Phase2Phase: Respiratory Motion-Resolved Reconstruction of Free-Breathing Magnetic Resonance Imaging Using Deep Learning Without a Ground Truth for Improved Liver Imaging.

Journal: Investigative radiology
Published Date: Dec 1, 2021

Abstract

OBJECTIVES: Respiratory binning of free-breathing magnetic resonance imaging data reduces motion blurring; however, it exacerbates noise and introduces severe artifacts due to undersampling. Deep neural networks can remove artifacts and noise but usually require high-quality ground truth images for training. This study aimed to develop a network that can be trained without this requirement.

Authors

  • Cihat Eldeniz
    Department of Radiology, Washington University School of Medicine, Saint Louis, Missouri.
  • Weijie Gan
    Department of Computer Science & Engineering.
  • Sihao Chen
    Department of Biomedical Engineering.
  • Tyler J Fraum
    From the Mallinckrodt Institute of Radiology.
  • Daniel R Ludwig
    Washington University School of Medicine, 660 S Euclid Ave, Campus, Box 8131, St Louis, MO, 63110, USA.
  • Yan Yan
    Department of Biomedical Engineering, Wayne State University, Detroit, Michigan, USA.
  • Jiaming Liu
    Department of Electrical and Systems Engineering, University in St. Louis, St. Louis, MO, USA.
  • Thomas Vahle
    Siemens Healthcare GmbH, Erlangen, Germany.
  • Uday Krishnamurthy
    Siemens Healthineers, St. Louis, Missouri.
  • Ulugbek S Kamilov
    Department of Computer Science and Engineering, Washington University in St. Louis, St. Louis, MO, USA.
  • Hongyu An
    Department of Radiology, Washington University School of Medicine, Saint Louis, Missouri.

Keywords

External Resources

Popular Topics
Recent Journals