i-RIM applied to the fastMRI challenge
Patrick Putzky, Dimitrios Karkalousos, Jonas Teuwen, Nikita Miriakov, Bart Bakker, Matthan Caan, Max Welling
arXiv:1910.08952v142 citations
Originality Synthesis-oriented
AI Analysis
This work addresses MRI reconstruction for medical imaging, but appears incremental as it builds on existing methods without claiming major breakthroughs.
The team tackled the fastMRI challenge by applying an invertible learning approach to infer models for both single-coil and multi-coil MRI reconstruction, but no concrete results or numbers are provided in the abstract.
We, team AImsterdam, summarize our submission to the fastMRI challenge (Zbontar et al., 2018). Our approach builds on recent advances in invertible learning to infer models as presented in Putzky and Welling (2019). Both, our single-coil and our multi-coil model share the same basic architecture.