000182656 001__ 182656
000182656 005__ 20240229145726.0
000182656 0247_ $$2doi$$a10.1002/mrm.29520
000182656 0247_ $$2pmid$$apmid:36377762
000182656 0247_ $$2ISSN$$a0740-3194
000182656 0247_ $$2ISSN$$a1522-2594
000182656 0247_ $$2altmetric$$aaltmetric:138461580
000182656 037__ $$aDKFZ-2022-02828
000182656 041__ $$aEnglish
000182656 082__ $$a610
000182656 1001_ $$00000-0002-8152-7271$$aHunger, Leonie$$b0
000182656 245__ $$aDeepCEST 7 T: Fast and homogeneous mapping of 7 T CEST MRI parameters and their uncertainty quantification.
000182656 260__ $$aNew York, NY [u.a.]$$bWiley-Liss$$c2023
000182656 3367_ $$2DRIVER$$aarticle
000182656 3367_ $$2DataCite$$aOutput Types/Journal article
000182656 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1675327204_2343
000182656 3367_ $$2BibTeX$$aARTICLE
000182656 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000182656 3367_ $$00$$2EndNote$$aJournal Article
000182656 500__ $$a2023 Apr;89(4):1543-1556
000182656 520__ $$aIn this work, we investigated the ability of neural networks to rapidly and robustly predict Lorentzian parameters of multi-pool CEST MRI spectra at 7 T with corresponding uncertainty maps to make them quickly and easily available for routine clinical use.We developed a deepCEST 7 T approach that generates CEST contrasts from just 1 scan with robustness against B1 inhomogeneities. The input data for a neural feed-forward network consisted of 7 T in vivo uncorrected Z-spectra of a single B1 level, and a B1 map. The 7 T raw data were acquired using a 3D snapshot gradient echo multiple interleaved mode saturation CEST sequence. These inputs were mapped voxel-wise to target data consisting of Lorentzian amplitudes generated conventionally by 5-pool Lorentzian fitting of normalized, denoised, B0 - and B1 -corrected Z-spectra. The deepCEST network was trained with Gaussian negative log-likelihood loss, providing an uncertainty quantification in addition to the Lorentzian amplitudes.The deepCEST 7 T network provides fast and accurate prediction of all Lorentzian parameters also when only a single B1 level is used. The prediction was highly accurate with respect to the Lorentzian fit amplitudes, and both healthy tissues and hyperintensities in tumor areas are predicted with a low uncertainty. In corrupted cases, high uncertainty indicated wrong predictions reliably.The proposed deepCEST 7 T approach reduces scan time by 50% to now 6:42 min, but still delivers both B0 - and B1 -corrected homogeneous CEST contrasts along with an uncertainty map, which can increase diagnostic confidence. Multiple accurate 7 T CEST contrasts are delivered within seconds.
000182656 536__ $$0G:(DE-HGF)POF4-315$$a315 - Bildgebung und Radioonkologie (POF4-315)$$cPOF4-315$$fPOF IV$$x0
000182656 588__ $$aDataset connected to CrossRef, PubMed, , Journals: inrepo02.dkfz.de
000182656 650_7 $$2Other$$aCEST
000182656 650_7 $$2Other$$aamide
000182656 650_7 $$2Other$$adeep learning
000182656 650_7 $$2Other$$aneural networks
000182656 650_7 $$2Other$$arNOE
000182656 650_7 $$2Other$$auncertainty quantification
000182656 7001_ $$00000-0002-3869-6918$$aRajput, Junaid R$$b1
000182656 7001_ $$00000-0001-8779-0209$$aKlein, Kiril$$b2
000182656 7001_ $$00000-0001-6795-5627$$aMennecke, Angelika$$b3
000182656 7001_ $$00000-0001-5437-8576$$aFabian, Moritz S$$b4
000182656 7001_ $$aSchmidt, Manuel$$b5
000182656 7001_ $$00000-0003-3506-4947$$aGlang, Felix$$b6
000182656 7001_ $$00000-0002-7286-1454$$aHerz, Kai$$b7
000182656 7001_ $$00000-0001-7342-3715$$aLiebig, Patrick$$b8
000182656 7001_ $$0P:(DE-He78)054fd7a5195b75b11fbdc5c360276011$$aNagel, Armin$$b9$$udkfz
000182656 7001_ $$00000-0001-6316-8773$$aScheffler, Klaus$$b10
000182656 7001_ $$aDörfler, Arnd$$b11
000182656 7001_ $$00000-0002-9550-5284$$aMaier, Andreas$$b12
000182656 7001_ $$aZaiss, Moritz$$b13
000182656 773__ $$0PERI:(DE-600)1493786-4$$a10.1002/mrm.29520$$gp. mrm.29520$$n4$$p1543-1556$$tMagnetic resonance in medicine$$v89$$x0740-3194$$y2023
000182656 909CO $$ooai:inrepo02.dkfz.de:182656$$pVDB
000182656 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)054fd7a5195b75b11fbdc5c360276011$$aDeutsches Krebsforschungszentrum$$b9$$kDKFZ
000182656 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
000182656 9141_ $$y2022
000182656 915__ $$0StatID:(DE-HGF)3001$$2StatID$$aDEAL Wiley$$d2021-01-27$$wger
000182656 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2021-01-27
000182656 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2021-01-27
000182656 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2021-01-27
000182656 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz$$d2023-10-21$$wger
000182656 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bMAGN RESON MED : 2022$$d2023-10-21
000182656 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2023-10-21
000182656 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2023-10-21
000182656 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2023-10-21
000182656 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2023-10-21
000182656 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2023-10-21
000182656 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences$$d2023-10-21
000182656 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine$$d2023-10-21
000182656 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2023-10-21
000182656 9201_ $$0I:(DE-He78)E020-20160331$$kE020$$lE020 Med. Physik in der Radiologie$$x0
000182656 980__ $$ajournal
000182656 980__ $$aVDB
000182656 980__ $$aI:(DE-He78)E020-20160331
000182656 980__ $$aUNRESTRICTED