Optimized fast GPU implementation of robust artificial-neural-networks for k-space interpolation (RAKI) reconstruction.

Journal: PloS one
Published Date: Oct 23, 2019

Abstract

BACKGROUND: Robust Artificial-neural-networks for k-space Interpolation (RAKI) is a recently proposed deep-learning-based reconstruction algorithm for parallel imaging. Its main premise is to perform k-space interpolation using convolutional neural networks (CNNs) trained on subject-specific autocalibration signal (ACS) data. Since training is performed individually for each subject, the reconstruction time is longer than approaches that pre-train on databases. In this study, we sought to reduce the computational time of RAKI.

Authors

  • Chi Zhang
    Department of Thoracic Surgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
  • Seyed Amir Hossein Hosseini
    Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, United States of America.
  • Sebastian Weingärtner
    Computer Assisted Clinical Medicine, Medical Faculty Mannheim, Heidelberg University, Germany.
  • Kâmil Uğurbil
    Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, Minnesota.
  • Steen Moeller
    Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, Minnesota.
  • Mehmet Akçakaya
    Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, Minnesota.

Keywords

External Resources

Popular Topics
Recent Journals