Rethinking Dual-Domain Undersampled MRI reconstruction: domain-specific design from the perspective of the receptive field
This work addresses accelerating clinical MRI scanning, but it appears incremental as it builds on existing dual-domain methods.
The paper tackled undersampled MRI reconstruction by rethinking dual-domain model design from a receptive field perspective and introducing domain-specific modules, achieving significant improvements over competing deep learning methods on the IXI dataset.
Undersampled MRI reconstruction is crucial for accelerating clinical scanning. Dual-domain reconstruction network is performant among SoTA deep learning methods. In this paper, we rethink dual-domain model design from the perspective of the receptive field, which is needed for image recovery and K-space interpolation problems. Further, we introduce domain-specific modules for dual-domain reconstruction, namely k-space global initialization and image-domain parallel local detail enhancement. We evaluate our modules by translating a SoTA method DuDoRNet under different conventions of MRI reconstruction including image-domain, dual-domain, and reference-guided reconstruction on the public IXI dataset. Our model DuDoRNet+ achieves significant improvements over competing deep learning methods.