Zhang Huiyao, Yang Tiejun, Wang Heng, Fan Jiacheng, Zhang Wenjie, Ji Mingzhu
School of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China.
School of Artificial Intelligence and Big Data, Henan University of Technology, Zhengzhou 450001, China; Key Laboratory of Grain Information Processing and Control (HAUT), Ministry of Education, Zhengzhou, China; Henan Key Laboratory of Grain Photoelectric Detection and Control (HAUT), Zhengzhou, Henan, China.
Magn Reson Imaging. 2025 Apr;117:110336. doi: 10.1016/j.mri.2025.110336. Epub 2025 Jan 24.
Magnetic resonance imaging (MRI) is a non-invasive medical imaging technique that is widely used for high-resolution imaging of soft tissues and organs. However, the slow speed of MRI imaging, especially in high-resolution or dynamic scans, makes MRI reconstruction an important research topic. Currently, MRI reconstruction methods based on deep learning (DL) have garnered significant attention, and they improve the reconstruction quality by learning complex image features. However, DL-based MR image reconstruction methods exhibit certain limitations. First, the existing reconstruction networks seldom account for the diverse frequency features in the wavelet domain. Second, existing dual-domain reconstruction methods may pay too much attention to the features of a single domain (such as the global information in the image domain or the local details in the wavelet domain), resulting in the loss of either critical global structures or fine details in certain regions of the reconstructed image. In this work, inspired by the lifting scheme in wavelet theory, we propose a novel Fully Dual-Domain Contrastive Learning Network (FDuDoCLNet) based on variational networks (VarNet) for accelerating PI in both the image and wavelet domains. It is composed of several cascaded dual-domain regularization units and data consistency (DC) layers, in which a novel dual-domain contrastive loss is introduced to optimize the reconstruction performance effectively. The proposed FDuDoCLNet was evaluated on the publicly available fastMRI multi-coil knee dataset under a 6× acceleration factor, achieving a PSNR of 34.439 dB and a SSIM of 0.895.
磁共振成像（MRI）是一种非侵入性医学成像技术，广泛用于软组织和器官的高分辨率成像。然而，MRI成像速度较慢，尤其是在高分辨率或动态扫描中，这使得MRI重建成为一个重要的研究课题。目前，基于深度学习（DL）的MRI重建方法受到了广泛关注，它们通过学习复杂的图像特征来提高重建质量。然而，基于DL的MR图像重建方法存在一定的局限性。首先，现有的重建网络很少考虑小波域中多样的频率特征。其次，现有的双域重建方法可能过于关注单个域的特征（如图像域中的全局信息或小波域中的局部细节），导致重建图像的某些区域丢失关键的全局结构或精细细节。在这项工作中，受小波理论中的提升方案启发，我们提出了一种基于变分网络（VarNet）的新型全双域对比学习网络（FDuDoCLNet），用于在图像域和小波域中加速并行成像（PI）。它由几个级联的双域正则化单元和数据一致性（DC）层组成，其中引入了一种新型的双域对比损失来有效优化重建性能。所提出的FDuDoCLNet在公开可用的fastMRI多线圈膝关节数据集上以6倍加速因子进行了评估，实现了34.439 dB的峰值信噪比（PSNR）和0.895的结构相似性指数（SSIM）。
