000287250 001__ 287250
000287250 005__ 20250731110623.0
000287250 0247_ $$2doi$$a10.1002/mrm.30014
000287250 0247_ $$2pmid$$apmid:38247050
000287250 0247_ $$2ISSN$$a1522-2594
000287250 0247_ $$2ISSN$$a0740-3194
000287250 037__ $$aDKFZ-2024-00182
000287250 041__ $$aEnglish
000287250 082__ $$a610
000287250 1001_ $$00000-0001-7969-5738$$aKilic, Toygan$$b0
000287250 245__ $$aUnsupervised deep learning with convolutional neural networks for static parallel transmit design: A retrospective study.
000287250 260__ $$aNew York, NY [u.a.]$$bWiley-Liss$$c2024
000287250 3367_ $$2DRIVER$$aarticle
000287250 3367_ $$2DataCite$$aOutput Types/Journal article
000287250 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1712665138_9969
000287250 3367_ $$2BibTeX$$aARTICLE
000287250 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000287250 3367_ $$00$$2EndNote$$aJournal Article
000287250 500__ $$a2024 Jun;91(6):2498-2507
000287250 520__ $$aTo mitigate B 1 + $$ {B}_1^{+} $$ inhomogeneity at 7T for multi-channel transmit arrays using unsupervised deep learning with convolutional neural networks (CNNs).Deep learning parallel transmit (pTx) pulse design has received attention, but such methods have relied on supervised training and did not use CNNs for multi-channel B 1 + $$ {B}_1^{+} $$ maps. In this work, we introduce an alternative approach that facilitates the use of CNNs with multi-channel B 1 + $$ {B}_1^{+} $$ maps while performing unsupervised training. The multi-channel B 1 + $$ {B}_1^{+} $$ maps are concatenated along the spatial dimension to enable shift-equivariant processing amenable to CNNs. Training is performed in an unsupervised manner using a physics-driven loss function that minimizes the discrepancy of the Bloch simulation with the target magnetization, which eliminates the calculation of reference transmit RF weights. The training database comprises 3824 2D sagittal, multi-channel B 1 + $$ {B}_1^{+} $$ maps of the healthy human brain from 143 subjects. B 1 + $$ {B}_1^{+} $$ data were acquired at 7T using an 8Tx/32Rx head coil. The proposed method is compared to the unregularized magnitude least-squares (MLS) solution for the target magnetization in static pTx design.The proposed method outperformed the unregularized MLS solution for RMS error and coefficient-of-variation and had comparable energy consumption. Additionally, the proposed method did not show local phase singularities leading to distinct holes in the resulting magnetization unlike the unregularized MLS solution.Proposed unsupervised deep learning with CNNs performs better than unregularized MLS in static pTx for speed and robustness.
000287250 536__ $$0G:(DE-HGF)POF4-315$$a315 - Bildgebung und Radioonkologie (POF4-315)$$cPOF4-315$$fPOF IV$$x0
000287250 588__ $$aDataset connected to CrossRef, PubMed, , Journals: inrepo02.dkfz.de
000287250 650_7 $$2Other$$a7 T
000287250 650_7 $$2Other$$aRF inhomogeneity mitigation
000287250 650_7 $$2Other$$aconvolutional neural networks
000287250 650_7 $$2Other$$adeep learning
000287250 650_7 $$2Other$$aparallel excitation
000287250 650_7 $$2Other$$aunsupervised learning
000287250 7001_ $$00000-0001-7342-3715$$aLiebig, Patrick$$b1
000287250 7001_ $$00000-0003-4726-0590$$aDemirel, Omer Burak$$b2
000287250 7001_ $$00000-0002-4620-8216$$aHerrler, Jürgen$$b3
000287250 7001_ $$0P:(DE-He78)054fd7a5195b75b11fbdc5c360276011$$aNagel, Armin$$b4$$udkfz
000287250 7001_ $$aUgurbil, Kamil$$b5
000287250 7001_ $$00000-0001-6400-7736$$aAkçakaya, Mehmet$$b6
000287250 773__ $$0PERI:(DE-600)1493786-4$$a10.1002/mrm.30014$$gp. mrm.30014$$n6$$p2498-2507$$tMagnetic resonance in medicine$$v91$$x1522-2594$$y2024
000287250 8564_ $$uhttps://inrepo02.dkfz.de/record/287250/files/Magnetic%20Resonance%20in%20Med%20-%202024%20-%20Kilic%20-%20Unsupervised%20deep%20learning%20with%20convolutional%20neural%20networks%20for%20static.pdf
000287250 8564_ $$uhttps://inrepo02.dkfz.de/record/287250/files/Magnetic%20Resonance%20in%20Med%20-%202024%20-%20Kilic%20-%20Unsupervised%20deep%20learning%20with%20convolutional%20neural%20networks%20for%20static.pdf?subformat=pdfa$$xpdfa
000287250 909CO $$ooai:inrepo02.dkfz.de:287250$$pVDB
000287250 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)054fd7a5195b75b11fbdc5c360276011$$aDeutsches Krebsforschungszentrum$$b4$$kDKFZ
000287250 9131_ $$0G:(DE-HGF)POF4-315$$1G:(DE-HGF)POF4-310$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lKrebsforschung$$vBildgebung und Radioonkologie$$x0
000287250 9141_ $$y2024
000287250 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz$$d2023-10-21$$wger
000287250 915__ $$0StatID:(DE-HGF)3001$$2StatID$$aDEAL Wiley$$d2023-10-21$$wger
000287250 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bMAGN RESON MED : 2022$$d2023-10-21
000287250 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2023-10-21
000287250 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2023-10-21
000287250 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2023-10-21
000287250 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2023-10-21
000287250 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2023-10-21
000287250 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2023-10-21
000287250 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences$$d2023-10-21
000287250 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2023-10-21
000287250 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2023-10-21
000287250 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine$$d2023-10-21
000287250 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2023-10-21
000287250 9201_ $$0I:(DE-He78)E020-20160331$$kE020$$lE020 Med. Physik in der Radiologie$$x0
000287250 980__ $$ajournal
000287250 980__ $$aVDB
000287250 980__ $$aI:(DE-He78)E020-20160331
000287250 980__ $$aUNRESTRICTED