Reconstructing images from under-sampled Magnetic Resonance Imaging (MRI) signals significantly reduces scan time and improves clinical practice. However, Convolutional Neural Network (CNN)-based methods, while demonstrating great performance in MRI reconstruction, may face limitations due to their restricted receptive field (RF), hindering the capture of global features. This is particularly crucial for reconstruction, as aliasing artifacts are distributed globally. Recent advancements in Vision Transformers have further emphasized the significance of a large RF. In this study, we proposed a novel global Fourier Convolution Block (FCB) with whole image RF and low computational complexity by transforming the regular spatial domain convolutions into frequency domain. Visualizations of the effective RF and trained kernels demonstrated that FCB improves the RF of reconstruction models in practice. The proposed FCB was evaluated on four popular CNN architectures using brain and knee MRI datasets. Models with FCB achieved superior PSNR and SSIM than baseline models and exhibited more details and texture recovery. The code is publicly available at https://github.com/Haozhoong/FCB.

中文翻译：

---

用于 MRI 重建的具有全局感受野的傅里叶卷积块


从采样不足的磁共振成像 （MRI） 信号中重建图像可显著缩短扫描时间并改善临床实践。然而，基于卷积神经网络 （CNN） 的方法虽然在 MRI 重建中表现出出色的性能，但由于感受野 （RF） 受限，可能面临限制，阻碍了全局特征的捕获。这对于重建尤其重要，因为混叠伪影分布在全球。Vision Transformer 的最新进展进一步强调了大型 RF 的重要性。在这项研究中，我们通过将常规空间域卷积转换为频域，提出了一种具有全图像射频和低计算复杂度的新型全局傅里叶卷积块 （FCB）。有效 RF 和训练内核的可视化表明，FCB 在实践中提高了重建模型的 RF。使用脑部和膝关节 MRI 数据集在四种流行的 CNN 架构上评估了所提出的 FCB。与基线模型相比，具有 FCB 的模型实现了更好的 PSNR 和 SSIM，并表现出更多的细节和纹理恢复。该代码在 https://github.com/Haozhoong/FCB 上公开提供。