Dual-Domain Differentiated Feature Extraction Network for MRI Reconstruction

XUE Nan; QIAO Han; WANG Peng

doi:10.11999/JEIT251093

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2026 >

XUE Nan, QIAO Han, WANG Peng. Dual-Domain Differentiated Feature Extraction Network for MRI Reconstruction[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT251093

Citation:

XUE Nan, QIAO Han, WANG Peng. Dual-Domain Differentiated Feature Extraction Network for MRI Reconstruction[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT251093

XUE Nan, QIAO Han, WANG Peng. Dual-Domain Differentiated Feature Extraction Network for MRI Reconstruction[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT251093

Citation:

XUE Nan, QIAO Han, WANG Peng. Dual-Domain Differentiated Feature Extraction Network for MRI Reconstruction[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT251093

PDF( 3334 KB)

Dual-Domain Differentiated Feature Extraction Network for MRI Reconstruction

doi: 10.11999/JEIT251093 cstr: 32379.14.JEIT251093

XUE Nan^{1
,
,},
QIAO Han¹,
WANG Peng²

1.
School of Measurement and Control Technology and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, China
2.
School of Electrical and Information Engineering, Changzhou Institute of Technology, Changzhou 213032, China

Received Date: 2025-10-14
Accepted Date: 2026-08-24
Rev Recd Date: 2026-05-04

Available Online: 2026-08-29

Abstract

Abstract

Objective In magnetic resonance imaging (MRI), undersampling of k-space data is an effective approach to accelerate image acquisition. Reconstructing high-quality MR images from undersampled data is of great clinical significance for diagnostic efficiency. Currently, dual-domain reconstruction methods that jointly exploit spatial- and frequency-domain features have become mainstream. However, existing dual-domain MRI reconstruction methods fail to design differentiated feature extraction strategies for the two domains, and their physical prior constraints are insufficient, leading to loss of original information during the reconstruction process. Methods To address these issues, this study proposes a Dual-Domain Differentiated Feature Extraction Network (DDF-Net) for MRI reconstruction. In the spatial domain, an interlaced row-column self-attention mechanism combined with depthwise convolution is designed to accurately capture anisotropic structures and texture details, thereby addressing the limitations of conventional convolutional feature extraction. In the frequency domain, amplitude and phase characteristics are independently modeled to capture intensity and structural positional information, respectively, and a frequency-domain feature enhancement module is introduced to fully exploit spectral information for improving reconstruction fidelity. Finally, a data consistency layer and a cross-domain adjustment module are incorporated to integrate physical priors and cross-domain information, thereby reinforcing measurement consistency and stabilizing the reconstruction process. Results and Discussions The proposed DDF-Net was evaluated on two publicly available MRI datasets, CC359 and IXI, and compared with six representative reconstruction algorithms, including DAGAN, KIKI-Net, MD-Recon-Net, SwinMR, Reconmer, and KTMR. As shown in Fig. 6 and Fig. 7, under a Gaussian 1D 30% undersampling mask, DDF-Net achieves the most faithful anatomical restoration with clearer cortical edges and finer texture details, while suppressing aliasing artifacts effectively. The error maps exhibit more uniform residual distributions, indicating better consistency between the reconstructed and reference images. Quantitative comparisons (Table 1 and Table 2) show that DDF-Net attains the highest PSNR and SSIM values across all sampling patterns. Specifically, it improves PSNR by 0.17 dB and 0.23 dB, and SSIM by 0.0063 and 0.0019 on the CC359 and IXI datasets, respectively, achieving the best overall performance over the second-best competing method. These results demonstrate that the differentiated spatial-frequency feature extraction enables DDF-Net to leverage complementary information between domains for more precise recovery. To further verify robustness, a noise experiment was conducted by adding Gaussian noise of varying intensity levels to the k-space data, following the procedure in SwinMR. As illustrated in Fig. 8 and summarized in Table 3, DDF-Net exhibits stronger robustness to noise perturbations, maintaining higher PSNR and SSIM values than SwinMR under all noise conditions. Even at NL = 80%, DDF-Net effectively preserves most structural details, confirming that the amplitude-phase separation and multi-level data consistency jointly improve noise resilience and stability. Conclusions This study proposes an end-to-end Dual-Domain Differentiated Feature Extraction Network to address the limitations of existing dual-domain MRI reconstruction methods, which often lack domain-specific feature extraction strategies and sufficient physical prior constraints, leading to potential information loss during reconstruction. In the spatial domain, an interlaced row-column self-attention mechanism is designed to more effectively model local structures and texture details. In the frequency domain, amplitude-phase separation and a frequency-domain feature enhancement module are introduced to effectively improve the decoupling and utilization of spectral information. Furthermore, by integrating a cross-domain adjustment module with multiple data consistency layers, DDF-Net enhances cross-domain interaction and measurement fidelity. Experimental results on the CC359 and IXI datasets demonstrate that the proposed method achieves superior performance in both quantitative metrics and visual reconstruction quality, successfully recovering fine anatomical details. In addition, noise experiments confirm the robustness of DDF-Net under complex conditions, showing that the network can effectively preserve image details across various noise levels. Future work will focus on extending DDF-Net to unsupervised or semi-supervised learning frameworks to reduce dependence on labeled data and further enhance its potential for clinical applications in fast MRI reconstruction.
- Magnetic resonance imaging,
- accelerated imaging,
- differentiated feature extraction,
- dual-domain feature fusion

FullText(HTML)

References(22)

References

[1]	刘侠, 吕志伟, 李博, 等. 基于多尺度残差双域注意力网络的乳腺动态对比度增强磁共振成像肿瘤分割方法[J]. 电子与信息学报, 2023, 45(5): 1774–1785. doi: 10.11999/JEIT220362. LIU Xia, LÜ Zhiwei, LI Bo, et al. Segmentation algorithm of breast tumor in dynamic contrast-enhanced magnetic resonance imaging based on network with multi-scale residuals and dual-domain attention[J]. Journal of Electronics & Information Technology, 2023, 45(5): 1774–1785. doi: 10.11999/JEIT220362.
[2]	宋笑影, 郝春雨, 柴利. 面向注意力缺陷多动障碍分类的多分辨率时空融合图卷积网络[J]. 电子与信息学报, 2025, 47(6): 1927–1936. doi: 10.11999/JEIT240872. SONG Xiaoying, HAO Chunyu, and CHAI Li. Multi-resolution spatio-temporal fusion graph convolutional network for attention deficit hyperactivity disorder classification[J]. Journal of Electronics & Information Technology, 2025, 47(6): 1927–1936. doi: 10.11999/JEIT240872.
[3]	SAFARI M, EIDEX Z, CHANG C W, et al. Advancing MRI reconstruction: A systematic review of deep learning and compressed sensing integration[J]. Biomedical Signal Processing and Control, 2026, 111: 108291. doi: 10.1016/J.bspc.2025.108291.
[4]	LYU Weiyi, FANG Xinming, HUANG Chaoyan, et al. Fast MRI reconstruction: A thorough survey from single-modal to multi-modal[J]. Expert Systems with Applications, 2025, 283: 127703. doi: 10.1016/J.eswa.2025.127703.
[5]	HAMILTON J, FRANSON D, and SEIBERLICH N. Recent advances in parallel imaging for MRI[J]. Progress in Nuclear Magnetic Resonance Spectroscopy, 2017, 101: 71–95. doi: 10.1016/j.pnmrs.2017.04.002.
[6]	蒋明峰, 刘渊, 徐文龙, 等. 基于全变分扩展方法的压缩感知磁共振成像算法研究[J]. 电子与信息学报, 2015, 37(11): 2608–2612. doi: 10.11999/JEIT150179. JIANG Mingfeng, LIU Yuan, XU Wenlong, et al. The study of compressed sensing MR image reconstruction algorithm based on the extension of total variation method[J]. Journal of Electronics & Information Technology, 2015, 37(11): 2608–2612. doi: 10.11999/JEIT150179.
[7]	WANG Shanshan, SU Zhenghang, YING L, et al. Accelerating magnetic resonance imaging via deep learning[C]. Proceedings of 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), Prague, Czech Republic, 2016: 514–517. doi: 10.1109/ISBI.2016.7493320.
[8]	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, 2018, 37(2): 491–503. doi: 10.1109/TMI.2017.2760978.
[9]	YANG Guang, YU Simiao, DONG Hao, 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. doi: 10.1109/TMI.2017.2785879.
[10]	HUANG Jiahao, DING Weiping, LV Jun, et al. Edge-enhanced dual discriminator generative adversarial network for fast MRI with parallel imaging using multi-view information[J]. Applied Intelligence, 2022, 52(13): 14693–14710. doi: 10.1007/s10489-021-03092-w.
[11]	HUANG Jiahao, FANG Yingying, WU Yinzhe, et al. Swin transformer for fast MRI[J]. Neurocomputing, 2022, 493: 281–304. doi: 10.1016/J.neucom.2022.04.051.
[12]	LIU Ze, LIN Yutong, CAO Yue, et al. Swin transformer: Hierarchical vision transformer using shifted windows[C]. Proceedings of 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, Canada, 2021: 9992–10002. doi: 10.1109/ICCV48922.2021.00986.
[13]	GUO Pengfei, MEI Yiqun, ZHOU Jinyuan, et al. ReconFormer: Accelerated MRI reconstruction using recurrent transformer[J]. IEEE Transactions on Medical Imaging, 2024, 43(1): 582–593. doi: 10.1109/TMI.2023.3314747.
[14]	WU Zhengliang, LIAO Weibin, YAN Chao, et al. Deep learning based MRI reconstruction with transformer[J]. Computer Methods and Programs in Biomedicine, 2023, 233: 107452. doi: 10.1016/J.cmpb.2023.107452.
[15]	LIANG Jingyun, CAO Jiezhang, SUN Guolei, et al. SwinIR: Image restoration using Swin transformer[C]. Proceedings of 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Montreal, Canada, 2021: 1833–1844. doi: 10.1109/ICCVW54120.2021.00210.
[16]	RAMANARAYANAN S, RAHUL G S, AL FAHIM M, et al. SHFormer: Dynamic spectral filtering convolutional neural network and high-pass kernel generation transformer for adaptive MRI reconstruction[J]. Neural Networks, 2025, 187: 107334. doi: 10.1016/J.neunet.2025.107334.
[17]	EO T, JUN Y, KIM T, et al. KIKI‐net: Cross‐domain convolutional neural networks for reconstructing undersampled magnetic resonance images[J]. Magnetic Resonance in Medicine, 2018, 80(5): 2188–2201. doi: 10.1002/mrm.27201.
[18]	WANG Zhilun, JIANG Haitao, DU Hongwei, et al. IKWI-net: A cross-domain convolutional neural network for undersampled magnetic resonance image reconstruction[J]. Magnetic Resonance Imaging, 2020, 73: 1–10. doi: 10.1016/j.mri.2020.06.015.
[19]	RAN Maosong, XIA Wenjun, HUANG Yongqiang, et al. MD-Recon-Net: A parallel dual-domain convolutional neural network for compressed sensing MRI[J]. IEEE Transactions on Radiation and Plasma Medical Sciences, 2021, 5(1): 120–135. doi: 10.1109/trpms.2020.2991877.
[20]	LIU Yu, PANG Yanwei, LIU Xiaohan, et al. DIIK-Net: A full-resolution cross-domain deep interaction convolutional neural network for MR image reconstruction[J]. Neurocomputing, 2023, 517: 213–222. doi: 10.1016/j.neucom.2022.09.048.
[21]	LIU Qiaohong, ZHANG Weikun, ZHANG Yuting, et al. DGEDDGAN: A dual-domain generator and edge-enhanced dual discriminator generative adversarial network for MRI reconstruction[J]. Magnetic Resonance Imaging, 2025, 119: 110381. doi: 10.1016/J.mri.2025.110381.
[22]	李秀梅, 丁林琳, 孙军梅, 等. SR-FDN: 面向图像细节恢复的频域扩散超分辨率重建网络[J]. 电子与信息学报, 2025, 47(10): 3941–3950. doi: 10.11999/JEIT250224. LI Xiumei, DING Linlin, SUN Junmei, et al. SR-FDN: A frequency-domain diffusion network for image detail restoration in super-resolution[J]. Journal of Electronics & Information Technology, 2025, 47(10): 3941–3950. doi: 10.11999/JEIT250224.