Efficient deformable motion correction for 3-D abdominal MRI using manifold regression

We present a novel framework for efficient retrospective respiratory motion correction of 3-D abdominal MRI using manifold regression. K-space data are continuously acquired under free breathing using the stack-of-stars radial gold-en-angle trajectory. The stack-of-profiles (SoP) from all temporal p...

Full description

Bibliographic Details
Main Authors: Chen, Xin, Balfour, Daniel R., Marsden, Paul K., Reader, Andrew J., Prieto, Claudia, King, Andrew P.
Format: Conference or Workshop Item
Published: 2017
Subjects:
Online Access:https://eprints.nottingham.ac.uk/46866/
_version_ 1848797415113490432
author Chen, Xin
Balfour, Daniel R.
Marsden, Paul K.
Reader, Andrew J.
Prieto, Claudia
King, Andrew P.
author_facet Chen, Xin
Balfour, Daniel R.
Marsden, Paul K.
Reader, Andrew J.
Prieto, Claudia
King, Andrew P.
author_sort Chen, Xin
building Nottingham Research Data Repository
collection Online Access
description We present a novel framework for efficient retrospective respiratory motion correction of 3-D abdominal MRI using manifold regression. K-space data are continuously acquired under free breathing using the stack-of-stars radial gold-en-angle trajectory. The stack-of-profiles (SoP) from all temporal positions are embedded into a common manifold, in which SoPs that were acquired at similar respiratory states are close together. Next, the SoPs in the manifold are clustered into groups using the k-means algorithm. One 3-D volume is reconstructed at the central SoP position of each cluster (a.k.a. key-volumes). Motion fields are estimated using deformable image registration between each of these key-volumes and a reference end-exhale volume. Subsequently, the motion field at any other SoP position in the manifold is derived using manifold regression. The regressed motion fields for each of the SoPs are used to deter-mine a final motion-corrected MRI volume. The method was evaluated on realistic synthetic datasets which were generated from real MRI data and also tested on an in vivo dataset. The framework enables more accurate motion correction compared to the conventional binning-based approach, with high computational efficiency.
first_indexed 2025-11-14T20:03:30Z
format Conference or Workshop Item
id nottingham-46866
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T20:03:30Z
publishDate 2017
recordtype eprints
repository_type Digital Repository
spelling nottingham-468662020-05-04T19:04:45Z https://eprints.nottingham.ac.uk/46866/ Efficient deformable motion correction for 3-D abdominal MRI using manifold regression Chen, Xin Balfour, Daniel R. Marsden, Paul K. Reader, Andrew J. Prieto, Claudia King, Andrew P. We present a novel framework for efficient retrospective respiratory motion correction of 3-D abdominal MRI using manifold regression. K-space data are continuously acquired under free breathing using the stack-of-stars radial gold-en-angle trajectory. The stack-of-profiles (SoP) from all temporal positions are embedded into a common manifold, in which SoPs that were acquired at similar respiratory states are close together. Next, the SoPs in the manifold are clustered into groups using the k-means algorithm. One 3-D volume is reconstructed at the central SoP position of each cluster (a.k.a. key-volumes). Motion fields are estimated using deformable image registration between each of these key-volumes and a reference end-exhale volume. Subsequently, the motion field at any other SoP position in the manifold is derived using manifold regression. The regressed motion fields for each of the SoPs are used to deter-mine a final motion-corrected MRI volume. The method was evaluated on realistic synthetic datasets which were generated from real MRI data and also tested on an in vivo dataset. The framework enables more accurate motion correction compared to the conventional binning-based approach, with high computational efficiency. 2017-09-04 Conference or Workshop Item PeerReviewed Chen, Xin, Balfour, Daniel R., Marsden, Paul K., Reader, Andrew J., Prieto, Claudia and King, Andrew P. (2017) Efficient deformable motion correction for 3-D abdominal MRI using manifold regression. In: International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2017), 10-14 Sept 2017, Quebec City, Quebec, Canada. 3D abdominal MRI Manifold learning Manifold regression Motion correction https://link.springer.com/chapter/10.1007/978-3-319-66185-8_31
spellingShingle 3D abdominal MRI
Manifold learning
Manifold regression
Motion correction
Chen, Xin
Balfour, Daniel R.
Marsden, Paul K.
Reader, Andrew J.
Prieto, Claudia
King, Andrew P.
Efficient deformable motion correction for 3-D abdominal MRI using manifold regression
title Efficient deformable motion correction for 3-D abdominal MRI using manifold regression
title_full Efficient deformable motion correction for 3-D abdominal MRI using manifold regression
title_fullStr Efficient deformable motion correction for 3-D abdominal MRI using manifold regression
title_full_unstemmed Efficient deformable motion correction for 3-D abdominal MRI using manifold regression
title_short Efficient deformable motion correction for 3-D abdominal MRI using manifold regression
title_sort efficient deformable motion correction for 3-d abdominal mri using manifold regression
topic 3D abdominal MRI
Manifold learning
Manifold regression
Motion correction
url https://eprints.nottingham.ac.uk/46866/
https://eprints.nottingham.ac.uk/46866/