基于小波域的复数卷积和复数Transformer的轻量级MR图像重建方法
Lightweight MR Image Reconstruction Network Based on Wavelet Domain Complex Convolution and Complex Transformer
- 电子学报 2025年53卷第4期 页码：1221-1231
- 作者机构：
1.燕山大学信息科学与工程学院，河北秦皇岛 066000
2.河北科技师范学院数学与信息科技学院，河北秦皇岛 066000
3.河北省信息传输与信号处理重点实验室，河北秦皇岛 066000
- 作者简介：
[ "张晓华 女，1979年12月出生于宁夏回族自治区青铜峡市.现为燕山大学信息科学与工程学院博士生，河北科技师范学院数学与信息科技学院讲师.主要研究方向为医学图像重建、深度学习.E-mail: zhang.xiaohua@126.com" ]
[ "练秋生 男，1969年8月出生于江西遂川县.现为燕山大学信息科学与工程学院教授，博士生导师.主要研究方向为图像处理、稀疏表示、压缩感知及深度学习等.中国电子学会会员编号：E190026832M.E-mail: lianqs@ysu.edu.cn" ]
- 基金信息：河北省自然科学基金(F2022203030)
DOI：10.12263/DZXB.20241058
中图分类号： TN911.73;TP391.41收稿：2024-11-25，
修回：2025-03-25，
纸质出版：2025-04-25
- 稿件说明：
移动端阅览
张晓华, 练秋生. 基于小波域的复数卷积和复数Transformer的轻量级MR图像重建方法[J]. 电子学报, 2025, 53(04): 1221-1231.
ZHANG Xiao-hua, LIAN Qiu-sheng. Lightweight MR Image Reconstruction Network Based on Wavelet Domain Complex Convolution and Complex Transformer[J]. Acta Electronica Sinica, 2025, 53(04): 1221-1231.
张晓华, 练秋生. 基于小波域的复数卷积和复数Transformer的轻量级MR图像重建方法[J]. 电子学报, 2025, 53(04): 1221-1231. DOI：10.12263/DZXB.20241058
ZHANG Xiao-hua, LIAN Qiu-sheng. Lightweight MR Image Reconstruction Network Based on Wavelet Domain Complex Convolution and Complex Transformer[J]. Acta Electronica Sinica, 2025, 53(04): 1221-1231. DOI：10.12263/DZXB.20241058
摘要
卷积神经网络能够从大规模数据中学习图像先验信息，在图像处理领域具有优异表现，但局部感受野使其难以捕捉像素间的远程依赖关系.Transformer网络架构具有全局感受野，在自然语言和高级视觉问题上表现出色，但其计算复杂度与图像尺寸的平方成正比，限制了其在高分辨图像处理任务中的应用.此外，许多MR（Magnetic Resonance）图像重建算法仅使用幅值数据或将实部和虚部分离到两个独立的通道作为网络输入，忽略了复值图像实部和虚部之间的相关性.本文提出基于复数卷积和复数Transformer的混合模块，既能利用卷积神经网络提取的高分辨率空间信息恢复MR图像细节，又能通过自注意力模块获取的全局上下文信息捕获远程特征.基于混合模块，结合小波变换进一步提出基于小波域的复数卷积和复数Transformer的轻量级MR图像重建算法.在Calgary-Campinas和fastMRI两个数据集上的实验结果表明，所提出的模型与四种具有代表性的MR图像重建算法相比，具有更高的重建性能和更少的资源消耗.源代码公开于
https：//github.com/zhangxh-qhd/WCCTNet
https://github.com/zhangxh-qhd/WCCTNet
.
Abstract
Convolutional neural networks (CNNs) have demonstrated remarkable capabilities in learning image priors from large-scale datasets
achieving exceptional performance across various image processing tasks. However
the local receptive field inherently limit their ability to capture long-range dependencies between pixels. In contrast
the transformer architecture
renowned for its global receptive field
has exhibited outstanding performance in natural language processing and high-level vision tasks. Nevertheless
its computational complexity
which scales quadratically with image size
poses significant challenges for high-resolution image processing applications. Furthermore
many magnetic resonance (MR) reconstruction algor
ithms exhibit limitations by either relying exclusively on magnitude data or processing real and imaginary components as separate channels
thereby failing to account for the intrinsic correlations within complex-valued images. By integrating complex convolution and complex transformer
an innovative hybrid module is introduced
which leverages the high-resolution spatial information extracted by CNNs to enhance the details of MR images and capture long-range features through global contextual information obtained by the self-attention module. Building on this hybrid module and wavelet transform
a lightweight MR image reconstruction method using complex convolution and complex transformer in the wavelet domain is further proposed. Experimental results on the Calgary-Campinas and fastMRI datasets demonstrate that the proposed model achieves superior reconstruction performance and while maintaining lower resource consumption compared to four representative MR image reconstruction algorithms. The source code is available at
https://github.com/zhangxh-qhd/WCCTNet
https://github.com/zhangxh-qhd/WCCTNet
.
关键词
Keywords
references
MADL J E M , NIETO ALVAREZ I , AMFT O , et al . The psychological, physiological, and behavioral responses of patients to magnetic resonance imaging (MRI): A systematic review and meta-analysis [J ] . Journal of Magnetic Resonance Imaging , 2024 , 59 ( 2 ): 675 - 687 .
YOU X X , CAO N , WANG W . An MTL1TV non-convex regularization model for MR Image reconstruction using the alternating direction method of multipliers [J ] . Electronic Research Archive , 2024 , 32 ( 5 ): 3433 - 3456 .
GENG C H , JIANG M F , FANG X , et al . HFIST-Net: High-throughput fast iterative shrinkage thresholding network for accelerating MR image reconstruction [J ] . Computer Methods and Programs in Biomedicine , 2023 , 232 : 107440 .
CHANDRA S S , BRAN LORENZANA M , LIU X W , et al . Deep learning in magnetic resonance image reconstruction [J ] . Journal of Medical Imaging and Radiation Oncology , 2021 , 65 ( 5 ): 564 - 577 .
GE Y M , XUE W , XU Y , et al . Magnetic resonance image denoising based on Laplacian prior sparsity constraint and nonconvex second-order TV penalty [J ] . Image Analysis & Stereology , 2023 , 42 ( 2 ): 119 - 132 .
LI Y Y , GAO L , HU S G , et al . Nonlocal low-rank plus deep denoising prior for robust image compressed sensing reconstruction [J ] . Expert Systems with Applications , 2023 , 228 : 120456 .
EKSIOGLU E M . Decoupled algorithm for MRI reconstruction using nonlocal block matching model: BM3D-MRI [J ] . Journal of Mathematical Imaging and Vision , 2016 , 56 ( 3 ): 430 - 440 .
SOOMRO T A , ZHENG L H , AFIFI A J , et al . Image segmentation for MR brain tumor detection using machine learning: A review [J ] . IEEE Reviews in Biomedical Engineering , 2023 , 16 : 70 - 90 .
DAS N , DAS S . Attention-UNet architectures with pretrained backbones for multi-class cardiac MR image segmentation [J ] . Current Problems in Cardiology , 2024 , 49 ( 1 ): 102129 .
HU Y X , LAFCI B , LUZGIN A , et al . Deep learning facilitates fully automated brain image registration of optoacoustic tomography and magnetic resonance imaging [J ] . Biomedical Optics Express , 2022 , 13 ( 9 ): 4817 - 4833 .
LIANG D , CHENG J , KE Z W , et al . Deep magnetic resonance image reconstruction: Inverse problems meet neural networks [J ] . IEEE Signal Processing Magazine , 2020 , 37 ( 1 ): 141 - 151 .
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 (ISBI) . Piscataway : IEEE , 2016 : 514 - 517 .
LEE D , YOO J , TAK S , et al . Deep residual learning for accelerated MRI using magnitude and phase networks [J ] . IEEE Transactions on Bio-Medical Engineering , 2018 , 65 ( 9 ): 1985 - 1995 .
SCHLEMPER J , CABALLERO J , HAJNAL J V , et al . A Deep Cascade of Convolutional Neural Networks for MR Image Reconstruction [M ] // Information Processing in Medical Imaging . Cham : Springer International Publishing , 2017 : 647 - 658 .
WANG S S , CHENG H T , YING L , et al . Deep complexMRI: Exploiting deep residual network for fast parallel MR imaging with complex convolution [J ] . Magnetic Resonance Imaging , 2020 , 68 : 136 - 147 .
COLE E , CHENG J , PAULY J , et al . Analysis of deep complex-valued convolutional neural networks for MRI reconstruction and phase-focused applications [J ] . Magnetic Resonance in Medicine , 2021 , 86 ( 2 ): 1093 - 1109 .
VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [C ] // Advances in Neural Information Processing Systems . Long Beach : Curran Associates , 2017 : 5998 - 6008 .
WU Z L , LIAO W B , YAN C , et al . Deep learning based MRI reconstruction with transformer [J ] . Computer Methods and Programs in Biomedicine , 2023 , 233 : 107452 .
GUO P F , MEI Y Q , ZHOU J Y , et al . ReconFormer: Accelerated MRI reconstruction using recurrent transformer [J ] . IEEE Transactions on Medical Imaging , 2024 , 43 ( 1 ): 582 - 593 .
HAN K , WANG Y H , CHEN H T , et al . A survey on vision transformer [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2023 , 45 ( 1 ): 87 - 110 .
LIANG J Y , CAO J Z , SUN G L , et al . SwinIR: Image restoration using swin transformer [C ] // 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) . Piscataway : IEEE , 2021 : 1833 - 1844 .
ZAMIR S W , ARORA A , KHAN S , et al . Restormer: Efficient transformer for high-resolution image restoration [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2022 : 5718 - 5729 .
HUANG J H , FANG Y Y , WU Y Z , et al . Swin transformer for fast MRI [J ] . Neurocomputing , 2022 , 493 : 281 - 304 .
ZHAO X , YANG T J , LI B J , et al . SwinGAN: A dual-domain Swin Transformer-based generative adversarial network for MRI reconstruction [J ] . Computers in Biology and Medicine , 2023 , 153 : 106513 .
曹洁 , 王乔 , 梁浩鹏 , 等 . 深度复数轴向自注意力卷积循环网络的语音增强 [J ] . 计算机系统应用 , 2024 , 33 ( 4 ): 60 - 68 .
CAO J , WANG Q , LIANG H P , et al . Speech enhancement based on deep complex axial self-attention convolutional recurrent network [J ] . Computer Systems and Applications , 2024 , 33 ( 4 ): 60 - 68 . (in Chinese)
EL-REWAIDY H , NEISIUS U , MANCIO J , et al . Deep complex convolutional network for fast reconstruction of 3D late gadolinium enhancement cardiac MRI [J ] . NMR in Biomedicine , 2020 , 33 ( 7 ): e4312 .
LEE C Y , HASEGAWA H , GAO S C . Complex-valued neural networks: A comprehensive survey [J ] . IEEE/CAA Journal of Automatica Sinica , 2022 , 9 ( 8 ): 1406 - 1426 .
LEE M . Mathematical analysis and performance evaluation of the GELU activation function in deep learning [J ] . Journal of Mathematics , 2023 , 2023 : 4229924 .
CHANG C L , GIROD B . Direction-adaptive discrete wavelet transform for image compression [J ] . IEEE Transactions on Image Processing , 2007 , 16 ( 5 ): 1289 - 1302 .
MIN T D , MANCINI M , ALAHARI K , et al . On the effectiveness of LayerNorm tuning for continual learning in vision transformers [C ] // 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) . Piscataway : IEEE , 2023 : 3577 - 3586 .
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 .
ZBONTAR J , KNOLL F , SRIRAM A , et al . fastMRI: An open dataset and benchmarks for accelerated MRI [EB/OL ] . ( 2018-11-21 )[ 2025-04-01 ] . https://arxiv.org/abs/1811.08839v2 https://arxiv.org/abs/1811.08839v2 .
SUBRAMANIAN V . Deep Learning with PyTorch: A Practical Approach to Building Neural Network Models Using PyTorch [M ] . Birmingham, UK : Packt Publishing , 2018 : 33 - 262 .
0
浏览量
11
下载量
0
CSCD
- 网络PDF下载
- Meta-XML下载
- BibTeX下载
- Endnote下载
- RefMan 下载
- NoteExpress下载
- NoteFirst下载
关联资源
相关文章
相关作者
相关机构
- 技术支持由北京北大方正电子有限公司提供 京ICP备09064830号-19
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies