Deep-learning-based image reconstruction with limited data: generating synthetic raw data using deep learning.

Journal: Magma (New York, N.Y.)
Published Date:

Abstract

OBJECT: Deep learning has shown great promise for fast reconstruction of accelerated MRI acquisitions by learning from large amounts of raw data. However, raw data is not always available in sufficient quantities. This study investigates synthetic data generation to complement small datasets and improve reconstruction quality.

Authors

  • Frank Zijlstra
    Centre for Image Sciences, University Medical Center Utrecht, Utrecht, The Netherlands.
  • Peter Thomas While
    Department of Radiology and Nuclear Medicine, St Olav's University Hospital, Postboks 3250 Torgarden, 7006, Trondheim, Norway.