Benchmarking learned non-Cartesian k-space trajectories and reconstruction networks
This work addresses the problem of optimizing MRI acquisition and reconstruction for researchers, but it is incremental as it focuses on benchmarking and comparing existing methods.
The paper benchmarks existing methods for jointly learning non-Cartesian k-space trajectories and reconstruction in MRI, comparing PILOT, BJORK, and a generalized hybrid learning framework, and reports results from a retrospective study on the fastMRI dataset.
We benchmark the current existing methods to jointly learn non-Cartesian k-space trajectory and reconstruction: PILOT, BJORK, and compare them with those obtained from the recently developed generalized hybrid learning (HybLearn) framework. We present the advantages of using projected gradient descent to enforce MR scanner hardware constraints as compared to using added penalties in the cost function. Further, we use the novel HybLearn scheme to jointly learn and compare our results through a retrospective study on fastMRI validation dataset.