000306255 001__ 306255
000306255 005__ 20251119115818.0
000306255 0247_ $$2doi$$a10.1371/journal.pone.0334604
000306255 0247_ $$2pmid$$apmid:41248138
000306255 037__ $$aDKFZ-2025-02484
000306255 041__ $$aEnglish
000306255 082__ $$a610
000306255 1001_ $$00000-0002-8623-8110$$aTopalis, Johanna$$b0
000306255 245__ $$aFast machine learning image reconstruction of radially undersampled k-space data for low-latency real-time MRI.
000306255 260__ $$aSan Francisco, California, US$$bPLOS$$c2025
000306255 3367_ $$2DRIVER$$aarticle
000306255 3367_ $$2DataCite$$aOutput Types/Journal article
000306255 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1763538518_2172553
000306255 3367_ $$2BibTeX$$aARTICLE
000306255 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000306255 3367_ $$00$$2EndNote$$aJournal Article
000306255 520__ $$aFast data acquisition and fast image reconstruction are essential to enable low-latency real-time magnetic resonance (MR) imaging applications with high temporal resolution such as interstitial percutaneous needle interventions or MR-guided radiotherapy. To accelerate the image reconstruction of radially undersampled 2D k-space data, we propose a machine learning (ML) model that consists of a single fully connected linear layer to interpolate radial k-space data to a Cartesian grid, followed by a conventional 2D inverse fast Fourier transform. This k-space-to-image ML model was trained on synthetic data from natural images. It was evaluated with respect to image quality (mean squared error (MSE) compared to ground truth where available) and reconstruction time both on synthetic data with undersampling factors R between 2 and 10 as well as on radial k-space data from MR measurements on two different MRI systems. For comparison, conventional non-iterative zero-filling non-uniform fast Fourier transform (NUFFT) reconstruction and compressed sensing (CS) reconstruction were used. On synthetic data, the ML model achieved better median MSE values than the non-iterative NUFFT reconstruction. The interquartile ranges of the MSE distributions overlapped for the ML and CS reconstructions for all R. Reconstruction times of the ML approach were shorter than for NUFFT and substantially shorter than for CS reconstructions. The generalizability (for real MRI data) of the ML model was demonstrated by reconstructing 0.35-tesla MR-Linac dynamic measurements of three volunteers and phantom data from a diagnostic 1.5-tesla MRI system; the median reconstruction time for the coil-combined images was much shorter than for the conventional approach (ML: [Formula: see text]; NUFFT: [Formula: see text]). The proposed ML model reconstructs MR data with reduced streaking artifacts compared to non-iterative NUFFT techniques and with extremely short reconstruction times; thus, it is ideally suited for rapid low-latency real-time MR applications.
000306255 536__ $$0G:(DE-HGF)POF4-899$$a899 - ohne Topic (POF4-899)$$cPOF4-899$$fPOF IV$$x0
000306255 588__ $$aDataset connected to CrossRef, PubMed, , Journals: inrepo02.dkfz.de
000306255 650_2 $$2MeSH$$aMagnetic Resonance Imaging: methods
000306255 650_2 $$2MeSH$$aMachine Learning
000306255 650_2 $$2MeSH$$aHumans
000306255 650_2 $$2MeSH$$aImage Processing, Computer-Assisted: methods
000306255 650_2 $$2MeSH$$aAlgorithms
000306255 650_2 $$2MeSH$$aFourier Analysis
000306255 650_2 $$2MeSH$$aPhantoms, Imaging
000306255 7001_ $$aDexl, Jakob$$b1
000306255 7001_ $$00000-0002-8678-7152$$aJeblick, Katharina$$b2
000306255 7001_ $$aKlaar, Rabea$$b3
000306255 7001_ $$aKurz, Christopher$$b4
000306255 7001_ $$aLöhr, Timo$$b5
000306255 7001_ $$aMittermeier, Andreas$$b6
000306255 7001_ $$00000-0002-8712-3948$$aSchachtner, Balthasar$$b7
000306255 7001_ $$aStüber, Anna Theresa$$b8
000306255 7001_ $$aWeber, Tobias$$b9
000306255 7001_ $$aWesp, Philipp$$b10
000306255 7001_ $$aRicke, Jens$$b11
000306255 7001_ $$aSeidensticker, Max$$b12
000306255 7001_ $$0P:(DE-HGF)0$$aLandry, Guillaume$$b13
000306255 7001_ $$aIngrisch, Michael$$b14
000306255 7001_ $$00000-0001-6182-5039$$aDietrich, Olaf$$b15
000306255 773__ $$0PERI:(DE-600)2267670-3$$a10.1371/journal.pone.0334604$$gVol. 20, no. 11, p. e0334604 -$$n11$$pe0334604 -$$tPLOS ONE$$v20$$x1932-6203$$y2025
000306255 909CO $$ooai:inrepo02.dkfz.de:306255$$pVDB
000306255 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-HGF)0$$aDeutsches Krebsforschungszentrum$$b13$$kDKFZ
000306255 9131_ $$0G:(DE-HGF)POF4-899$$1G:(DE-HGF)POF4-890$$2G:(DE-HGF)POF4-800$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bProgrammungebundene Forschung$$lohne Programm$$vohne Topic$$x0
000306255 9141_ $$y2025
000306255 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bPLOS ONE : 2022$$d2024-12-16
000306255 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-16
000306255 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2024-12-16
000306255 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2024-02-08T09:37:46Z
000306255 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2024-02-08T09:37:46Z
000306255 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Anonymous peer review$$d2024-02-08T09:37:46Z
000306255 915__ $$0LIC:(DE-HGF)CCBYNV$$2V:(DE-HGF)$$aCreative Commons Attribution CC BY (No Version)$$bDOAJ$$d2024-02-08T09:37:46Z
000306255 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2024-12-16
000306255 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2024-12-16
000306255 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2024-12-16
000306255 915__ $$0StatID:(DE-HGF)1040$$2StatID$$aDBCoverage$$bZoological Record$$d2024-12-16
000306255 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2024-12-16
000306255 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2024-12-16
000306255 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2024-12-16
000306255 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2024-12-16
000306255 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2024-12-16
000306255 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2024-12-16
000306255 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2024-12-16
000306255 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2024-12-16
000306255 9201_ $$0I:(DE-He78)MU01-20160331$$kMU01$$lDKTK Koordinierungsstelle München$$x0
000306255 980__ $$ajournal
000306255 980__ $$aVDB
000306255 980__ $$aI:(DE-He78)MU01-20160331
000306255 980__ $$aUNRESTRICTED