Accelerated Computing in Magnetic Resonance Imaging: Real-Time Imaging Using Nonlinear Inverse Reconstruction.

Sebastian SchaetzDirk VoitJens Frahm Martin Uecker

Published in: Computational and mathematical methods in medicine (2017)

Novel parallel decomposition methods are presented which are applicable to many iterative algorithms for dynamic MRI. Using these methods to parallelize the NLINV algorithm on multiple GPUs, it is possible to achieve online image reconstruction with high frame rates.

Keyphrases

magnetic resonance imaging
deep learning
machine learning
contrast enhanced
diffusion weighted imaging
social media
image quality
magnetic resonance
fluorescence imaging
dual energy