Kerstin Hammernik1, Teresa Klatzer1, Erich Kobler1, Michael P Recht2,3, Daniel K Sodickson2,3, Thomas Pock1,4, Florian Knoll2,3. 1. Institute of Computer Graphics and Vision, Graz University of Technology, Graz, Austria. 2. Center for Biomedical Imaging, Department of Radiology, NYU School of Medicine, New York, New York, USA. 3. Center for Advanced Imaging Innovation and Research (CAI2R), NYU School of Medicine, New York, New York, USA. 4. Center for Vision, Automation & Control, AIT Austrian Institute of Technology GmbH, Vienna, Austria.
Abstract
PURPOSE: To allow fast and high-quality reconstruction of clinical accelerated multi-coil MR data by learning a variational network that combines the mathematical structure of variational models with deep learning. THEORY AND METHODS: Generalized compressed sensing reconstruction formulated as a variational model is embedded in an unrolled gradient descent scheme. All parameters of this formulation, including the prior model defined by filter kernels and activation functions as well as the data term weights, are learned during an offline training procedure. The learned model can then be applied online to previously unseen data. RESULTS: The variational network approach is evaluated on a clinical knee imaging protocol for different acceleration factors and sampling patterns using retrospectively and prospectively undersampled data. The variational network reconstructions outperform standard reconstruction algorithms, verified by quantitative error measures and a clinical reader study for regular sampling and acceleration factor 4. CONCLUSION: Variational network reconstructions preserve the natural appearance of MR images as well as pathologies that were not included in the training data set. Due to its high computational performance, that is, reconstruction time of 193 ms on a single graphics card, and the omission of parameter tuning once the network is trained, this new approach to image reconstruction can easily be integrated into clinical workflow. Magn Reson Med 79:3055-3071, 2018.
PURPOSE: To allow fast and high-quality reconstruction of clinical accelerated multi-coil MR data by learning a variational network that combines the mathematical structure of variational models with deep learning. THEORY AND METHODS: Generalized compressed sensing reconstruction formulated as a variational model is embedded in an unrolled gradient descent scheme. All parameters of this formulation, including the prior model defined by filter kernels and activation functions as well as the data term weights, are learned during an offline training procedure. The learned model can then be applied online to previously unseen data. RESULTS: The variational network approach is evaluated on a clinical knee imaging protocol for different acceleration factors and sampling patterns using retrospectively and prospectively undersampled data. The variational network reconstructions outperform standard reconstruction algorithms, verified by quantitative error measures and a clinical reader study for regular sampling and acceleration factor 4. CONCLUSION: Variational network reconstructions preserve the natural appearance of MR images as well as pathologies that were not included in the training data set. Due to its high computational performance, that is, reconstruction time of 193 ms on a single graphics card, and the omission of parameter tuning once the network is trained, this new approach to image reconstruction can easily be integrated into clinical workflow. Magn Reson Med 79:3055-3071, 2018.
Authors: Mark A Griswold; Peter M Jakob; Robin M Heidemann; Mathias Nittka; Vladimir Jellus; Jianmin Wang; Berthold Kiefer; Axel Haase Journal: Magn Reson Med Date: 2002-06 Impact factor: 4.668
Authors: Pim Moeskops; Max A Viergever; Adrienne M Mendrik; Linda S de Vries; Manon J N L Benders; Ivana Isgum Journal: IEEE Trans Med Imaging Date: 2016-03-30 Impact factor: 10.048
Authors: Vladimir Golkov; Alexey Dosovitskiy; Jonathan I Sperl; Marion I Menzel; Michael Czisch; Philipp Samann; Thomas Brox; Daniel Cremers Journal: IEEE Trans Med Imaging Date: 2016-04-06 Impact factor: 10.048
Authors: Florian Knoll; Christian Clason; Kristian Bredies; Martin Uecker; Rudolf Stollberger Journal: Magn Reson Med Date: 2011-06-27 Impact factor: 4.668
Authors: Martin Uecker; Peng Lai; Mark J Murphy; Patrick Virtue; Michael Elad; John M Pauly; Shreyas S Vasanawala; Michael Lustig Journal: Magn Reson Med Date: 2014-03 Impact factor: 4.668
Authors: Michael P Recht; Kai Tobias Block; Hersh Chandarana; Jennifer Friedland; Thomas Mullholland; Donal Teahan; Roy Wiggins Journal: AJR Am J Roentgenol Date: 2019-02-26 Impact factor: 3.959
Authors: Berkin Bilgic; Itthi Chatnuntawech; Mary Kate Manhard; Qiyuan Tian; Congyu Liao; Siddharth S Iyer; Stephen F Cauley; Susie Y Huang; Jonathan R Polimeni; Lawrence L Wald; Kawin Setsompop Journal: Magn Reson Med Date: 2019-05-20 Impact factor: 4.668
Authors: Ukash Nakarmi; Joseph Y Cheng; Edgar P Rios; Morteza Mardani; John M Pauly; Leslie Ying; Shreyas S Vasanawala Journal: Proc IEEE Int Symp Biomed Imaging Date: 2020-05-22