Is good old GRAPPA dead?
arXiv:2106.00753v2
AI Analysis
This is an incremental study for MRI reconstruction researchers, showing competitive results without establishing broad superiority.
The paper compared the performance of XPDNet, a deep learning method for MRI reconstruction, against the classical GRAPPA approach, finding that XPDNet generalizes well to unseen settings.
We perform a qualitative analysis of performance of XPDNet, a state-of-the-art deep learning approach for MRI reconstruction, compared to GRAPPA, a classical approach. We do this in multiple settings, in particular testing the robustness of the XPDNet to unseen settings, and show that the XPDNet can to some degree generalize well.