Magnetic resonance imaging (MRI) is a crucial tool for clinical diagnosis while facing the challenge of long scanning time. To reduce the acquisition time, fast MRI reconstruction aims to restore high-quality images from the undersampled k-space. Existing methods typically train deep learning models to map the undersampled data to artifact-free MRI images. However, these studies often overlook the unique properties of k-space and directly apply general networks designed for image processing to k-space recovery, leaving the precise learning of k-space largely underexplored. In this work, we propose a continuous k-space recovery network from a new perspective of implicit neural representation with image domain guidance, which boosts the performance of MRI reconstruction. Specifically, (1) an implicit neural representation based encoder-decoder structure is customized to continuously query unsampled k-values. (2) an image guidance module is designed to mine the semantic information from the low-quality MRI images to further guide the k-space recovery. (3) a multi-stage training strategy is proposed to recover dense k-space progressively. Extensive experiments conducted on CC359, fastMRI, and IXI datasets demonstrate the effectiveness of our method and its superiority over other competitors.

翻译：磁共振成像（MRI）是临床诊断的关键工具，但面临扫描时间长的挑战。为缩短采集时间，快速MRI重建旨在从欠采样的k空间中恢复高质量图像。现有方法通常训练深度学习模型将欠采样数据映射至无伪影的MRI图像。然而，这些研究常忽视k空间的独特性质，直接将为图像处理设计的通用网络应用于k空间恢复，导致对k空间的精确学习仍未被充分探索。本工作从隐式神经表示的新视角出发，提出一种结合图像域引导的连续k空间恢复网络，以提升MRI重建性能。具体而言：（1）定制基于隐式神经表示的编码器-解码器结构，以连续查询未采样的k值；（2）设计图像引导模块，从低质量MRI图像中挖掘语义信息，进一步指导k空间恢复；（3）提出多阶段训练策略，逐步恢复稠密k空间。在CC359、fastMRI和IXI数据集上的大量实验证明了本方法的有效性及其相对于其他竞争方法的优越性。