Publication detail

Frequency and phase shifts correction of MR spectra using deep learning in time domain

SHAMAEI, A. STARČUK, Z. Pavlova, I STARČUKOVÁ, J.

Original Title

Frequency and phase shifts correction of MR spectra using deep learning in time domain

Type

abstract

Language

English

Original Abstract

Processing magnetic resonance spectroscopy (MRS) signals remains challenging due to hardware and physiologic processes, which may lead to frequency and phase shifts (FPS). Thus, frequency-and-phase correction (FPC) is a useful step in MRS signal processing. Deep learning (DL) has proved to be successful in a wide range of tasks, including the MR field. DL applications in MRS have recently emerged1 . It has been shown that DL can also be used for FPC2 in the frequency domain with two separated networks. In this study, we proposed a novel deep autoencoder (DAE) network for FPC. We showed that a single DAE network could learn a nonlinear low-dimensional model to predict frequency and phase shifts.

Keywords

magnetic resonance spectroscopy, deep learning, deep autoencoder, frequency and phase correction

Authors

SHAMAEI, A.; STARČUK, Z.; Pavlova, I; STARČUKOVÁ, J.

Released

18. 9. 2021

Publisher

Springer

Pages from

175

Pages to

175

Pages count

1

URL

https://link.springer.com/article/10.1007/s10334-021-00947-8

BibTex

@misc{BUT177483,
  author="SHAMAEI, A. and STARČUK, Z. and Pavlova, I and STARČUKOVÁ, J.",
  title="Frequency and phase shifts correction of MR spectra using deep learning in time domain",
  year="2021",
  pages="175--175",
  publisher="Springer",
  doi="10.1007/s10334-021-00947-8",
  url="https://link.springer.com/article/10.1007/s10334-021-00947-8",
  note="abstract"
}