Improving accelerated MRI by deep learning with sparsified complex data.

Journal: Magnetic resonance in medicine
Published Date:

Abstract

PURPOSE: To obtain high-quality accelerated MR images with complex-valued reconstruction from undersampled k-space data.

Authors

  • Zhaoyang Jin
    Machine Learning and I-health International Cooperation Base of Zhejiang Province, School of Automation, Hangzhou Dianzi University, Hangzhou, People's Republic of China.
  • Qing-San Xiang
    Physics & Astronomy, University of British Columbia, Canada; Radiology, University of British Columbia, Canada.