Literature DB >> 33724507

Analysis of deep complex-valued convolutional neural networks for MRI reconstruction and phase-focused applications.

Elizabeth Cole1, Joseph Cheng1, John Pauly1, Shreyas Vasanawala2.   

Abstract

PURPOSE: Deep learning has had success with MRI reconstruction, but previously published works use real-valued networks. The few works which have tried complex-valued networks have not fully assessed their impact on phase. Therefore, the purpose of this work is to fully investigate end-to-end complex-valued convolutional neural networks (CNNs) for accelerated MRI reconstruction and in several phase-based applications in comparison to 2-channel real-valued networks.
METHODS: Several complex-valued activation functions for MRI reconstruction were implemented, and their performance was compared. Complex-valued convolution was implemented and tested on an unrolled network architecture and a U-Net-based architecture over a wide range of network widths and depths with knee, body, and phase-contrast datasets.
RESULTS: Quantitative and qualitative results demonstrated that complex-valued CNNs with complex-valued convolutions provided superior reconstructions compared to real-valued convolutions with the same number of trainable parameters for both an unrolled network architecture and a U-Net-based architecture, and for 3 different datasets. Complex-valued CNNs consistently had superior normalized RMS error, structural similarity index, and peak SNR compared to real-valued CNNs.
CONCLUSION: Complex-valued CNNs can enable superior accelerated MRI reconstruction and phase-based applications such as fat-water separation, and flow quantification compared to real-valued convolutional neural networks.
© 2021 International Society for Magnetic Resonance in Medicine.

Entities:  

Keywords:  MRI; complex-valued models; convolutional neural networks; image reconstruction; learning representations

Mesh:

Year:  2021        PMID: 33724507      PMCID: PMC8291740          DOI: 10.1002/mrm.28733

Source DB:  PubMed          Journal:  Magn Reson Med        ISSN: 0740-3194            Impact factor:   3.737


  29 in total

1.  SENSE: sensitivity encoding for fast MRI.

Authors:  K P Pruessmann; M Weiger; M B Scheidegger; P Boesiger
Journal:  Magn Reson Med       Date:  1999-11       Impact factor: 4.668

2.  Sparse MRI: The application of compressed sensing for rapid MR imaging.

Authors:  Michael Lustig; David Donoho; John M Pauly
Journal:  Magn Reson Med       Date:  2007-12       Impact factor: 4.668

Review 3.  Deep learning.

Authors:  Yann LeCun; Yoshua Bengio; Geoffrey Hinton
Journal:  Nature       Date:  2015-05-28       Impact factor: 49.962

4.  Kafnets: Kernel-based non-parametric activation functions for neural networks.

Authors:  Simone Scardapane; Steven Van Vaerenbergh; Simone Totaro; Aurelio Uncini
Journal:  Neural Netw       Date:  2018-11-13

5.  Image reconstruction by domain-transform manifold learning.

Authors:  Bo Zhu; Jeremiah Z Liu; Stephen F Cauley; Bruce R Rosen; Matthew S Rosen
Journal:  Nature       Date:  2018-03-21       Impact factor: 49.962

6.  Deep complex convolutional network for fast reconstruction of 3D late gadolinium enhancement cardiac MRI.

Authors:  Hossam El-Rewaidy; Ulf Neisius; Jennifer Mancio; Selcuk Kucukseymen; Jennifer Rodriguez; Amanda Paskavitz; Bjoern Menze; Reza Nezafat
Journal:  NMR Biomed       Date:  2020-04-30       Impact factor: 4.044

7.  Learning a variational network for reconstruction of accelerated MRI data.

Authors:  Kerstin Hammernik; Teresa Klatzer; Erich Kobler; Michael P Recht; Daniel K Sodickson; Thomas Pock; Florian Knoll
Journal:  Magn Reson Med       Date:  2017-11-08       Impact factor: 4.668

8.  Variable-Density Single-Shot Fast Spin-Echo MRI with Deep Learning Reconstruction by Using Variational Networks.

Authors:  Feiyu Chen; Valentina Taviani; Itzik Malkiel; Joseph Y Cheng; Jonathan I Tamir; Jamil Shaikh; Stephanie T Chang; Christopher J Hardy; John M Pauly; Shreyas S Vasanawala
Journal:  Radiology       Date:  2018-07-24       Impact factor: 11.105

9.  Deep Generative Adversarial Neural Networks for Compressive Sensing MRI.

Authors:  Morteza Mardani; Enhao Gong; Joseph Y Cheng; Shreyas S Vasanawala; Greg Zaharchuk; Lei Xing; John M Pauly
Journal:  IEEE Trans Med Imaging       Date:  2018-07-23       Impact factor: 10.048

10.  RUN-UP: Accelerated multishot diffusion-weighted MRI reconstruction using an unrolled network with U-Net as priors.

Authors:  Yuxin Hu; Yunyingying Xu; Qiyuan Tian; Feiyu Chen; Xinwei Shi; Catherine J Moran; Bruce L Daniel; Brian A Hargreaves
Journal:  Magn Reson Med       Date:  2020-08-11       Impact factor: 4.668

View more
  2 in total

1.  SNR Enhancement for Multi-TE MRSI Using Joint Low-Dimensional Model and Spatial Constraints.

Authors:  Yahang Li; Zepeng Wang; Fan Lam
Journal:  IEEE Trans Biomed Eng       Date:  2022-09-19       Impact factor: 4.756

2.  Real-time deep artifact suppression using recurrent U-Nets for low-latency cardiac MRI.

Authors:  Olivier Jaubert; Javier Montalt-Tordera; Dan Knight; Gerry J Coghlan; Simon Arridge; Jennifer A Steeden; Vivek Muthurangu
Journal:  Magn Reson Med       Date:  2021-05-25       Impact factor: 4.668

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.