Deep Learning for Retrospective Motion Correction in MRI: A Comprehensive Review

Veronika Spieker; Hannah Eichhorn; Kerstin Hammernik; Daniel Rueckert; Christine Preibisch; Dimitrios C. Karampinos; Julia A. Schnabel

doi:10.1109/TMI.2023.3323215

Deep Learning for Retrospective Motion Correction in MRI: A Comprehensive Review

Veronika Spieker, Hannah Eichhorn, Kerstin Hammernik, Daniel Rueckert, Christine Preibisch, Dimitrios C. Karampinos, Julia A. Schnabel^*

^*Corresponding author for this work

Biomedical Engineering Department

Research output: Contribution to journal › Article › peer-review

25 Citations (Scopus)

Abstract

Motion represents one of the major challenges in magnetic resonance imaging (MRI). Since the MR signal is acquired in frequency space, any motion of the imaged object leads to complex artefacts in the reconstructed image in addition to other MR imaging artefacts. Deep learning has been frequently proposed for motion correction at several stages of the reconstruction process. The wide range of MR acquisition sequences, anatomies and pathologies of interest, and motion patterns (rigid vs. deformable and random vs. regular) makes a comprehensive solution unlikely. To facilitate the transfer of ideas between different applications, this review provides a detailed overview of proposed methods for learning-based motion correction in MRI together with their common challenges and potentials. This review identifies differences and synergies in underlying data usage, architectures, training and evaluation strategies. We critically discuss general trends and outline future directions, with the aim to enhance interaction between different application areas and research fields.

Original language	English
Pages (from-to)	846-859
Number of pages	14
Journal	IEEE Transactions on Medical Imaging
Volume	43
Issue number	2
DOIs	https://doi.org/10.1109/TMI.2023.3323215
Publication status	Published - 1 Feb 2024

Keywords

deep learning
motion artefacts
motion compensation
Motion correction
motion simulation
MRI

Access to Document

10.1109/TMI.2023.3323215

Cite this

@article{4e61053c3ba8404fb38ed47fc523f52a,

title = "Deep Learning for Retrospective Motion Correction in MRI: A Comprehensive Review",

abstract = "Motion represents one of the major challenges in magnetic resonance imaging (MRI). Since the MR signal is acquired in frequency space, any motion of the imaged object leads to complex artefacts in the reconstructed image in addition to other MR imaging artefacts. Deep learning has been frequently proposed for motion correction at several stages of the reconstruction process. The wide range of MR acquisition sequences, anatomies and pathologies of interest, and motion patterns (rigid vs. deformable and random vs. regular) makes a comprehensive solution unlikely. To facilitate the transfer of ideas between different applications, this review provides a detailed overview of proposed methods for learning-based motion correction in MRI together with their common challenges and potentials. This review identifies differences and synergies in underlying data usage, architectures, training and evaluation strategies. We critically discuss general trends and outline future directions, with the aim to enhance interaction between different application areas and research fields.",

keywords = "deep learning, motion artefacts, motion compensation, Motion correction, motion simulation, MRI",

author = "Veronika Spieker and Hannah Eichhorn and Kerstin Hammernik and Daniel Rueckert and Christine Preibisch and Karampinos, {Dimitrios C.} and Schnabel, {Julia A.}",

note = "Publisher Copyright: {\textcopyright} 1982-2012 IEEE.",

year = "2024",

month = feb,

day = "1",

doi = "10.1109/TMI.2023.3323215",

language = "English",

volume = "43",

pages = "846--859",

journal = "IEEE Transactions on Medical Imaging",

issn = "0278-0062",

publisher = "I E E E",

number = "2",

}

TY - JOUR

T1 - Deep Learning for Retrospective Motion Correction in MRI

T2 - A Comprehensive Review

AU - Spieker, Veronika

AU - Eichhorn, Hannah

AU - Hammernik, Kerstin

AU - Rueckert, Daniel

AU - Preibisch, Christine

AU - Karampinos, Dimitrios C.

AU - Schnabel, Julia A.

PY - 2024/2/1

Y1 - 2024/2/1

N2 - Motion represents one of the major challenges in magnetic resonance imaging (MRI). Since the MR signal is acquired in frequency space, any motion of the imaged object leads to complex artefacts in the reconstructed image in addition to other MR imaging artefacts. Deep learning has been frequently proposed for motion correction at several stages of the reconstruction process. The wide range of MR acquisition sequences, anatomies and pathologies of interest, and motion patterns (rigid vs. deformable and random vs. regular) makes a comprehensive solution unlikely. To facilitate the transfer of ideas between different applications, this review provides a detailed overview of proposed methods for learning-based motion correction in MRI together with their common challenges and potentials. This review identifies differences and synergies in underlying data usage, architectures, training and evaluation strategies. We critically discuss general trends and outline future directions, with the aim to enhance interaction between different application areas and research fields.

AB - Motion represents one of the major challenges in magnetic resonance imaging (MRI). Since the MR signal is acquired in frequency space, any motion of the imaged object leads to complex artefacts in the reconstructed image in addition to other MR imaging artefacts. Deep learning has been frequently proposed for motion correction at several stages of the reconstruction process. The wide range of MR acquisition sequences, anatomies and pathologies of interest, and motion patterns (rigid vs. deformable and random vs. regular) makes a comprehensive solution unlikely. To facilitate the transfer of ideas between different applications, this review provides a detailed overview of proposed methods for learning-based motion correction in MRI together with their common challenges and potentials. This review identifies differences and synergies in underlying data usage, architectures, training and evaluation strategies. We critically discuss general trends and outline future directions, with the aim to enhance interaction between different application areas and research fields.

KW - deep learning

KW - motion artefacts

KW - motion compensation

KW - Motion correction

KW - motion simulation

KW - MRI

UR - http://www.scopus.com/inward/record.url?scp=85174856232&partnerID=8YFLogxK

U2 - 10.1109/TMI.2023.3323215

DO - 10.1109/TMI.2023.3323215

M3 - Article

C2 - 37831582

AN - SCOPUS:85174856232

SN - 0278-0062

VL - 43

SP - 846

EP - 859

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

IS - 2

ER -

Deep Learning for Retrospective Motion Correction in MRI: A Comprehensive Review

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this