 2018
|2 Crossref
|o Isola 2018
999 C 5 |1 Ronneberger
|y 2015
|2 Crossref
|o Ronneberger 2015
999 C 5 |a 10.1002/mrm.24158
|9 -- missing cx lookup --
|1 Nehrke
|p 1517 -
|2 Crossref
|t Magn Reson Med
|v 68
|y 2012
999 C 5 |a 10.1016/j.jmr.2014.06.006
|9 -- missing cx lookup --
|1 Tse
|p 125 -
|2 Crossref
|t J Magn Reson
|v 245
|y 2014
999 C 5 |a 10.1002/mrm.1910360421
|9 -- missing cx lookup --
|1 Kanayamay
|p 637 -
|2 Crossref
|t Magn Reson Med
|v 36
|y 1996
999 C 5 |1 NVlabs
|y 2020
|2 Crossref
|o NVlabs 2020
999 C 5 |1 He
|y 2016
|2 Crossref
|o He 2016
999 C 5 |1 Paszke
|y 2019
|2 Crossref
|o Paszke 2019
999 C 5 |1 Zhao
|y 2019
|2 Crossref
|o Zhao 2019
999 C 5 |a 10.1002/mrm.20978
|9 -- missing cx lookup --
|1 Grissom
|p 620 -
|2 Crossref
|t Magn Reson Med
|v 56
|y 2006
999 C 5 |a 10.1002/mrm.24726
|9 -- missing cx lookup --
|1 Shajan
|p 870 -
|2 Crossref
|t Magn Reson Med
|v 71
|y 2014
999 C 5 |a 10.1007/s10334-016-0543-6
|9 -- missing cx lookup --
|1 Tse
|p 333 -
|2 Crossref
|t Magn Reson Mater Phys Biol Med
|v 29
|y 2016
999 C 5 |a 10.1002/mrm.26501
|9 -- missing cx lookup --
|1 Tse
|p 1050 -
|2 Crossref
|t Magn Reson Med
|v 78
|y 2017
999 C 5 |a 10.1002/mrm.25512
|9 -- missing cx lookup --
|1 Schmitter
|p 1291 -
|2 Crossref
|t Magn Reson Med
|v 74
|y 2015
999 C 5 |a 10.1109/TMI.2013.2295465
|9 -- missing cx lookup --
|1 Hoyos-Idrobo
|p 739 -
|2 Crossref
|t IEEE Trans Med Imaging
|v 33
|y 2014
999 C 5 |1 Hansen
|y 2015
|2 Crossref
|o Hansen 2015
999 C 5 |a 10.1186/s40537-019-0197-0
|9 -- missing cx lookup --
|1 Shorten
|p 60 -
|2 Crossref
|t J. Big Data
|v 6
|y 2019
999 C 5 |a 10.1002/mrm.26086
|9 -- missing cx lookup --
|1 Vinding
|p 374 -
|2 Crossref
|t Magn Reson Med
|v 77
|y 2017
999 C 5 |a 10.1002/mrm.24311
|9 -- missing cx lookup --
|1 Yoon
|p 278 -
|2 Crossref
|t Magn Reson Med
|v 68
|y 2012

LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21