Go back to publications View external

Benchmarking learned non-Cartesian k-space trajectories and reconstruction networks

January 2022 Chaithya Giliyar Radhakrishna, Philippe Ciuciu CoRR · Preprint (arXiv)
#Non-Cartesian Sampling #k-space Sampling #MRI #trajectory learning #MRI reconstruction #projected gradient descent

Abstract

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.

Details

  • Type of work: Preprint (arXiv)
  • Venue: CoRR
  • Published: 27 January 2022
  • DOI: 10.58530/2022/1785
  • Authors: Chaithya Giliyar Radhakrishna, and Philippe Ciuciu
  • Cited by: 1 times (OpenAlex)
  • Data sources: ref.bib, OpenAlex

BibTeX

@article{chaithya2022benchmarking,
  title={Benchmarking learned non-Cartesian k-space trajectories and reconstruction networks},
  author={Chaithya, GR and Ciuciu, Philippe},
  journal={CoRR},
  year={2022}
}