TY - JOUR
T1 - Deep-Learning Methods for Parallel Magnetic Resonance Imaging Reconstruction
T2 - A Survey of the Current Approaches, Trends, and Issues
AU - Knoll, Florian
AU - Hammernik, Kerstin
AU - Zhang, Chi
AU - Moeller, Steen
AU - Pock, Thomas
AU - Sodickson, Daniel K.
AU - Akcakaya, Mehmet
N1 - Publisher Copyright:
© 1991-2012 IEEE.
PY - 2020/1
Y1 - 2020/1
N2 - Following the success of deep learning in a wide range of applications, neural network-based machine-learning techniques have received interest as a means of accelerating magnetic resonance imaging (MRI). A number of ideas inspired by deeplearning techniques for computer vision and image processing have been successfully applied to nonlinear image reconstruction in the spirit of compressed sensing for both low-dose computed tomography and accelerated MRI. The additional integration of multicoil information to recover missing k-space lines in the MRI reconstruction process is studied less frequently, even though it is the de facto standard for the currently used accelerated MR acquisitions. This article provides an overview of the recent machine-learning approaches that have been proposed specifically for improving parallel imaging. A general background introduction to parallel MRI is given and structured around the classical view of image- and k-space-based methods. Linear and nonlinear methods are covered, followed by a discussion of the recent efforts to further improve parallel imaging using machine learning and, specifically, artificial neural networks. Image domain-based techniques that introduce improved regularizers are covered as well as k-space-based methods, where the focus is on better interpolation strategies using neural networks. Issues and open problems are discussed and recent efforts for producing open data sets and benchmarks for the community are examined.
AB - Following the success of deep learning in a wide range of applications, neural network-based machine-learning techniques have received interest as a means of accelerating magnetic resonance imaging (MRI). A number of ideas inspired by deeplearning techniques for computer vision and image processing have been successfully applied to nonlinear image reconstruction in the spirit of compressed sensing for both low-dose computed tomography and accelerated MRI. The additional integration of multicoil information to recover missing k-space lines in the MRI reconstruction process is studied less frequently, even though it is the de facto standard for the currently used accelerated MR acquisitions. This article provides an overview of the recent machine-learning approaches that have been proposed specifically for improving parallel imaging. A general background introduction to parallel MRI is given and structured around the classical view of image- and k-space-based methods. Linear and nonlinear methods are covered, followed by a discussion of the recent efforts to further improve parallel imaging using machine learning and, specifically, artificial neural networks. Image domain-based techniques that introduce improved regularizers are covered as well as k-space-based methods, where the focus is on better interpolation strategies using neural networks. Issues and open problems are discussed and recent efforts for producing open data sets and benchmarks for the community are examined.
UR - http://www.scopus.com/inward/record.url?scp=85078525893&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85078525893&partnerID=8YFLogxK
U2 - 10.1109/MSP.2019.2950640
DO - 10.1109/MSP.2019.2950640
M3 - Article
C2 - 33758487
AN - SCOPUS:85078525893
SN - 1053-5888
VL - 37
SP - 128
EP - 140
JO - IEEE Signal Processing Magazine
JF - IEEE Signal Processing Magazine
IS - 1
M1 - 8962951
ER -