000906178 001__ 906178
000906178 005__ 20230217124246.0
000906178 0247_ $$2doi$$a10.1016/j.zemedi.2021.12.003
000906178 0247_ $$2ISSN$$a0040-5973
000906178 0247_ $$2ISSN$$a0939-3889
000906178 0247_ $$2ISSN$$a1876-4436
000906178 0247_ $$2Handle$$a2128/31907
000906178 0247_ $$2WOS$$aWOS:000878590000008
000906178 037__ $$aFZJ-2022-01278
000906178 082__ $$a610
000906178 1001_ $$0P:(DE-Juel1)166296$$aEberhardt, Boris$$b0
000906178 245__ $$aB1 field map synthesis with generative deep learning used in the design of parallel-transmit RF pulses for ultra-high field MRI
000906178 260__ $$aAmsterdam$$bElsevier, Urban & Fischer$$c2022
000906178 264_1 $$2Crossref$$3print$$bElsevier BV$$c2022-08-01
000906178 264_1 $$2Crossref$$3print$$bElsevier BV$$c2022-08-01
000906178 3367_ $$2DRIVER$$aarticle
000906178 3367_ $$2DataCite$$aOutput Types/Journal article
000906178 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1664264235_9370
000906178 3367_ $$2BibTeX$$aARTICLE
000906178 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000906178 3367_ $$00$$2EndNote$$aJournal Article
000906178 520__ $$aSpoke trajectory parallel transmit (pTX) excitation in ultra-high field MRI enablesinhomogeneities arising from the shortened RF wavelength in biological tissue to be mitigated. To this end, current RF excitation pulse design algorithms either employ the acquisition of field maps with subsequent non-linear optimization or a universal approach applying robust pre-computed pulses. We suggest and evaluate an intermediate method that uses a subset of acquired field maps combined with generative machine learning models to reduce the pulse calibration time while offering more tailored excitation than robust pulses (RP).The possibility of employing image-to-image translation and semantic image synthesis machine learning models based on generative adversarial networks (GANs) to deduce the missing field maps is examined. Additionally, an RF pulse design that employs a predictive machine learning model to find solutions for the non-linear (two-spokes) pulse design problem is investigated.As a proof of concept, we present simulation results obtained with the suggested machine learning approaches that were trained on a limited data-set, acquired in vivo. The achieved excitation homogeneity based on a subset of half of themaps acquired in the calibration scans and half of the maps synthesized with GANs is comparable with state of the art pulse design methods when using the full set of calibration data while halving the total calibration time. By employing RP dictionaries or machine-learning RF pulse predictions, the total calibration time can be reduced significantly as these methods take only seconds or milliseconds per slice, respectively.
000906178 536__ $$0G:(DE-HGF)POF4-5253$$a5253 - Neuroimaging (POF4-525)$$cPOF4-525$$fPOF IV$$x0
000906178 542__ $$2Crossref$$i2022-08-01$$uhttps://www.elsevier.com/tdm/userlicense/1.0/
000906178 542__ $$2Crossref$$i2021-12-28$$uhttp://creativecommons.org/licenses/by-nc-nd/4.0/
000906178 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
000906178 7001_ $$00000-0001-8190-4367$$aPoser, Benedikt A.$$b1
000906178 7001_ $$0P:(DE-Juel1)131794$$aShah, N. Jon$$b2$$ufzj
000906178 7001_ $$0P:(DE-Juel1)131761$$aFelder, Jörg$$b3$$eCorresponding author
000906178 77318 $$2Crossref$$3journal-article$$a10.1016/j.zemedi.2021.12.003$$bElsevier BV$$d2022-08-01$$n3$$p334-345$$tZeitschrift für Medizinische Physik$$v32$$x0939-3889$$y2022
000906178 773__ $$0PERI:(DE-600)2231492-1$$a10.1016/j.zemedi.2021.12.003$$gp. S0939388921001161$$n3$$p334-345$$tZeitschrift für medizinische Physik$$v32$$x0939-3889$$y2022
000906178 8564_ $$uhttps://juser.fz-juelich.de/record/906178/files/1-s2.0-S0939388921001161-main.pdf$$yOpenAccess
000906178 909CO $$ooai:juser.fz-juelich.de:906178$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
000906178 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)166296$$aForschungszentrum Jülich$$b0$$kFZJ
000906178 9101_ $$0I:(DE-HGF)0$$60000-0001-8190-4367$$aExternal Institute$$b1$$kExtern
000906178 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131794$$aForschungszentrum Jülich$$b2$$kFZJ
000906178 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131761$$aForschungszentrum Jülich$$b3$$kFZJ
000906178 9131_ $$0G:(DE-HGF)POF4-525$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5253$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vDecoding Brain Organization and Dysfunction$$x0
000906178 9141_ $$y2022
000906178 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS
000906178 915__ $$0LIC:(DE-HGF)CCBYNCND4$$2HGFVOC$$aCreative Commons Attribution-NonCommercial-NoDerivs CC BY-NC-ND 4.0
000906178 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bZ MED PHYS : 2015
000906178 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection
000906178 915__ $$0StatID:(DE-HGF)0111$$2StatID$$aWoS$$bScience Citation Index Expanded
000906178 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5
000906178 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000906178 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline
000906178 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bThomson Reuters Master Journal List
000906178 9201_ $$0I:(DE-Juel1)INM-4-20090406$$kINM-4$$lPhysik der Medizinischen Bildgebung$$x0
000906178 9201_ $$0I:(DE-Juel1)INM-11-20170113$$kINM-11$$lJara-Institut Quantum Information$$x1
000906178 9201_ $$0I:(DE-Juel1)VDB1046$$kJARA-BRAIN$$lJülich-Aachen Research Alliance - Translational Brain Medicine$$x2
000906178 980__ $$ajournal
000906178 980__ $$aVDB
000906178 980__ $$aUNRESTRICTED
000906178 980__ $$aI:(DE-Juel1)INM-4-20090406
000906178 980__ $$aI:(DE-Juel1)INM-11-20170113
000906178 980__ $$aI:(DE-Juel1)VDB1046
000906178 9801_ $$aFullTexts
000906178 999C5 $$1Deniz$$2Crossref$$9-- missing cx lookup --$$a10.1097/RMR.0000000000000204$$p159 -$$tTop Magn Reson Imaging$$v28$$y2019
000906178 999C5 $$1Van de Moortele$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.20708$$p1503 -$$tMagn Reson Med$$v54$$y2005
000906178 999C5 $$1Vaughan$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.21073$$p1274 -$$tMagn Reson Med$$v56$$y2006
000906178 999C5 $$1Katscher$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.10353$$p144 -$$tMagn Reson Med$$v49$$y2003
000906178 999C5 $$1Zhu$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.20011$$p775 -$$tMagn Reson Med$$v51$$y2004
000906178 999C5 $$1Saekho$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.20840$$p719 -$$tMagn Reson Med$$v55$$y2006
000906178 999C5 $$1Grissom$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.26512$$p1352 -$$tMagn Reson Med$$v78$$y2017
000906178 999C5 $$1Setsompop$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.21513$$p908 -$$tMagn Reson Med$$v59$$y2008
000906178 999C5 $$1Paez$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.28820$$tMagn Reson Med$$y2021
000906178 999C5 $$1Dupas$$2Crossref$$9-- missing cx lookup --$$a10.1016/j.jmr.2015.03.013$$p59 -$$tJ Magn Reson$$v255$$y2015
000906178 999C5 $$1Eberhardt$$2Crossref$$9-- missing cx lookup --$$a10.1109/TMI.2020.3013982$$p4225 -$$tIEEE Trans Med Imaging$$v39$$y2020
000906178 999C5 $$1Guerin$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.24800$$p1446 -$$tMagn Reson Med$$v71$$y2014
000906178 999C5 $$1Gras$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.26491$$p1009 -$$tMagn Reson Med$$v78$$y2017
000906178 999C5 $$1Gras$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.26148$$p635 -$$tMagn Reson Med$$v77$$y2017
000906178 999C5 $$1Gras$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.27001$$p53 -$$tMagn Reson Med$$v80$$y2018
000906178 999C5 $$1Herrler$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.28643$$p3140 -$$tMagn Reson Med$$v85$$y2021
000906178 999C5 $$1LeCun$$2Crossref$$9-- missing cx lookup --$$a10.1038/nature14539$$p436 -$$tNature$$v521$$y2015
000906178 999C5 $$1Ng$$2Crossref$$oNg 2002$$y2002
000906178 999C5 $$1Lathuilière$$2Crossref$$9-- missing cx lookup --$$a10.1109/TPAMI.2019.2910523$$p2065 -$$tIEEE Trans Pattern Anal Mach Intell$$v42$$y2020
000906178 999C5 $$1Kingma$$2Crossref$$9-- missing cx lookup --$$a10.1561/2200000056$$p307 -$$tFound Trends® Mach Learn$$v12$$y2019
000906178 999C5 $$1Dupont$$2Crossref$$oDupont 2021$$y2021
000906178 999C5 $$1Kingma$$2Crossref$$oKingma 2014$$y2014
000906178 999C5 $$1Goodfellow$$2Crossref$$oGoodfellow 2014$$y2014
000906178 999C5 $$1Ianni$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.27192$$p1871 -$$tMagn Reson Med$$v80$$y2018
000906178 999C5 $$1Cloos$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.22978$$p72 -$$tMagn Reson Med$$v67$$y2012
000906178 999C5 $$1Tomi-Tricot$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.27870$$tMagn Reson Med$$y2019
000906178 999C5 $$1Vinding$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.28667$$p3308 -$$tMagn Reson Med$$v85$$y2021
000906178 999C5 $$1Tavaf$$2Crossref$$oTavaf 2021$$y2021
000906178 999C5 $$1Zbontar$$2Crossref$$oZbontar 2019$$y2019
000906178 999C5 $$1Lan$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.28819$$p1718 -$$tMagn Reson Med$$v86$$y2021
000906178 999C5 $$1Meliadò$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.27948$$p695 -$$tMagn Reson Med$$v83$$y2020
000906178 999C5 $$1Lei$$2Crossref$$9-- missing cx lookup --$$a10.1109/TMI.2020.3022968$$p105 -$$tIEEE Trans Med Imaging$$v40$$y2021
000906178 999C5 $$1Abbasi-Rad$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.28590$$p2462 -$$tMagn Reson Med$$v85$$y2021
000906178 999C5 $$1Wu$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.25689$$p1444 -$$tMagn Reson Med$$v75$$y2016
000906178 999C5 $$1Wang$$2Crossref$$oWang 2018$$y2018
000906178 999C5 $$1Park$$2Crossref$$oPark 2019$$y2019
000906178 999C5 $$1Kassakian$$2Crossref$$oKassakian 2006$$y2006
000906178 999C5 $$1Isola$$2Crossref$$oIsola 2018$$y2018
000906178 999C5 $$1Ronneberger$$2Crossref$$oRonneberger 2015$$y2015
000906178 999C5 $$1Nehrke$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.24158$$p1517 -$$tMagn Reson Med$$v68$$y2012
000906178 999C5 $$1Tse$$2Crossref$$9-- missing cx lookup --$$a10.1016/j.jmr.2014.06.006$$p125 -$$tJ Magn Reson$$v245$$y2014
000906178 999C5 $$1Kanayamay$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.1910360421$$p637 -$$tMagn Reson Med$$v36$$y1996
000906178 999C5 $$1NVlabs$$2Crossref$$oNVlabs 2020$$y2020
000906178 999C5 $$1He$$2Crossref$$oHe 2016$$y2016
000906178 999C5 $$1Paszke$$2Crossref$$oPaszke 2019$$y2019
000906178 999C5 $$1Zhao$$2Crossref$$oZhao 2019$$y2019
000906178 999C5 $$1Grissom$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.20978$$p620 -$$tMagn Reson Med$$v56$$y2006
000906178 999C5 $$1Shajan$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.24726$$p870 -$$tMagn Reson Med$$v71$$y2014
000906178 999C5 $$1Tse$$2Crossref$$9-- missing cx lookup --$$a10.1007/s10334-016-0543-6$$p333 -$$tMagn Reson Mater Phys Biol Med$$v29$$y2016
000906178 999C5 $$1Tse$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.26501$$p1050 -$$tMagn Reson Med$$v78$$y2017
000906178 999C5 $$1Schmitter$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.25512$$p1291 -$$tMagn Reson Med$$v74$$y2015
000906178 999C5 $$1Hoyos-Idrobo$$2Crossref$$9-- missing cx lookup --$$a10.1109/TMI.2013.2295465$$p739 -$$tIEEE Trans Med Imaging$$v33$$y2014
000906178 999C5 $$1Hansen$$2Crossref$$oHansen 2015$$y2015
000906178 999C5 $$1Shorten$$2Crossref$$9-- missing cx lookup --$$a10.1186/s40537-019-0197-0$$p60 -$$tJ. Big Data$$v6$$y2019
000906178 999C5 $$1Vinding$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.26086$$p374 -$$tMagn Reson Med$$v77$$y2017
000906178 999C5 $$1Yoon$$2Crossref$$9-- missing cx lookup --$$a10.1002/mrm.24311$$p278 -$$tMagn Reson Med$$v68$$y2012