Tags

Type your tag names separated by a space and hit enter

A divide-and-conquer approach to compressed sensing MRI.
Magn Reson Imaging 2019; 63:37-48MR

Abstract

Compressed sensing (CS) theory assures us that we can accurately reconstruct magnetic resonance images using fewer k-space measurements than the Nyquist sampling rate requires. In traditional CS-MRI inversion methods, the fact that the energy within the Fourier measurement domain is distributed non-uniformly is often neglected during reconstruction. As a result, more densely sampled low frequency information tends to dominate penalization schemes for reconstructing MRI at the expense of high frequency details. In this paper, we propose a new framework for CS-MRI inversion in which we decompose the observed k-space data into "subspaces" via sets of filters in a lossless way, and reconstruct the images in these various spaces individually using off-the-shelf algorithms. We then fuse the results to obtain the final reconstruction. In this way, we are able to focus reconstruction on frequency information within the entire k-space more equally, preserving both high and low frequency details. We demonstrate that the proposed framework is competitive with state-of-the-art methods in CS-MRI in terms of quantitative performance, and often improves an algorithm's results qualitatively compared with its direct application to k-space.

Authors+Show Affiliations

Fujian Key Laboratory of Sensing and Computing for Smart City, Xiamen University, China.Fujian Key Laboratory of Sensing and Computing for Smart City, Xiamen University, China.Fujian Key Laboratory of Sensing and Computing for Smart City, Xiamen University, China. Electronic address: dxh@xmu.edu.cn.Department of Electronic Science, Xiamen University, Xiamen, China.Fujian Key Laboratory of Sensing and Computing for Smart City, Xiamen University, China.Department of Electrical Engineering, Columbia University, New York, NY, USA.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

31306732

Citation

Sun, Liyan, et al. "A Divide-and-conquer Approach to Compressed Sensing MRI." Magnetic Resonance Imaging, vol. 63, 2019, pp. 37-48.
Sun L, Fan Z, Ding X, et al. A divide-and-conquer approach to compressed sensing MRI. Magn Reson Imaging. 2019;63:37-48.
Sun, L., Fan, Z., Ding, X., Cai, C., Huang, Y., & Paisley, J. (2019). A divide-and-conquer approach to compressed sensing MRI. Magnetic Resonance Imaging, 63, pp. 37-48. doi:10.1016/j.mri.2019.06.014.
Sun L, et al. A Divide-and-conquer Approach to Compressed Sensing MRI. Magn Reson Imaging. 2019 Jul 12;63:37-48. PubMed PMID: 31306732.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - A divide-and-conquer approach to compressed sensing MRI. AU - Sun,Liyan, AU - Fan,Zhiwen, AU - Ding,Xinghao, AU - Cai,Congbo, AU - Huang,Yue, AU - Paisley,John, Y1 - 2019/07/12/ PY - 2018/12/21/received PY - 2019/06/19/revised PY - 2019/06/22/accepted PY - 2019/7/16/pubmed PY - 2019/7/16/medline PY - 2019/7/16/entrez KW - Compressed sensing KW - Divide-and-conquer KW - Magnetic resonance imaging SP - 37 EP - 48 JF - Magnetic resonance imaging JO - Magn Reson Imaging VL - 63 N2 - Compressed sensing (CS) theory assures us that we can accurately reconstruct magnetic resonance images using fewer k-space measurements than the Nyquist sampling rate requires. In traditional CS-MRI inversion methods, the fact that the energy within the Fourier measurement domain is distributed non-uniformly is often neglected during reconstruction. As a result, more densely sampled low frequency information tends to dominate penalization schemes for reconstructing MRI at the expense of high frequency details. In this paper, we propose a new framework for CS-MRI inversion in which we decompose the observed k-space data into "subspaces" via sets of filters in a lossless way, and reconstruct the images in these various spaces individually using off-the-shelf algorithms. We then fuse the results to obtain the final reconstruction. In this way, we are able to focus reconstruction on frequency information within the entire k-space more equally, preserving both high and low frequency details. We demonstrate that the proposed framework is competitive with state-of-the-art methods in CS-MRI in terms of quantitative performance, and often improves an algorithm's results qualitatively compared with its direct application to k-space. SN - 1873-5894 UR - https://www.unboundmedicine.com/medline/citation/31306732/A_Divide-and-Conquer_Approach_to_Compressed_Sensing_MRI L2 - https://linkinghub.elsevier.com/retrieve/pii/S0730-725X(18)30674-X DB - PRIME DP - Unbound Medicine ER -