research-article

Joint optimization of Cartesian sampling patterns and reconstruction for single‐contrast and multi‐contrast fast magnetic resonance imaging

Authors:

Shuhui CaiAuthors Info & Claims

Volume 226, Issue C

https://doi.org/10.1016/j.cmpb.2022.107150

Published: 01 November 2022 Publication History

Highlights

•

Sampling patterns and reconstruction are jointly optimized for fast MRI.

•

Identical morphologic information in multi-contrast images helps to accelerate MRI.

•

End-to-end learning enable achievement of multiple adaptive sampling patterns.

•

Adaptive sampling patterns improve reconstruction quality of under-sampled images.

Abstract

Background and objective

Compressed sensing (CS) has gained increased attention in magnetic resonance imaging (MRI), leveraging its efficacy to accelerate image acquisition. Incoherence measurement and non-linear reconstruction are the most crucial guarantees of accurate restoration. However, the loose link between measurement and reconstruction hinders the further improvement of reconstruction quality, i.e., the default sampling pattern is not adaptively tailored to the downstream reconstruction method. When single-contrast reconstruction (SCR) has been upgraded to its multi-contrast reconstruction (MCR) variant, the identical morphologic information as a priori source could be integrated into the reconstruction procedure. How to measure less and reconstruct effectively by using the shareable morphologic information of various contrast images is an attractive topic.

Methods

An adaptive sampling (AS) based end-to-end framework (ASSCR or ASMCR) is proposed to address this issue, which simultaneously optimizes sampling patterns and reconstruction from under-sampled data in SCR or MCR scenarios. Several deep probabilistic subsampling (DPS) modules are used in AS network to construct a sampling pattern generator. In SCR and MCR, a convolution block and a data consistency layer are iteratively applied in the reconstruction network. Specifically, the learned optimal sampling pattern output from the trained AS sub-net is used for under-sampling. Incoherence measurement for single-contrast images and the combination of sampling patterns for multi-contrast data are guided by the SCR/MCR sub-net.

Results

Experiments were conducted on two single-contrast and one multi-contrast public MRI datasets. Compared with several state-of-the-art reconstruction methods, SCR results show that a learned sampling pattern brings the quality of the reconstructed image closer to the fully-sampled reference. With the addition of different contrast images, under-sampled images with higher acceleration factors could be well recovered.

Conclusion

The proposed method could improve the reconstruction quality of under-sampled images by using adaptive sampling patterns and learning-based reconstruction.

References

[1]

D.L. Donoho, Compressed sensing, IEEE Trans. Inf. Theory 52 (2006) 1289–1306,.

Digital Library

[2]

M. Lustig, D.L. Donoho, J.M. Pauly, Sparse MRI: The application of compressed sensing for rapid MR imaging, Magn. Reson. Med. 58 (2007) 1182–1195,.

[3]

M. Lustig, D.L. Donoho, J.M. Santos, et al., Compressed sensing MRI, IEEE Signal Process. Mag. 25 (2008) 72–82,.

[4]

J. Schlemper, J. Caballero, J. Hajnal, et al., A deep cascade of convolutional neural networks for dynamic MR image reconstruction, IEEE Trans. Med. Imag. 37 (2017) 491–503,.

[5]

J. Zhang, B. Ghanem, ISTA-Net: Interpretable optimization-inspired deep network for image compressive sensing, in: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 1828–1837,.

[6]

H.K. Aggarwal, M.P. Mani, M. Jacob, MoDL: Model-based deep learning architecture for inverse problems, IEEE Trans. Med. Imag. 38 (2019) 394–405,.

[7]

K. Hammernik, T. Klatzer, E. Kobler, et al., Learning a variational network for reconstruction of accelerated MRI data, Magn. Reson. Med. 79 (2017) 3055–3071,.

[8]

K. Zeng, Y. Yang, G. Xiao, et al., A very deep densely connected network for compressed sensing MRI, IEEE Access 7 (2019) 85430–85439,.

[9]

L. Bao, F. Ye, C. Cai, et al., Undersampled MR image reconstruction using an enhanced recursive residual network, J. Magn. Reson. 305 (2019) 232–246,.

[10]

E.M. Eksioglu, Decoupled algorithm for MRI reconstruction using nonlocal block matching model: BM3D-MRI, J. Math. Imag. Vis. 56 (2016) 430–440,.

Digital Library

[11]

X. Qu, Y. Hou, F. Lam, et al., Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator, Med. Image Anal. 18 (2014) 843–856,.

[12]

Y. Liu, Z. Zhan, J. Cai, et al., Projected iterative soft-thresholding algorithm for tight frames in compressed sensing magnetic resonance imaging, IEEE Trans. Med. Imag. 35 (2016) 2130–2140,.

[13]

B. Zhou, S.K. Zhou, DuDoRNet: learning a dual-domain recurrent network for fast MRI reconstruction with deep T₁ prior, in: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2020, pp. 4272–4281,.

[14]

A.T. Curtis, C.K. Anand, Random volumetric MRI trajectories via genetic algorithms, Int. J. Biomed. Imag. 2008 (2014),.

Digital Library

[15]

S. Matthias, N. Hannes, P. Rolf, et al., Optimization of k-space trajectories for compressed sensing by Bayesian experimental design, Magn. Reson. Med. 63 (2010) 116–126,.

[16]

C. Boyer, N. Chauffert, P. Ciuciu, et al., On the generation of sampling schemes for magnetic resonance imaging, SIAM J. Imag. Sci. 9 (2016) 2039–2072,.

Digital Library

[17]

C. Lazarus, P. Weiss, N. Chauffert, et al., SPARKLING: Variable-density k-space filling curves for accelerated T₂*-weighted MRI, Magn. Reson. Med. 81 (2019) 3643–3661,.

[18]

F. Knoll, C. Clason, C. Diwoky, et al., Adapted random sampling patterns for accelerated MRI, Magn. Reson. Mater. Phys. Biol. Med. 24 (2011) 43–50,.

[19]

G.R. Chaithya, Z. Ramzi, P. Ciuciu, Learning the sampling density in 2D SPARKLING MRI acquisition for optimized image reconstruction, arXiv preprint (2021) arXiv:2103.03559 https://arxiv.org/abs/2103.03559.

[20]

G. Wang, T. Luo, J.F. Nielsen, et al., B-spline parameterized joint optimization of reconstruction and k-space trajectories (BJORK) for accelerated 2D MRI, arXiv preprint (2021) arXiv:2101.11369 https://arxiv.org/abs/2101.11369.

[21]

S. Ravishankar, Y. Bresler, Adaptive sampling design for compressed sensing MRI, Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. (2011) 3751–3755,.

[22]

H.K. Aggarwal, M. Jacob, J-MoDL: Joint model-based deep learning for optimized sampling and reconstruction, IEEE J. Sel. Top. Signal Process. 14 (2020) 1151–1162,.

[23]

T. Weiss, S. Vedula, O. Senouf, et al., Joint learning of cartesian under sampling andre construction for accelerated MRI, in: Proc. IEEE Int. Conf. Acoust. Speech Signal Process. (ICASSP), 2020, pp. 8653–8657,.

[24]

C.D. Bahadir, A.Q. Wang, A.V. Dalca, et al., Deep-learning-based optimization of the under-sampling pattern in MRI, IEEE Trans. Comput. Imag. 6 (2020) 1139–1152,.

[25]

F. Sherry, M. Benning, J.C. De los Reyes, et al., Learning the sampling pattern for MRI, IEEE Trans. Med. Imag. 39 (2020) 4310–4321,.

[26]

I.A.M. Huijben, B.S. Veeling, R.J.G.V. Sloun, Learning sampling and model-based signal recovery for compressed sensing MRI, in: Proc. IEEE Int. Conf. Acoust. Speech Signal Process. (ICASSP), 2020, pp. 8906–8910,.

[27]

Z. Zhang, A. Romero, M.J. Muckley, et al., Reducing uncertainty in undersampled MRI reconstruction with active acquisition, in: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2019, pp. 2049–2058,.

[28]

P. Luis, B. Sumana, R. Adriana, et al., Active MR k-space sampling with reinforcement learning, Med. Image Comput. Comput. Assist. Interv. (MICCAI) (2020) 23–33. https://arxiv.org/abs/2007.10469.

[29]

L. Sun, Z. Fan, X. Fu, et al., A deep information sharing network for multi-contrast compressed sensing MRI reconstruction, IEEE Trans. Image Process. 28 (2019) 6141–6153,.

Digital Library

[30]

B. Bilgic, V.K. Goyal, E. Adalsteinsson, Multi-contrast reconstruction with Bayesian compressed sensing, Magn. Reson. Med. 66 (2011) 1601–1615,.

[31]

J. Huang, C. Chen, L. Axel, Fast multi-contrast MRI reconstruction, Magn. Reson. Imaging 32 (2014) 1344–1352,.

[32]

M.J. Ehrhardt, M.M. Betcke, Multicontrast MRI reconstruction with structure-guided total variation, SIAM J. Imag. Sci. 9 (2016) 1084–1106,.

Digital Library

[33]

C. Peng, W.-A. Lin, R. Chellappa, et al., Towards multi-sequence MR image recovery from undersampled k-space data, arXiv preprint (2019) arXiv:1908.05615 https://arxiv.org/abs/1908.05615.

[34]

X. Liu, J. Wang, F. Tang, et al., Deep simultaneous optimization of sampling and reconstruction for multi-contrast MRI, arXiv preprint (2021),.

[35]

J. Yang, X. Li, F. Liu, et al., Fast T₂w/FLAIR MRI acquisition by optimal sampling of information complementary to pre-acquired T₁w MRI, arXiv preprint (2021) arXiv:2111.06400 https://arxiv.org/abs/2111.06400.

[36]

E. Jang, S. Gu, B. Poole, Categorical reparameterization with gumbel-softmax, in: Int. Conf. learn. Repres. (ICLR), 2017, pp. 1–12. https://www.openreview.net/forum?id=rkE3y85ee.

[37]

C.J. Maddison, A. Mnih, Y.W. Teh, The concrete distribution: A continuous relaxation of discrete random variables, in: Int. Conf. learn. Repres. (ICLR), 2017, pp. 1–17. https://www.openreview.net/forum?id=S1jE5L5gl.

[38]

K. He, X. Zhang, S. Ren, et al., Deep residual learning for image recognition, in: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 770–778,.

[39]

G. Huang, Z. Liu, L.V.D. Maaten, et al., Densely connected convolutional networks, in: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 2261–2269,.

[40]

J. Zbontar, F. Knoll, A. Sriram, et al., fastMRI: An open dataset and benchmarks for accelerated MRI, arXiv preprint (2018) arXiv:1811.08839 https://arxiv.org/abs/1811.08839.

[41]

T. Zhang, J.M. Pauly, S.S. Vasanawala, et al., Coil compression for accelerated imaging with Cartesian sampling, Magn. Reson. Med. 69 (2013) 571–582,.

[42]

M. Uecker, P. Lai, M.J. Murphy, et al., ESPIRiT—an eigenvalue approach to autocalibrating parallel MRI: Where SENSE meets GRAPPA, Magn. Reson. Med. 71 (2014) 990–1001,.

[43]

G. McGibney, M. Smith, S. Nichols, et al., Quantitative evaluation of several partial Fourier reconstruction algorithms used in MRI, Magn. Reson. Med. 30 (1993) 51–59,.

[44]

T. Küstner, C. Würslin, S. Gatidis, et al., MR image reconstruction using a combination of compressed sensing and partial Fourier acquisition: ESPReSSo, IEEE Trans. Med. Imag. 35 (2016) 2447–2458,.

[45]

R. Otazo, D. Kim, L. Axel, et al., Combination of compressed sensing and parallel imaging for highly accelerated first-pass cardiac perfusion MRI, Magn. Reson. Med. 64 (2010) 767–776,.

[46]

F. Liu, Y. Duan, B. Peterson, et al., Compressed sensing MRI combined with SENSE in partial k-space, Phys. Med. Biol. 57 (2012) N391,.

[47]

G. Li, J. Hennig, E. Raithel, et al., An L₁-norm phase constraint for half-Fourier compressed sensing in 3D MR imaging, Magn. Reson. Mater. Phys. Biol. Med. 28 (2015) 459–472,.

[48]

C. Binter, V. Knobloch, R. Manka, et al., Bayesian multipoint velocity encoding for concurrent flow and turbulence mapping, Magn. Reson. Med. 69 (2013) 1337–1345,.

[49]

J. Walheim, A. Gotschy, S. Kozerke, On the limitations of partial Fourier acquisition in phase-contrast MRI of turbulent kinetic energy, Magn. Reson. Med. 81 (2019) 514–523,.

[50]

Y. Zhang, M. Brady, S. Smith, Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm, IEEE Trans. Med. Imag. 20 (2001) 45–57,.

[51]

J. Ashburner, K.J. Friston, Unified segmentation, Neuroimage 26 (2005) 839–851,.

[52]

G. Balakrishnan, A. Zhao, M.R. Sabuncu, et al., VoxelMorph: A learning framework for deformable medical image registration, IEEE Trans. Med. Imag. 38 (2019) 1788–1800,.

[53]

X. Liu, J. Wang, J. Jin, et al., Deep unregistered multi-contrast MRI reconstruction, Magn. Reson. Imag. 81 (2021) 33–41,.

[54]

K. Xuan, L. Xiang, X. Huang, et al., Multi-modal MRI reconstruction assisted with spatial alignment network, IEEE Trans. Med. Imag. 41 (2022) 2499–2509,.

Cited By

Liu YPang YSun XHou YYang ZWang Z(2024)Dual states based reinforcement learning for fast MR scan and image reconstructionNeurocomputing10.1016/j.neucom.2023.127067568:COnline publication date: 1-Feb-2024
https://dl.acm.org/doi/10.1016/j.neucom.2023.127067
Yang ZJiang MRuan DLi YTan THuang SLiu F(2024)LUCMTComputer Methods and Programs in Biomedicine10.1016/j.cmpb.2024.108359255:COnline publication date: 18-Nov-2024
https://dl.acm.org/doi/10.1016/j.cmpb.2024.108359
Du YDharmakumar RTsaftaris S(2024)The MRI Scanner as a Diagnostic: Image-Less Active SamplingMedical Image Computing and Computer Assisted Intervention – MICCAI 202410.1007/978-3-031-72384-1_44(467-476)Online publication date: 7-Oct-2024
https://dl.acm.org/doi/10.1007/978-3-031-72384-1_44
Show More Cited By

Index Terms

Joint optimization of Cartesian sampling patterns and reconstruction for single‐contrast and multi‐contrast fast magnetic resonance imaging

Index terms have been assigned to the content through auto-classification.

Recommendations

Multi-contrast deep nuclei segmentation using a probabilistic atlas
ISBI'10: Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro

In this paper we propose a new hybrid segmentation approach of the deep brain structures based on a multicontrast deformable model of regions in competition, with deformations preserving the topology of the structures, as well as their shape and ...
Fill the K-Space and Refine the Image: Prompting for Dynamic and Multi-Contrast MRI Reconstruction
Statistical Atlases and Computational Models of the Heart. Regular and CMRxRecon Challenge Papers
Abstract
The key to dynamic or multi-contrast magnetic resonance imaging (MRI) reconstruction lies in exploring inter-frame or inter-contrast information. Currently, the unrolled model, an approach combining iterative MRI reconstruction steps with ...
Improved prostate cancer localization with spatially regularized dynamic contrast -enhanced magnetic resonance imaging
ISBI'10: Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro

Imaging methods to localize prostate cancer with sufficient accuracy are extremely useful in guiding biopsy, radiotherapy and surgery as well as to monitor disease progression. Imaging prostate cancer with multispectral magnetic resonance imaging (MRI) ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Computer Methods and Programs in Biomedicine

Computer Methods and Programs in Biomedicine Volume 226, Issue C

Nov 2022

1043 pages

ISSN:0169-2607

Issue’s Table of Contents

Elsevier B.V.

Publisher

Elsevier North-Holland, Inc.

United States

Publication History

Published: 01 November 2022

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 24 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Liu YPang YSun XHou YYang ZWang Z(2024)Dual states based reinforcement learning for fast MR scan and image reconstructionNeurocomputing10.1016/j.neucom.2023.127067568:COnline publication date: 1-Feb-2024
https://dl.acm.org/doi/10.1016/j.neucom.2023.127067
Yang ZJiang MRuan DLi YTan THuang SLiu F(2024)LUCMTComputer Methods and Programs in Biomedicine10.1016/j.cmpb.2024.108359255:COnline publication date: 18-Nov-2024
https://dl.acm.org/doi/10.1016/j.cmpb.2024.108359
Du YDharmakumar RTsaftaris S(2024)The MRI Scanner as a Diagnostic: Image-Less Active SamplingMedical Image Computing and Computer Assisted Intervention – MICCAI 202410.1007/978-3-031-72384-1_44(467-476)Online publication date: 7-Oct-2024
https://dl.acm.org/doi/10.1007/978-3-031-72384-1_44
Geng CJiang MFang XLi YJin GChen ALiu F(2023)HFIST-NetComputer Methods and Programs in Biomedicine10.1016/j.cmpb.2023.107440232:COnline publication date: 1-Apr-2023
https://dl.acm.org/doi/10.1016/j.cmpb.2023.107440
Ramanarayanan SPalla ARam KSivaprakasam M(2023)Generalizing supervised deep learning MRI reconstruction to multiple and unseen contrasts using meta-learning hypernetworks▪Applied Soft Computing10.1016/j.asoc.2023.110633146:COnline publication date: 1-Oct-2023
https://dl.acm.org/doi/10.1016/j.asoc.2023.110633

View Options

View options

Figures

Tables

Media

View Issue’s Table of Contents