Rapid estimation of 2D relative -maps from localizers in the human heart at 7T using deep learning.

Journal: Magnetic resonance in medicine
Published Date: Nov 6, 2022

Abstract

PURPOSE: Subject-tailored parallel transmission pulses for ultra-high fields body applications are typically calculated based on subject-specific -maps of all transmit channels, which require lengthy adjustment times. This study investigates the feasibility of using deep learning to estimate complex, channel-wise, relative 2D -maps from a single gradient echo localizer to overcome long calibration times.

Authors

  • Felix Krueger
    Physikalisch-Technische Bundesanstalt, Braunschweig and Berlin, Germany.
  • Christoph Stefan Aigner
    Physikalisch-Technische Bundesanstalt, Braunschweig and Berlin, Germany.
  • Kerstin Hammernik
    Institute of Computer Graphics and Vision, Graz University of Technology, Graz, Austria.
  • Sebastian Dietrich
    Physikalisch-Technische Bundesanstalt, Braunschweig and Berlin, Germany.
  • Max Lutz
    Physikalisch-Technische Bundesanstalt, Braunschweig and Berlin, Germany.
  • Jeanette Schulz-Menger
    Charité-Universitätsmedizin Berlin, Experimental and Clinical Research Center, Working Group On CMR and HELIOS Klinikum Berlin Buch, Cardiology Berlin, DZHK partnersite Berlin, Berlin, Germany.
  • Tobias Schaeffter
  • Sebastian Schmitter
    Physikalisch-Technische Bundesanstalt, Braunschweig and Berlin, Germany.

Keywords

External Resources

Popular Topics
Recent Journals