Generalizing Deep Learning MRI Reconstruction across Different Domains
Abstract
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- January 2019
- DOI:
- 10.48550/arXiv.1902.10815
- arXiv:
- arXiv:1902.10815
- Bibcode:
- 2019arXiv190210815O
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition
- E-Print:
- Accepted for ISBI2019 as a 1-page abstract