Corpus ID: 222379577

XPDNet for MRI Reconstruction: an Application to the fastMRI 2020 Brain Challenge

@article{Ramzi2020XPDNetFM,
  title={XPDNet for MRI Reconstruction: an Application to the fastMRI 2020 Brain Challenge},
  author={Zaccharie Ramzi and P. Ciuciu and Jean-Luc Starck},
  journal={ArXiv},
  year={2020},
  volume={abs/2010.07290}
}
  • Zaccharie Ramzi, P. Ciuciu, Jean-Luc Starck
  • Published 2020
  • Engineering, Computer Science, Physics, Mathematics
  • ArXiv
  • We present a modular cross-domain neural network the XPDNet and its application to the MRI reconstruction task. This approach consists in unrolling the PDHG algorithm as well as learning the acceleration scheme between steps. We also adopt state-of-the-art techniques specific to Deep Learning for MRI reconstruction. At the time of writing, this approach is the best performer in PSNR on the fastMRI leaderboards for both knee and brain at acceleration factor 4. 

    Figures from this paper.

    References

    SHOWING 1-10 OF 13 REFERENCES
    End-to-End Variational Networks for Accelerated MRI Reconstruction
    • 9
    • PDF
    An Adaptive Intelligence Algorithm for Undersampled Knee MRI Reconstruction
    • 5
    • PDF
    Learned Primal-Dual Reconstruction
    • 202
    • PDF
    ESPIRiT—an eigenvalue approach to autocalibrating parallel MRI: Where SENSE meets GRAPPA
    • 553
    • PDF
    U-Net: Convolutional Networks for Biomedical Image Segmentation
    • 16,882
    • PDF
    Multi-level Wavelet-CNN for Image Restoration
    • 126
    • Highly Influential
    • PDF
    A First-Order Primal-Dual Algorithm for Convex Problems with Applications to Imaging
    • A. Chambolle, T. Pock
    • Mathematics, Computer Science
    • Journal of Mathematical Imaging and Vision
    • 2010
    • 3,098
    • PDF
    Deep Learning on Image Denoising: An overview
    • 24
    • PDF
    Sparse MRI: The application of compressed sensing for rapid MR imaging
    • 4,932
    • PDF
    On the Variance of the Adaptive Learning Rate and Beyond
    • 324
    • PDF