i-RIM applied to the fastMRI challenge

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.

arXiv commentAbstract submitted to the fastMRI challenge

References in corpus (3)

• fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
• Recurrent Inference Machines for Solving Inverse Problems
• Invert to Learn to Invert

Cited by in corpus (6)

• Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction
• Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challenge
• Assessment of Data Consistency through Cascades of Independently Recurrent Inference Machines for fast and robust accelerated MRI reconstruction
• Experimental design for MRI by greedy policy search
• Reconstructing unseen modalities and pathology with an efficient Recurrent Inference Machine
• Learning to Predict Error for MRI Reconstruction