Detail publikace

Unrolled L+S decomposition for compressed sensing in magnetic resonance imaging

MOKRÝ, O. VITOUŠ, J.

Originální název

Unrolled L+S decomposition for compressed sensing in magnetic resonance imaging

Typ

článek v časopise - ostatní, Jost

Jazyk

angličtina

Originální abstrakt

A deep unrolled reconstruction method for dynamic magnetic resonance imaging is developed, based on the low-rank + sparse model. A standard solver of this model is enriched with trainable structures, forming a deep neural network, and several variants of the unrolled algorithm are trained on a simulated dataset. Evaluation against the standard solver for the model shows improvement in terms of mean squared error with the same computational cost.

Klíčová slova

magnetic resonance imaging, L+S model, reconstruction, unrolled optimization

Autoři

MOKRÝ, O.; VITOUŠ, J.

Vydáno

12. 12. 2022

Nakladatel

International Society for Science and Engineering, o.s.

Místo

Brno

ISSN

1213-1539

Periodikum

Elektrorevue - Internetový časopis (http://www.elektrorevue.cz)

Ročník

24

Číslo

3

Stát

Česká republika

Strany od

86

Strany do

93

Strany počet

8

URL

BibTex

@article{BUT180329,
  author="Ondřej {Mokrý} and Jiří {Vitouš}",
  title="Unrolled L+S decomposition for compressed sensing in magnetic resonance imaging",
  journal="Elektrorevue - Internetový časopis (http://www.elektrorevue.cz)",
  year="2022",
  volume="24",
  number="3",
  pages="86--93",
  issn="1213-1539",
  url="http://www.elektrorevue.cz/cz/clanky/zpracovani-signalu/0/unrolled-l-s-decomposition-for-compressed-sensing-in-magnetic-resonance-imaging--rozbaleny-l-s-rozklad-pro-komprimovane-snimani-pri-zobrazovani-magnetickou-rezonanci-/"
}