Literature DB >> 29115689

Learning a variational network for reconstruction of accelerated MRI data.

Kerstin Hammernik1, Teresa Klatzer1, Erich Kobler1, Michael P Recht2,3, Daniel K Sodickson2,3, Thomas Pock1,4, Florian Knoll2,3.   

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.
© 2017 International Society for Magnetic Resonance in Medicine. © 2017 International Society for Magnetic Resonance in Medicine.

Entities:  

Keywords:  accelerated MRI; compressed sensing; deep learning; image reconstruction; parallel imaging; variational network

Mesh:

Year:  2017        PMID: 29115689      PMCID: PMC5902683          DOI: 10.1002/mrm.26977

Source DB:  PubMed          Journal:  Magn Reson Med        ISSN: 0740-3194            Impact factor:   4.668


  19 in total

1.  Generalized autocalibrating partially parallel acquisitions (GRAPPA).

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

2.  Image quality assessment: from error visibility to structural similarity.

Authors:  Zhou Wang; Alan Conrad Bovik; Hamid Rahim Sheikh; Eero P Simoncelli
Journal:  IEEE Trans Image Process       Date:  2004-04       Impact factor: 10.856

3.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images.

Authors:  B A Olshausen; D J Field
Journal:  Nature       Date:  1996-06-13       Impact factor: 49.962

4.  Simultaneous acquisition of spatial harmonics (SMASH): fast imaging with radiofrequency coil arrays.

Authors:  D K Sodickson; W J Manning
Journal:  Magn Reson Med       Date:  1997-10       Impact factor: 4.668

5.  Deep convolutional neural networks for multi-modality isointense infant brain image segmentation.

Authors:  Wenlu Zhang; Rongjian Li; Houtao Deng; Li Wang; Weili Lin; Shuiwang Ji; Dinggang Shen
Journal:  Neuroimage       Date:  2015-01-03       Impact factor: 6.556

6.  Automatic Segmentation of MR Brain Images With a Convolutional Neural Network.

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

7.  q-Space Deep Learning: Twelve-Fold Shorter and Model-Free Diffusion MRI Scans.

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

8.  Deep learning with domain adaptation for accelerated projection-reconstruction MR.

Authors:  Yoseob Han; Jaejun Yoo; Hak Hee Kim; Hee Jung Shin; Kyunghyun Sung; Jong Chul Ye
Journal:  Magn Reson Med       Date:  2018-02-04       Impact factor: 4.668

9.  Parallel imaging with nonlinear reconstruction using variational penalties.

Authors:  Florian Knoll; Christian Clason; Kristian Bredies; Martin Uecker; Rudolf Stollberger
Journal:  Magn Reson Med       Date:  2011-06-27       Impact factor: 4.668

10.  ESPIRiT--an eigenvalue approach to autocalibrating parallel MRI: where SENSE meets GRAPPA.

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

View more
  174 in total

1.  QSMGAN: Improved Quantitative Susceptibility Mapping using 3D Generative Adversarial Networks with increased receptive field.

Authors:  Yicheng Chen; Angela Jakary; Sivakami Avadiappan; Christopher P Hess; Janine M Lupo
Journal:  Neuroimage       Date:  2019-11-21       Impact factor: 6.556

2.  Optimization of MRI Turnaround Times Through the Use of Dockable Tables and Innovative Architectural Design Strategies.

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

3.  PET Image Reconstruction Using Deep Image Prior.

Authors:  Kuang Gong; Ciprian Catana; Jinyi Qi; Quanzheng Li
Journal:  IEEE Trans Med Imaging       Date:  2018-12-19       Impact factor: 10.048

4.  Highly accelerated multishot echo planar imaging through synergistic machine learning and joint reconstruction.

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

5.  Nonlinear dipole inversion (NDI) enables robust quantitative susceptibility mapping (QSM).

Authors:  Daniel Polak; Itthi Chatnuntawech; Jaeyeon Yoon; Siddharth Srinivasan Iyer; Carlos Milovic; Jongho Lee; Peter Bachert; Elfar Adalsteinsson; Kawin Setsompop; Berkin Bilgic
Journal:  NMR Biomed       Date:  2020-02-20       Impact factor: 4.044

Review 6.  Current applications and future directions of deep learning in musculoskeletal radiology.

Authors:  Pauley Chea; Jacob C Mandell
Journal:  Skeletal Radiol       Date:  2019-08-04       Impact factor: 2.199

7.  Self-supervised learning of physics-guided reconstruction neural networks without fully sampled reference data.

Authors:  Burhaneddin Yaman; Seyed Amir Hossein Hosseini; Steen Moeller; Jutta Ellermann; Kâmil Uğurbil; Mehmet Akçakaya
Journal:  Magn Reson Med       Date:  2020-07-02       Impact factor: 4.668

8.  Accelerated single-shot T2-weighted fat-suppressed (FS) MRI of the liver with deep learning-based image reconstruction: qualitative and quantitative comparison of image quality with conventional T2-weighted FS sequence.

Authors:  Krishna Shanbhogue; Angela Tong; Paul Smereka; Dominik Nickel; Simon Arberet; Rebecca Anthopolos; Hersh Chandarana
Journal:  Eur Radiol       Date:  2021-05-07       Impact factor: 5.315

9.  Multi-scale Unrolled Deep Learning Framework for Accelerated Magnetic Resonance Imaging.

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

10.  Image Reconstruction: From Sparsity to Data-adaptive Methods and Machine Learning.

Authors:  Saiprasad Ravishankar; Jong Chul Ye; Jeffrey A Fessler
Journal:  Proc IEEE Inst Electr Electron Eng       Date:  2019-09-19       Impact factor: 10.961

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.