Phase reconstruction from velocity-encoded MRI measurements - A survey of sparsity-promoting variational approaches

被引:43
作者
Benning, Martin [2 ]
Gladden, Lynn [2 ]
Holland, Daniel [2 ]
Schoenlieb, Carola-Bibiane [1 ,2 ]
Valkonen, Tuomo [1 ,2 ]
机构
[1] Univ Cambridge, Dept Appl Math & Theoret Phys, Cambridge CB3 0WA, England
[2] Magnet Resonance Res Ctr, Dept Chem Engn & Biotechnol, Cambridge CB3 0HE, England
基金
英国工程与自然科学研究理事会;
关键词
Phase-encoded magnetic resonance; Velocity imaging; Compressed sensing; Bregman iteration; Higher-order regularisation; Total variation; NUCLEAR-MAGNETIC-RESONANCE; LATTICE-BOLTZMANN; FLOW; NMR; REGULARIZATION; ALGORITHMS;
D O I
10.1016/j.jmr.2013.10.003
中图分类号
Q5 [生物化学];
学科分类号
071010 ; 081704 ;
摘要
In recent years there has been significant developments in the reconstruction of magnetic resonance velocity images from sub-sampled k-space data. While showing a strong improvement in reconstruction quality compared to classical approaches, the vast number of different methods, and the challenges in setting them up, often leaves the user with the difficult task of choosing the correct approach, or more importantly, not selecting a poor approach. In this paper, we survey variational approaches for the reconstruction of phase-encoded magnetic resonance velocity images from sub-sampled k-space data. We are particularly interested in regularisers that correctly treat both smooth and geometric features of the image. These features are common to velocity imaging, where the flow field will be smooth but interfaces between the fluid and surrounding material will be sharp, but are challenging to represent sparsely. As an example we demonstrate the variational approaches on velocity imaging of water flowing through a packed bed of solid particles. We evaluate Wavelet regularisation against Total Variation and the relatively recent second order Total Generalised Variation regularisation. We combine these regularisation schemes with a contrast enhancement approach called Bregman iteration. We verify for a variety of sampling patterns that Morozov's discrepancy principle provides a good criterion for stopping the iterations. Therefore, given only the noise level, we present a robust guideline for setting up a variational reconstruction scheme for MR velocity imaging. (C) 2013 Elsevier Inc. All rights reserved.
引用
收藏
页码:26 / 43
页数:18
相关论文
共 59 条
  • [1] [Anonymous], 1992, CBMS-NSF Reg. Conf. Ser. in Appl. Math
  • [2] [Anonymous], J MATH IMAGING VISIO
  • [3] [Anonymous], 1996, Die Grundlehren der mathematischen Wissenschaften
  • [4] [Anonymous], 1983, AUGMENTED LAGRANGIAN, DOI DOI 10.1016/S0168-2024(08)70034-1
  • [5] [Anonymous], 1966, Soviet Mathematics Doklady
  • [6] A variational approach to removing multiplicative noise
    Aubert, Gilles
    Aujol, Jean-Francois
    [J]. SIAM JOURNAL ON APPLIED MATHEMATICS, 2008, 68 (04) : 925 - 946
  • [7] BENNING M, GROUND STAT IN PRESS
  • [8] Higher-Order TV Methods-Enhancement via Bregman Iteration
    Benning, Martin
    Brune, Christoph
    Burger, Martin
    Mueller, Jahn
    [J]. JOURNAL OF SCIENTIFIC COMPUTING, 2013, 54 (2-3) : 269 - 310
  • [9] Compressed sensing reconstruction of undersampled 3D NOESY spectra: application to large membrane proteins
    Bostock, Mark J.
    Holland, Daniel J.
    Nietlispach, Daniel
    [J]. JOURNAL OF BIOMOLECULAR NMR, 2012, 54 (01) : 15 - 32
  • [10] Distributed optimization and statistical learning via the alternating direction method of multipliers
    Boyd S.
    Parikh N.
    Chu E.
    Peleato B.
    Eckstein J.
    [J]. Foundations and Trends in Machine Learning, 2010, 3 (01): : 1 - 122