Motion-Guided Physics-Based Learning for Cardiac MRI Reconstruction

Kerstin Hammernik, Jiazhen Pan, Daniel Rueckert, Thomas Kustner

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Scopus citations

Abstract

In this work, we propose a robust learning-based cardiac motion estimation framework, to estimate non-rigid cardiac motion fields from undersampled cardiac data. Our proposed frameworks leverages the advantages of a lightweight motion estimation network and a combination of photometric and smoothness losses. This framework enables the prediction of cardiac motion fields to further improve on the downstream task of motion-compensated image reconstruction. We evaluate our motion estimation framework qualitatively and quantitatively on 41 in-house acquired 2D cardiac CINE MRIs. Our proposed method provides quantitatively competitive results to state-of-the art methods in motion estimation, and superior results in image reconstruction in terms of structural similarity metric and peak-signal-to-noise ratio. Furthermore, our frameworks allows for ~3500x faster motion estimation compared to state-of-the-art approaches, opening up the practical application potential for motion-guided physics-based image reconstruction.

Original languageEnglish
Title of host publication55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021
EditorsMichael B. Matthews
PublisherIEEE Computer Society
Pages900-907
Number of pages8
ISBN (Electronic)9781665458283
DOIs
StatePublished - 2021
Externally publishedYes
Event55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021 - Virtual, Pacific Grove, United States
Duration: 31 Oct 20213 Nov 2021

Publication series

NameConference Record - Asilomar Conference on Signals, Systems and Computers
Volume2021-October
ISSN (Print)1058-6393

Conference

Conference55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021
Country/TerritoryUnited States
CityVirtual, Pacific Grove
Period31/10/213/11/21

Keywords

  • cardiac
  • deep learning
  • image reconstruction
  • magnetic resonance imaging
  • motion estimation
  • neural networks

Fingerprint

Dive into the research topics of 'Motion-Guided Physics-Based Learning for Cardiac MRI Reconstruction'. Together they form a unique fingerprint.

Cite this