Model-driven parallel compressive sensing magnetic resonance imaging algorithm based on trainable dual frames and its convergence analysis
SHI Baoshun1,2, LIU Zheng1,2, LIU Kexun1,2
1. School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, China; 2. Hebei Key Laboratory of Information Transmission and Signal Processing, Yanshan University, Qinhuangdao 066004, China
Abstract：[Objective] Parallel compressive sensing magnetic resonance imaging (p-CSMRI) algorithms aim to improve and refine the reconstructed image using partial k-space data sampled from multiple coils. Recently, learning-based model-driven p-CSMRI algorithms have attracted extensive attention because of their superior reconstruction quality. Nevertheless, their prior network architectures are typically designed empirically, lacking model interpretability and hampering the analysis of algorithm convergence. To address this problem, we introduce a provably bounded denoiser based on deep learning and incorporate it as a prior module into a model-driven p-CSMRI network. Moreover, we propose a deep unrolled p-CSMRI algorithm; its convergence can be explicitly analyzed. [Methods] First, to improve the sparse representation capability and learning speed of traditional tight frames, we extend the single tight frame to a dual-frame network. Because the image pixels vary in the spatial domain, a deep threshold network is developed to adaptively extract thresholds from the input images, thereby improving the generalization ability of the dual frames. Based on the dual frames integrated with the elaborated deep threshold network, we introduce a novel provably bounded deep denoiser. Second, we describe a p-CSMRI optimization model based on dual frames. The constructed optimization model is iteratively solved via the half-quadratic splitting solver, and the corresponding iterations are unfolded into a deep neural network that can be trained by end-to-end supervised learning. Finally, under reducing noise level conditions, the convergence of model-driven p-CSMRI algorithms is explicitly proved based on the bounded denoiser theory. The convergence theory of plug-and-play (PnP) imaging methods demonstrates that methods with decreasing noise levels can realize a fixed-point convergence under the assumption of a bounded denoiser. We explicitly prove that the proposed deep denoiser as the prior network is bounded. Based on this bounded property, we develop a model-driven p-CSMRI algorithmic framework with guaranteed convergence. [Results] Theoretically, we explicitly prove that the built deep denoiser as the prior network satisfies the bounded property and perform a convergence analysis of the proposed algorithm under the mild condition of gradually decreasing noise. Simulation experiments carried out on the knee MRI dataset from New York University disclose that, compared with the Modl, VN, and VS-Net algorithms, the proposed method realizes improvements of 1.70, 1.45, and 0.46 dB, respectively, in peak signal-to-noise ratio for reconstructed images under a fourfold acceleration factor. However, a comparative assessment of the proposed model with Modl, VN, and VS-Net algorithms concerning parameter memory and average inference time reveals that the model-driven p-CSMRI method based on the dual frames recommended in this study has a high number of parameters. Furthermore, the image inference time of the proposed method is lower than those of Modl and VN and slightly higher than that of VS-Net. Therefore, our proposed method shows a moderate level of computational complexity. [Conclusions] The model-driven p-CSMRI network algorithm proposed here, based on trainable dual frames, has a theoretical convergence guarantee and demonstrates stable performance in experiments. Moreover, our algorithm proved effective in reconstructing high-quality MR images. This work offers valuable insights into future research and development in the area of magnetic resonance imaging.
石保顺, 刘政, 刘柯讯. 基于可训练对偶标架的模型驱动并行压缩感知磁共振成像算法及其收敛性分析[J]. 清华大学学报（自然科学版）, 2024, 64(4): 712-723.
SHI Baoshun, LIU Zheng, LIU Kexun. Model-driven parallel compressive sensing magnetic resonance imaging algorithm based on trainable dual frames and its convergence analysis. Journal of Tsinghua University(Science and Technology), 2024, 64(4): 712-723.
[1] LIANG D, LIU B, WANG J, et al. Accelerating SENSE using compressed sensing[J]. Magnetic Resonance in Medicine, 2009, 62(6): 1574-1584. [2] CHEN C, LI Y Q, HUANG J Z. Calibrationless parallel MRI with joint total variation regularization[C]//Proceedings of the 16th International Conference on Medical Image Computing and Computer-Assisted Intervention. Nagoya, Japan: Springer, 2013: 106-114. [3] CHAÂRI L, PESQUET J C, BENAZZA-BENYAHIA A, et al. A wavelet-based regularized reconstruction algorithm for SENSE parallel MRI with applications to neuroimaging[J]. Medical Image Analysis, 2011, 15(2): 185-201. [4] BLOCK K T, UECKER M, FRAHM J. Undersampled radial MRI with multiple coils. Iterative image reconstruction using a total variation constraint[J]. Magnetic Resonance in Medicine, 2007, 57(6): 1086-1098. [5] WELLER D. Reconstruction with dictionary learning for accelerated parallel magnetic resonance imaging[C]//Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation. Santa Fe, NM, USA: IEEE, 2016: 105-108. [6] LUSTIG M, ALLEY M, VASANAWALA S, et al. Fast L1-SPIRiT Compressed Sensing Parallel Imaging MRI: Scalable Parallel Implementation and Clinically Feasible Runtime[J]. IEEE Transactions on Medical Imaging. 2012, 31(6): 1250-1262. [7] 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. [8] KIM T H, SETSOMPOP K, HALDAR J P. LORAKS makes better SENSE: Phase-constrained partial fourier SENSE reconstruction without phase calibration[J]. Magnetic Resonance in Medicine, 2017, 77(3): 1021-1035. [9] ZHANG X L, GUO D, HUANG Y M, et al. Image reconstruction with low-rankness and self-consistency of k-space data in parallel MRI[J]. Medical Image Analysis, 2020, 63: 101687. [10] 王尧. 基于深度学习的脑部多模态核磁共振影像研究[D]. 长春: 吉林大学, 2022. WANG Y. Multi-modality brain magnetic resonance images recognition with deep learning[D]. Changchun: Jilin University, 2022. (in Chinese) [11] 施伟成, 金朝阳, 叶铮. 基于PCAU-Net的快速多通道磁共振成像方法[J]. 波谱学杂志, 2023, 40(1): 39-51. SHI W C, JIN Z Y, YE Z. Fast multi-channel magnetic resonance imaging based on PCAU-Net[J]. Chinese Journal of Magnetic Resonance, 2023, 40(1): 39-51. (in Chinese) [12] WANG S S, SU Z H, YING L, et al. Accelerating magnetic resonance imaging via deep learning[C]//Proceedings of the IEEE 13th International Symposium on Biomedical Imaging. Prague, Czech Republic: IEEE, 2016: 514-517. [13] AGGARWAL H K, MANI M P, JACOB M. MoDL: Model-based deep learning architecture for inverse problems[J]. IEEE Transactions on Medical Imaging, 2019, 38(2): 394-405. [14] DUAN J M, SCHLEMPER J, QIN C, et al. VS-Net: Variable splitting network for accelerated parallel MRI reconstruction[C]//Proceedings of the 22nd International Conference on Medical Image Computing and Computer Assisted Intervention. Shenzhen, China: Springer, 2019: 713-722. [15] HAMMERNIK K, KLATZER T, KOBLER E, et al. Learning a variational network for reconstruction of accelerated MRI data[J]. Magnetic Resonance in Medicine, 2018, 79(6): 3055-3071. [16] MENG N, YANG Y, XU Z B, et al. A prior learning network for joint image and sensitivity estimation in parallel MR imaging[C]//Proceedings of the 22nd International Conference on Medical Image Computing and Computer Assisted Intervention. Shenzhen, China: Springer, 2019: 732-740. [17] WANG S S, WU R Y, LI C, et al. PARCEL: Physics-based unsupervised contrastive representation learning for multi-coil MR imaging[J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2023, 20(5): 2659-2670. [18] YANG Y, WANG N, YANG H R, et al. Model-driven deep attention network for ultra-fast compressive sensing MRI guided by cross-contrast MR image[C]//Proceedings of the 23rd International Conference on Medical Image Computing and Computer Assisted Intervention. Lima, Peru: Springer, 2020: 188-198. [19] CHAN S H, WANG X R, ELGENDY O A. Plug-and-play ADMM for image restoration: Fixed-point convergence and applications[J]. IEEE Transactions on Computational Imaging, 2017, 3(1): 84-98. [20] TERRIS M, REPETTI A, PESQUET J C, et al. Enhanced convergent PnP algorithms for image restoration[C]//Proceedings of the International Conference on Image Processing. Anchorage, AK, USA: IEEE, 2021: 1684-1688. [21] YUAN X, LIU Y, SUO J L, et al. Plug-and-play algorithms for large-scale snapshot compressive imaging[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Seattle, WA, USA: IEEE, 2020: 1444-1454. [22] CAI J F, JI H, SHEN Z W, et al. Data-driven tight frame construction and image denoising[J]. Applied and Computational Harmonic Analysis, 2014, 37(1): 89-105. [23] CAI J F, CHOI J K, WEI K. Data driven tight frame for compressed sensing MRI reconstruction via off-the-grid regularization[J]. SIAM Journal on Imaging Sciences, 2020, 13(3): 1272-1301. [24] SHI B S, WANG Y X, LI D. Provable general bounded denoisers for snapshot compressive imaging with convergence guarantee[J]. IEEE Transactions on Computational Imaging, 2023, 9: 55-69. [25] ISOGAWA K, IDA T, SHIODERA T, et al. Deep shrinkage convolutional neural network for adaptive noise reduction[J]. IEEE Signal Processing Letters, 2018, 25(2): 224-228. [26] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: IEEE, 2018: 7132-7141. [27] UECKER M, LAI P, MURPHY M J, et al. ESPIRiT—an eigenvalue approach to autocalibrating parallel MRI: Where SENSE meets GRAPPA[J]. Magnetic Resonance in Medicine, 2014, 71(3): 990-1001.
2024, Vol. 64 
