J Shanghai Jiaotong Univ Sci

Journal of Shanghai Jiaotong University(Science) >

2025 , Vol. 30 >Issue 3: 499 - 509

DOI: https://doi.org/10.1007/s12204-023-2647-2

Medicine-Engineering Interdisciplinary

Fast Parallel Magnetic Resonance Imaging Reconstruction Based on Sparsifying Transform Learning and Structured Low-Rank Model

Expand
  • Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China

Received date: 2022-08-10

  Accepted date: 2022-12-24

  Online published: 2025-06-06

Fold

Abstract

The structured low-rank model for parallel magnetic resonance (MR) imaging can efficiently reconstruct MR images with limited auto-calibration signals. To improve the reconstruction quality of MR images, we integrate the joint sparsity and sparsifying transform learning (JTL) into the simultaneous auto-calibrating and k-space estimation (SAKE) structured low-rank model, named JTLSAKE. The alternate direction method of multipliers is exploited to solve the resulting optimization problem, and the optimized gradient method is used to improve the convergence speed. In addition, a graphics processing unit is used to accelerate the proposed algorithm. The experimental results on four in vivo human datasets demonstrate that the reconstruction quality of the proposed algorithm is comparable to that of JTL-based low-rank modeling of local k-space neighborhoods with parallel imaging (JTL-PLORAKS), and the proposed algorithm is 46 times faster than the JTL-PLORAKS, requiring only 4 s to reconstruct a 200 × 200 pixels MR image with 8 channels.

Cite this article

Duan Jizhong, Xu Yuhán, Huang Huan . Fast Parallel Magnetic Resonance Imaging Reconstruction Based on Sparsifying Transform Learning and Structured Low-Rank Model[J]. Journal of Shanghai Jiaotong University(Science), 2025 , 30(3) : 499 -509 . DOI: 10.1007/s12204-023-2647-2

References

[1] DONOHO D L. Compressed sensing [J]. IEEE Transactions  on Information Theory, 2006, 52(4): 1289- 1306. 

[2] PRUESSMANN K P, WEIGER M, SCHEIDEGGER M B, et al. SENSE: Sensitivity encoding for fast MRI [J]. Magnetic Resonance in Medicine, 1999, 42(5): 952-962. 

[3] CANDES E J, ROMBERG J, TAO T. Robust uncertainty  principles: Exact signal reconstruction from  highly incomplete frequency information [J]. IEEE Transactions on Information Theory, 2006, 52(2): 489-509. 

[4] LUSTIG M, DONOHO D, PAULY J M. Sparse MRI: The application of compressed sensing for rapid MR  imaging [J]. Magnetic Resonance in Medicine, 2007, 58(6): 1182-1195. 

[5] YANG J F, ZHANG Y, YIN W T. A fast alternating  direction method for TVL1-L2 signal reconstruction  from partial Fourier data [J]. IEEE Journal of Selected Topics in Signal Processing, 2010, 4(2): 288-297. 

[6] RAVISHANKAR S, BRESLER Y. MR image reconstruction  from highly undersampled k-space data by  dictionary learning [J]. IEEE Transactions on Medical Imaging, 2011, 30(5): 1028-1041. 

[7] RAVISHANKAR S, BRESLER Y. Efficient blind compressed  sensing using sparsifying transforms with convergence  guarantees and application to MRI [J]. SIAM Journal on Imaging Sciences, 2015, 8(4): 2519-2557. 

[8] WEN B H, LI Y J, BRESLER Y. Image recovery via  transform learning and low-rank modeling: The power  of complementary regularizers [J]. IEEE Transactions  on Image Processing, 2020, 29: 5310-5323. 

[9] WEN B H, RAVISHANKAR S, PFISTER L, et al. Transform learning for magnetic resonance image reconstruction: From model-based learning to building  neural networks [J]. IEEE Signal Processing Magazine, 2020, 37(1): 41-53.

[10] GRISWOLD M A, JAKOB P M, HEIDEMANN R M, et al. Generalized autocalibrating partially parallel  acquisitions (GRAPPA) [J]. Magnetic Resonance in Medicine, 2002, 47(6): 1202-1210. 

[11] LUSTIG M, PAULY J M. SPIRiT: Iterative selfconsistent  parallel imaging reconstruction from arbitrary  k-space [J]. Magnetic Resonance in Medicine, 2010, 64(2): 457-471. 

[12] SHIN P J, LARSON P E Z, OHLIGER M A, et al. Calibrationless parallel imaging reconstruction based  on structured low-rank matrix completion [J]. Magnetic Resonance in Medicine, 2014, 72(4): 959-970. 

[13] HALDAR J P, ZHUO J W. P-LORAKS: Low-rank  modeling of local k-space neighborhoods with parallel  imaging data [J]. Magnetic Resonance in Medicine, 2016, 75(4): 1499-1514. 

[14] KIM T H, HALDAR J P. LORAKS software version 2.0: Faster implementation and enhanced capabilities [R]. Los Angeles: University of Southern California, 2018. 

[15] HALDAR J P. Autocalibrated loraks for fast constrained MRI reconstruction [C]//2015 IEEE 12th International Symposium on Biomedical Imaging. Brooklyn: IEEE, 2015: 910-913. 

[16] LIU Y L, YI Z Y, ZHAO Y J, et al. Calibrationless  parallel imaging reconstruction for multislice MR data  using low-rank tensor completion [J]. Magnetic Resonance  in Medicine, 2021, 85(2): 897-911. 

[17] DUAN J Z, LIU C, LIU Y, et al. Adaptive transform  learning and joint sparsity based PLORAKS parallel  magnetic resonance image reconstruction [J]. IEEE Access, 2020, 8: 212315-212326. 

[18] CHANG C H, YU X D, JI J X. Compressed sensing MRI reconstruction from 3D multichannel data using GPUs [J]. Magnetic Resonance in Medicine, 2017, 78(6): 2265-2274. 

[19] ULLAH I, NISAR H, RAZA H, et al. QRdecomposition  based SENSE reconstruction using  parallel architecture [J]. Computers in Biology and Medicine, 2018, 95: 1-12. 

[20] MURPHY M, ALLEY M, DEMMEL J, et al. Fast 1-SPIRiT compressed sensing parallel imaging MRI: Scalable parallel implementation and clinically feasible  runtime [J]. IEEE Transactions on Medical Imaging, 2012, 31(6): 1250-1262. 

[21] KIM D, FESSLER J A. On the convergence analysis  of the optimized gradient method [J]. Journal of Optimization Theory and Applications, 2017, 172(1): 187-205. 

[22] GOLDSTEIN T, O’DONOGHUE B, SETZER S, et  al. Fast alternating direction optimization methods [J]. SIAM Journal on Imaging Sciences, 2014, 7(3): 1588- 1623. 

[23] FESSLER J A. Optimization methods for magnetic  resonance image reconstruction: Key models and optimization  algorithms [J]. IEEE Signal Processing Magazine, 2020, 37(1): 33-40.

Options
Outlines

/

〈 〉