基于外积有效和字典学习的改进灵敏度编码重建算法

J Shanghai Jiaotong Univ Sci››2025,Vol. 30››Issue (3): 555-565.doi:10.1007/s12204-023-2677-9

基于外积有效和字典学习的改进灵敏度编码重建算法

昆明理工大学信息工程与自动化学院，昆明 650500

收稿日期:2022-09-22接受日期:2022-09-22出版日期:2025-06-06发布日期:2025-06-06

Improved Sensitivity Encoding Parallel Magnetic Resonance Imaging Reconstruction Algorithm Based on Efficient Sum of Outer Products Dictionary Learning

段继忠，苏艳

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

Received:2022-09-22Accepted:2022-09-22Online:2025-06-06Published:2025-06-06

摘要/Abstract

摘要：灵敏度编码(Sensitivity Encoding, SENSE)是一种利用接收器线圈灵敏度的固有空间编码信息来实现图像重建的并行磁共振成像(Magnetic Resonance Imaging, MRI)技术。现存基于SENSE模型的MRI重建算法的自适应能力不足,导致重建图像精度欠缺。基于上述情况，将包含L0范数的外积有效和字典学习(Efficient Sum of Outer Products Dictionary Learning, SOUPDIL)引入SENSE模型中，提出一种基于SOUPDIL的改进灵敏度编码重建算法，即SOUPDIL-SENSE。提出的算法主要基于交替方向乘子法求解，通过字典学习和图像更新两步实现并行MRI重建。仿真实验结果表明：该算法能够促进图像稀疏性，有效消除图像重建噪声和伪影，显著提升图像重建精度。

关键词:并行磁共振成像,灵敏度编码,外积有效和字典学习,交替方向乘子法

Abstract:Sensitivity encoding (SENSE) is a parallel magnetic resonance imaging (MRI) reconstruction model by utilizing the sensitivity information of receiver coils to achieve image reconstruction. The existing SENSE-based reconstruction algorithms usually used nonadaptive sparsifying transforms, resulting in a limited reconstruction accuracy. Therefore, we proposed a new model for accurate parallel MRI reconstruction by combining the L0 norm regularization term based on the efficient sum of outer products dictionary learning (SOUPDIL) with the SENSE model, called SOUPDIL-SENSE. The SOUPDIL-SENSE model is mainly solved by utilizing the variable splitting and alternating direction method of multipliers techniques. The experimental results on four human datasets show that the proposed algorithm effectively promotes the image sparsity, eliminates the noise and artifacts of the reconstructed images, and improves the reconstruction accuracy.

中图分类号:

TP391
R445.2

. 基于外积有效和字典学习的改进灵敏度编码重建算法[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(3): 555-565.

Duan Jizhong, Su Yan. Improved Sensitivity Encoding Parallel Magnetic Resonance Imaging Reconstruction Algorithm Based on Efficient Sum of Outer Products Dictionary Learning[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(3): 555-565.

参考文献

[1] FANG L L, WANG X, LIAN Z Y, et al. Supervoxelbased brain tumor segmentation with multimodal MRI images [J]. Signal, Image and Video Processing, 2022, 16(5): 1215-1223.

[2] 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.

[3] SHENG J H, YIN J, WANG L Y, et al. Parallel MR image reconstruction based on triple cycle optimization [J]. Scientific Reports, 2022, 12: 7783.

[4] CAO C H, DUANW, HU K, et al. Compressive sensing MR imaging based on adaptive tight frame and reference image [J]. IET Image Processing, 2020, 14(14): 3508-3515.

[5] HU Z Q, ZHAO C L, ZHAO X, et al. Joint reconstruction framework of compressed sensing and nonlinear parallel imaging for dynamic cardiac magnetic resonance imaging [J]. BMC Medical Imaging, 2021, 21(1): 182.

[6] SHENG J H, SHI Y C, ZHANG Q. Improved parallel magnetic resonance imaging reconstruction with multiple variable density sampling [J]. Scientific Reports, 2021, 11: 9005.

[7] PAN T, DUAN J Z, WANG J F, et al. Iterative selfconsistent parallel magnetic resonance imaging reconstruction based on nonlocal low-rank regularization [J]. Magnetic Resonance Imaging, 2022, 88: 62-75.

[8] 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.

[9] 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.

[10] UECKER M, LAI P,MURPHYM 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.

[11] LIU B, ZOU Y M, YING L. Sparsesense: Application of compressed sensing in parallel MRI [C]//2008 International Conference on Information Technology and Applications in Biomedicine. Shenzhen: IEEE, 2008: 127-130.

[12] RAMANI S, FESSLER J A. Parallel MR image reconstruction using augmented Lagrangian methods [J]. IEEE Transactions on Medical Imaging, 2011, 30(3): 694-706.

[13] 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.

[14] YASHTINI M. Euler’s elastica-based algorithm for Parallel MRI reconstruction using SENSitivity Encoding [J]. Optimization Letters, 2020, 14(6): 1435-1458.

[15] DUAN J Z, BAO Z W, LIU Y. Eigenvector-based SPIRiT parallel MR imaging reconstruction based on p pseudo-norm joint total variation [J]. Magnetic Resonance Imaging, 2019, 58: 108-115.

[16] ZHANG P, MANG A, HE J W, et al. Diffeomorphic shape matching by operator splitting in 3D cardiology imaging [J]. Journal of Optimization Theory and Applications, 2021, 188(1): 143-168.

[17] 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.

[18] RAVISHANKAR S, NADAKUDITI R R, FESSLER J A. Efficient sum of outer products dictionary learning (SOUP-DIL) and its application to inverse problems [J]. IEEE Transactions on Computational Imaging, 2017, 3(4): 694-709.

[19] ZHANG Y L, LI X W, ZHAO G Y, et al. Signal reconstruction of compressed sensing based on alternating direction method of multipliers [J]. Circuits, Systems, and Signal Processing, 2020, 39(1): 307-323.

[20] RUBINSTEIN R, ZIBULEVSKY M, ELAD M. Efficient implementation of the K-SVD algorithm using batch orthogonal matching pursuit [EB/OL]. [2022-09- 22]. https://csaws.cs.technion.ac.il/∼ronrubin/Publications/ KSVD-OMP-v2.pdf

[21] SOUZA R, LUCENA O, GARRAFA J, et al. An open, multi-vendor, multi-field-strength brain MR dataset and analysis of publicly available skull stripping methods agreement [J]. NeuroImage, 2018, 170: 482-494.

[22] YE X J, CHEN YM, HUANG F. Computational acceleration for MR image reconstruction in partially parallel imaging [J]. IEEE Transactions on Medical Imaging, 2011, 30(5): 1055-1063.

[23] KNOLL F, ZBONTAR J, SRIRAM A, et al. fastMRI: A publicly available raw k-space and DICOM dataset of knee images for accelerated MR image reconstruction using machine learning [J]. Radiology Artificial Intelligence, 2020, 2(1): e190007.