Generalizing Deep Learning MRI Reconstruction across Different Domains
This addresses robustness issues in medical imaging for clinicians and researchers, but is incremental as it adapts existing methods to new data.
The paper tackles the problem of deep learning MRI reconstruction failing on unseen contrasts and organs, and proposes training with large natural image datasets with synthesized phase information to achieve cross-domain performance competitive with domain-specific training.
We look into the robustness of deep learning based MRI reconstruction when tested on unseen contrasts and organs. We then propose to generalize the network by training with large publicly-available natural image datasets with synthesized phase information to achieve high cross-domain reconstruction performance which is competitive with domain-specific training. To explain its generalization mechanism, we have also analyzed patch sets for different training datasets.