MSCFN: Multiscale Spatial–Frequency Collaborative Fusion Network for Multicontrast Magnetic Resonance Imaging Super-Resolution

Magnetic resonance imaging (MRI) can obtain images with different contrasts and acquisition times de-pending on the imaging parameters. Utilizing a high-resolution contrast with a short acquisition time as a reference for the super-resolution (SR) of low-resolution contrasts with long acquisition times is effec-tive for the rapid acquisition of high-quality images. However, existing methods mainly process features in the spatial domain, and overlook potential features in the frequency domain. This paper proposes the multiscale spatial–frequency collaborative fusion network (MSCFN), which jointly leverages infor-mation in the spatial and frequency domains for SR. A global–local fusion block optimizes global struc-tural features and local texture details at different scales, and an adaptive low–high frequency fusion module utilizes the complementary nature of multiple contrasts to decompose reference images into high- and low-frequency components and adaptively fuse them to enhance feature integration. Experi-mental results indicated that MSCFN outperforms existing multicontrast MRI SR methods. The code is available at https://github.com/crystal177/MSCFN.