基于蝶形空洞几何蒸馏的磁共振成像重建

doi:10.1007/s12204-024-2701-8

摘要/Abstract

摘要： 为了提高磁共振成像的重建精度，提出了一种精确的自然图像压缩感知 (Compressed Sensing， CS)重建网络，结合了基于模型和基于深度学习的CS-MRI 方法的优点。理论上，在线性重建中增强几何纹理细节是可行的。首先，将优化问题分解为线性近似和几何补偿两个问题。针对图像线性近似问题，采用数据一致性模块对其进行处理。由于处理过程会丢失纹理细节，因此提出一种显式结合图像和频率特征表示的神经网络层，命名为蝶形空洞几何蒸馏网络。该网络引入了蝶形运算的思想，巧妙地融合了图像域和频域的特征，避免了单一域提取特征时纹理细节的丢失。最后，结合通道注意力机制和空洞卷积设计了通道特征融合模块。通道注意力使得最终输出的特征图集中在更重要的部分，从而提高了特征表示能力。空洞卷积扩大了感受野，从而获得更稠密的图像特征数据。实验结果表明，在笛卡尔采样掩码CS比例为10%的大脑数据集上，该网络的峰值信噪比比 ISTA-Net+、FISTA 和DGDN 网络分别提高了 5.43 dB、5.23 dB 和 3.89 dB。

关键词: 蝶形几何蒸馏, 空洞卷积, 通道注意力, 图像重建

Abstract: In order to improve the reconstruction accuracy of magnetic resonance imaging (MRI), an accurate natural image compressed sensing (CS) reconstruction network is proposed, which combines the advantages of model-based and deep learning-based CS-MRI methods. In theory, enhancing geometric texture details in linear reconstruction is possible. First, the optimization problem is decomposed into two problems: linear approximation and geometric compensation. Aimed at the problem of image linear approximation, the data consistency module is used to deal with it. Since the processing process will lose texture details, a neural network layer that explicitly combines image and frequency feature representation is proposed, which is named butterfly dilated geometric distillation network. The network introduces the idea of butterfly operation, skillfully integrates the features of image domain and frequency domain, and avoids the loss of texture details when extracting features in a single domain. Finally, a channel feature fusion module is designed by combining channel attention mechanism and dilated convolution. The attention of the channel makes the final output feature map focus on the more important part, thus improving the feature representation ability. The dilated convolution enlarges the receptive field, thereby obtaining more dense image feature data. The experimental results show that the peak signal-tonoise ratio of the network is 5.43 dB, 5.24 dB and 3.89 dB higher than that of ISTA-Net+, FISTA and DGDN networks on the brain data set with a Cartesian sampling mask CS ratio of 10%.

中图分类号:

TP391
R445

. 基于蝶形空洞几何蒸馏的磁共振成像重建[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(3): 591-599.

Duolin, Xu Boyu, Ren Yong, Yang Xin. Magnetic Resonance Imaging Reconstruction Based on Butterfly Dilated Geometric Distillation[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(3): 591-599.

参考文献

[1] ZHAN Z F, CAI J F, GUO D, et al. Fast multiclass dictionaries learning with geometrical directions in MRI reconstruction [J]. IEEE Transactions on Biomedical Engineering, 2016, 63(9): 1850-1861.

[2] LAI Z Y, QU X B, LIU Y S, et al. Image reconstruction of compressed sensing MRI using graph-based redundant wavelet transform [J]. Medical Image Analysis, 2016, 27: 93-104.

[3] LINGALA S G, JACOB M. Blind compressive sensing dynamic MRI [J]. IEEE Transactions on Medical Imaging, 2013, 32(6): 1132-1145.

[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] BECK A, TEBOULLE M. A fast iterative shrinkage-thresholding algorithm for linear inverse problems [J]. SIAM Journal on Imaging Sciences, 2009, 2(1): 183-202.

[6] CHAMBOLLE A, POCK T. A first-order primal-dual algorithm for convex problems with applications to imaging [J]. Journal of Mathematical Imaging and Vision, 2011, 40(1): 120-145.

[7] BOYD S, PARIKH N, CHU E, et al. Distributed optimization and statistical learning via the alternating direction method of multipliers [J]. Foundations and Trends® in Machine Learning, 2011, 3(1): 1-122.

[8] DATTA S, DANDAPAT S, DEKA B. A deep framework for enhancement of diagnostic information in CSMRI reconstruction [J]. Biomedical Signal Processing and Control, 2022, 71: 103117.

[9] WANG S S, SU Z H, YING L, et al. Accelerating magnetic resonance imaging via deep learning [C]//2016 IEEE 13th International Symposium on Biomedical Imaging. Prague: IEEE, 2016: 514-517.

[10] JIN K H, MCCANN M T, FROUSTEY E, et al. Deep convolutional neural network for inverse problems in imaging [J]. IEEE Transactions on Image Processing, 2017, 26(9): 4509-4522.

[11] QUAN T M, NGUYEN-DUC T, JEONG W K. Compressed sensing MRI reconstruction using a generative adversarial network with a cyclic loss [J]. IEEE Transactions on Medical Imaging, 2018, 37(6): 1488-1497.

[12] YANG G, YU S M, DONG H, et al. DAGAN: Deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction [J]. IEEE Transactions on Medical Imaging, 2018, 37(6): 1310-1321.

[13] WEI H N, LI Z S, WANG S, et al. Undersampled multi-contrast MRI reconstruction based on double-domain generative adversarial network [J]. IEEE Journal of Biomedical and Health Informatics, 2022, 26(9): 4371-4377.

[14] ÖZBEY M, DALMAZ O, DAR S U H, et al. Unsupervised medical image translation with adversarial diffusion models [J]. IEEE Transactions on Medical Imaging, 2023, 42(12): 3524-3539.

[15] GÜNGÖR A, DAR S U, ÖZTÜRK Ş, et al. Adaptive diffusion priors for accelerated MRI reconstruction [J]. Medical Image Analysis, 2023, 88: 102872.

[16] SOUZA R, FRAYNE R. A hybrid frequency-domain/image-domain deep network for magnetic resonance image reconstruction [C]//2019 32nd SIBGRAPI Conference on Graphics, Patterns and Images. Rio de Janeiro: IEEE, 2019: 257-264.

[17] ZHOU B, ZHOU S K. DuDoRNet: learning a dual-domain recurrent network for fast MRI reconstruction with deep T1 prior [C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 4272-4281.

[18] YANG Y, SUN J, LI H B, et al. ADMM-CSNet: A deep learning approach for image compressive sensing [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(3): 521-538.

[19] ZHENG H, FANG F M, ZHANG G X. Cascaded dilated dense network with two-step data consistency for MRI reconstruction [C]// 33rd Conference on Neural Information Processing Systems. Vancouver: NIPS, 2019: 1744-1754.

[20] DUAN J M, SCHLEMPER J, QIN C, et al. VS-net: Variable splitting network for accelerated parallel MRI reconstruction [M]// Medical image computing and computer assisted intervention – MICCAI 2019. Cham: Springer, 2019: 713-722.

[21] SCHLEMPER J, CABALLERO J, HAJNAL J V, et al. A deep cascade of convolutional neural networks for dynamic MR image reconstruction [J]. IEEE Transactions on Medical Imaging, 2017, 37(2): 491-503.

[22] ZHANG J, GHANEM B. ISTA-net: Interpretable optimization-inspired deep network for image compressive sensing [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 1828-1837.

[23] 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.

[24] XIANG J X, DONG Y G, YANG Y J. FISTA-net: Learning a fast iterative shrinkage thresholding network for inverse problems in imaging [J]. IEEE Transactions on Medical Imaging, 2021, 40(5): 1329-1339.

[25] SINGH N M, IGLESIAS J E, ADALSTEINSSON E, et al. Joint frequency and image space learning for MRI reconstruction and analysis [J]. Machine Learning for Biomedical Imaging, 2022, 1: 1-28.

[26] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module [M]// Computer vision – ECCV 2018. Cham: Springer, 2018: 3-19.

[27] YU F, KOLTUN V. Multi-scale context aggregation by dilated convolutions [DB/OL]. (2015-11-23). https://arxiv.org/abs/1511.07122

[28] JIANG K, WANG Z Y, YI P, et al. Deep distillation recursive network for remote sensing imagery super-resolution [J]. Remote Sensing, 2018, 10(11): 1700.

[29] BIAN W. Optimization-Based Deep learning methods for Magnetic Resonance Imaging Reconstruction and Synthesis[D]. Gainesville: University of Florida, 2022.

[30] BERMÚDEZ C, REMEDIOS S, RAMADASS K, et al. Generalizing deep whole-brain segmentation for post-contrast MRI with transfer learning [J]. Journal of Medical Imaging, 2020, 7: 64004-064004.

[31] KINGMA D P, BA J. Adam: A method for stochastic optimization [DB/OL]. (2014-12-22). https://arxiv.org/abs/1412.6980

[32] BERNSTEIN M A, FAIN S B, RIEDERER S J. Effect of windowing and zero-filled reconstruction of MRI data on spatial resolution and acquisition strategy [J]. Journal of Magnetic Resonance Imaging, 2001, 14(3): 270-280.

[33] QU X B, GUO D, NING B D, et al. Undersampled MRI reconstruction with patch-based directional wavelets [J]. Magnetic Resonance Imaging, 2012, 30(7): 964-977.

[34] QU X B, HOU Y K, LAM F, et al. Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator [J]. Medical Image Analysis, 2014, 18(6): 843-856.

[35] FAN X H, YANG Y, ZHANG J P. Deep geometric distillation network for compressive sensing MRI [C]//2021 IEEE EMBS International Conference on Biomedical and Health Informatics. Athens: IEEE, 2021: 1-4.