Combined Deep Learning-based Super-Resolution and Partial Fourier Reconstruction for Gradient Echo Sequences in Abdominal MRI at 3 Tesla: Shortening Breath-Hold Time and Improving Image Sharpness and Lesion Conspicuity.

Journal: Academic radiology
PMID:

Abstract

RATIONALE AND OBJECTIVES: To investigate the impact of a prototypical deep learning-based super-resolution reconstruction algorithm tailored to partial Fourier acquisitions on acquisition time and image quality for abdominal T1-weighted volume-interpolated breath-hold examination (VIBE) at 3 Tesla. The standard T1-weighted images were used as the reference standard (VIBE).

Authors

  • Haidara Almansour
    From the Department of Diagnostic and Interventional Radiology, Eberhard Karls University, Tuebingen University Hospital, Tuebingen.
  • Judith Herrmann
    Department of Diagnostic and Interventional Radiology, Eberhard-Karls-University Tuebingen, Tuebingen, Germany.
  • Sebastian Gassenmaier
    Division of Cardiovascular Imaging, Department of Radiology and Radiological Science, Medical University of South Carolina, Charleston, SC, USA.
  • Andreas Lingg
    From the Department of Diagnostic and Interventional Radiology, Eberhard Karls University Tuebingen, Tuebingen.
  • Marcel Dominik Nickel
    MR Application Predevelopment, Siemens Healthineers AG, Erlangen, Germany.
  • Stephan Kannengiesser
    MR Application Predevelopment, Siemens Healthineers AG, Erlangen, Germany.
  • Simon Arberet
    Digital Technology & Innovation, Siemens Medical Solutions USA, Inc., Princeton, NJ, USA.
  • Ahmed E Othman
    Department of Diagnostic and Interventional Radiology, Eberhard-Karls-University Tuebingen, Tuebingen, Germany; Department of Neuroradiology, University Medical Centre, Johannes Gutenberg University Mainz, 55131 Mainz, Germany. Electronic address: ahmed.e.othman@googlemail.com.
  • Saif Afat
    Department of Diagnostic and Interventional Radiology, Eberhard-Karls-University Tuebingen, Tuebingen, Germany.