Correction of out-of-FOV motion artifacts using convolutional neural network.

Journal: Magnetic resonance imaging
Published Date: May 25, 2020

Abstract

PURPOSE: Subject motion during MRI scan can result in severe degradation of image quality. Existing motion correction algorithms rely on the assumption that no information is missing during motions. However, this assumption does not hold when out-of-FOV motion happens. Currently available algorithms are not able to correct for image artifacts introduced by out-of-FOV motion. The purpose of this study is to demonstrate the feasibility of incorporating convolutional neural network (CNN) derived prior image into solving the out-of-FOV motion problem.

Authors

  • ChengYan Wang
  • Yucheng Liang
    Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, Illinois, USA.
  • Yuan Wu
    State Key Laboratory of Precision Spectroscopy, Quantum Institute for Light and Atoms, Department of Physics and Electronic Science, East China Normal University, Shanghai 200062, China.
  • Siwei Zhao
    Institute for Medical Imaging Technology (IMIT), School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China.
  • Yiping P Du
    Institute for Medical Imaging Technology (IMIT), School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China. Electronic address: yipingdu@sjtu.edu.cn.

Keywords

External Resources

Popular Topics
Recent Journals