Publication detail

Unfolded Low-rank + Sparse Reconstruction for MRI

MOKRÝ, O. VITOUŠ, J.

Original Title

Unfolded Low-rank + Sparse Reconstruction for MRI

Type

conference paper

Language

English

Original Abstract

We apply the methodology of deep unfolding on the problem of reconstruction of DCE-MRI data. The problem is formulated as a convex optimization problem, solvable via the primal–dual splitting algorithm. The unfolding allows for optimal hyperparameter selection for the model. We examine two approaches – with the parameters shared across the layers/iterations, and an adaptive version where the parameters can differ. The results demonstrate that the more complex model can better adapt to the data.

Keywords

DCE-MRI, proximal splitting algorithms, deep unfolding, L+S model

Authors

MOKRÝ, O.; VITOUŠ, J.

Released

26. 4. 2022

Publisher

Brno University of Technology, Faculty of Electrical Engineering and Communication

Location

Brno

ISBN

978-80-214-6030-0

Book

Proceedings II of the 28th Conference STUDENT EEICT 2022 Selected papers

Edition

1

Pages from

271

Pages to

275

Pages count

5

URL

BibTex

@inproceedings{BUT177793,
  author="Ondřej {Mokrý} and Jiří {Vitouš}",
  title="Unfolded Low-rank + Sparse Reconstruction for MRI",
  booktitle="Proceedings II of the 28th Conference STUDENT EEICT 2022 Selected papers",
  year="2022",
  series="1",
  pages="271--275",
  publisher="Brno University of Technology, Faculty of Electrical Engineering and Communication",
  address="Brno",
  isbn="978-80-214-6030-0",
  url="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2022_sbornik_2_v3.pdf"
}