Reconstruction of highly under-sampled dynamic MRI using sparse representation of 1D temporal snippets

Esben Plenge, Mitchell A. Cooper, Martin R. Prince, Yi Wang, Pascal Spincemaille, Michael Elad

Abstract

This paper introduces a new empirical model for dynamic MRI and shows its application to reconstruction of highly under-sampled dynamic MRI. The model proposes that short 1D signals, so-called snippets, along the image's temporal dimension are sparse under non-linear transformation using a compact dictionary trained on the data itself. We employ this model to the problem of reconstructing dynamic abdominal MRI and validate its efficacy on a dynamic computational phantom and on an in vivo dynamic MRI sequence. We show how the approach extends and outperforms a state-of-the-art reconstruction algorithm.
BibTeX
@inproceedings{plenge2015reconstruction,
  author = {Esben Plenge and Mitchell A. Cooper and Martin R. Prince and Yi Wang and Pascal Spincemaille and Michael Elad},
  title = {{Reconstruction of highly under-sampled dynamic MRI using sparse representation of 1D temporal snippets}},
  booktitle = {ISBI},
  year = {2015},
  doi = {10.1109/isbi.2015.7164098},
}

Loading related content...

Figure