Skip to main content
Top

Hint

Swipe to navigate through the chapters of this book

2018 | OriginalPaper | Chapter

Cardiac MR Motion Artefact Correction from K-space Using Deep Learning-Based Reconstruction

Authors : Ilkay Oksuz, James Clough, Aurelien Bustin, Gastao Cruz, Claudia Prieto, Rene Botnar, Daniel Rueckert, Julia A. Schnabel, Andrew P. King

Published in: Machine Learning for Medical Image Reconstruction

Publisher: Springer International Publishing

share
SHARE

Abstract

Incorrect ECG gating of cardiac magnetic resonance (CMR) acquisitions can lead to artefacts, which hampers the accuracy of diagnostic imaging. Therefore, there is a need for robust reconstruction methods to ensure high image quality. In this paper, we propose a method to automatically correct motion-related artefacts in CMR acquisitions during reconstruction from k-space data. Our method is based on the Automap reconstruction method, which directly reconstructs high quality MR images from k-space using deep learning. Our main methodological contribution is the addition of an adversarial element to this architecture, in which the quality of image reconstruction (the generator) is increased by using a discriminator. We train the reconstruction network to automatically correct for motion-related artefacts using synthetically corrupted CMR k-space data and uncorrupted reconstructed images. Using 25000 images from the UK Biobank dataset we achieve good image quality in the presence of synthetic motion artefacts, but some structural information was lost. We quantitatively compare our method to a standard inverse Fourier reconstruction. In addition, we qualitatively evaluate the proposed technique using k-space data containing real motion artefacts.
Literature
2.
go back to reference Ferreira, P.F., et al.: Cardiovascular magnetic resonance artefacts. JCMR 15, 1–41 (2013) Ferreira, P.F., et al.: Cardiovascular magnetic resonance artefacts. JCMR 15, 1–41 (2013)
3.
go back to reference Frogner, C., et al.: Learning with a Wasserstein loss. In: NIPS, pp. 2053–2061 (2015) Frogner, C., et al.: Learning with a Wasserstein loss. In: NIPS, pp. 2053–2061 (2015)
5.
go back to reference Jin, K.H., et al.: Deep convolutional neural network for inverse problems in imaging. IEEE TIP 26(9), 4509–4522 (2017) MathSciNet Jin, K.H., et al.: Deep convolutional neural network for inverse problems in imaging. IEEE TIP 26(9), 4509–4522 (2017) MathSciNet
6.
go back to reference Kim, Y.C., et al.: Automatic correction of echoplanar imaging (EPI) ghosting artifacts in realtime interactive cardiac MRI using sensitivity encoding. JMRI 27(1), 239–245 (2008) CrossRef Kim, Y.C., et al.: Automatic correction of echoplanar imaging (EPI) ghosting artifacts in realtime interactive cardiac MRI using sensitivity encoding. JMRI 27(1), 239–245 (2008) CrossRef
7.
go back to reference Kwon, K., et al.: A parallel MR imaging method using multilayer perceptron. Med. Phys. 44(12), 6209–6224 (2017) CrossRef Kwon, K., et al.: A parallel MR imaging method using multilayer perceptron. Med. Phys. 44(12), 6209–6224 (2017) CrossRef
8.
go back to reference Lotjonen, J., et al.: Correction of motion artifacts from cardiac cine magnetic resonance images. Acad. Radiol. 12(10), 1273–1284 (2005) CrossRef Lotjonen, J., et al.: Correction of motion artifacts from cardiac cine magnetic resonance images. Acad. Radiol. 12(10), 1273–1284 (2005) CrossRef
9.
go back to reference Lustig, M., et al.: Compressed sensing MRI. IEEE Sig. Process. Mag. 25(2), 72–82 (2008) CrossRef Lustig, M., et al.: Compressed sensing MRI. IEEE Sig. Process. Mag. 25(2), 72–82 (2008) CrossRef
10.
go back to reference McCann, M.T., et al.: Convolutional neural networks for inverse problems in imaging: a review. IEEE Sig. Process. Mag. 34(6), 85–95 (2017) MathSciNetCrossRef McCann, M.T., et al.: Convolutional neural networks for inverse problems in imaging: a review. IEEE Sig. Process. Mag. 34(6), 85–95 (2017) MathSciNetCrossRef
11.
go back to reference Oksuz, I., et al.: Deep learning using K-space based data augmentation for automated cardiac MR motion artefact detection. In: MICCAI (2018) Oksuz, I., et al.: Deep learning using K-space based data augmentation for automated cardiac MR motion artefact detection. In: MICCAI (2018)
12.
go back to reference Petersen, S.E., et al.: UK Biobank’s cardiovascular magnetic resonance protocol. JCMR 18(1), 1–8 (2016) MathSciNet Petersen, S.E., et al.: UK Biobank’s cardiovascular magnetic resonance protocol. JCMR 18(1), 1–8 (2016) MathSciNet
13.
go back to reference Saremi, F., et al.: Optimizing cardiac MR imaging: practical remedies for artifacts. Radiographics 28(4), 1161–1187 (2008) CrossRef Saremi, F., et al.: Optimizing cardiac MR imaging: practical remedies for artifacts. Radiographics 28(4), 1161–1187 (2008) CrossRef
14.
go back to reference Schlemper, J., et al.: A deep cascade of convolutional neural networks for MR image reconstruction. In: IPMI (2017) Schlemper, J., et al.: A deep cascade of convolutional neural networks for MR image reconstruction. In: IPMI (2017)
15.
go back to reference Schlemper, J., et al.: A deep cascade of convolutional neural networks for dynamic MR image reconstruction. IEEE TMI 37(2), 491–503 (2018) Schlemper, J., et al.: A deep cascade of convolutional neural networks for dynamic MR image reconstruction. IEEE TMI 37(2), 491–503 (2018)
16.
go back to reference Wang, Z., et al.: Image quality assessment: from error visibility to structural similarity. IEEE TIP 13(4), 600–612 (2004) MathSciNet Wang, Z., et al.: Image quality assessment: from error visibility to structural similarity. IEEE TIP 13(4), 600–612 (2004) MathSciNet
17.
go back to reference Yang, G., et al.: DAGAN: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction. IEEE TMI 37, 1310–1321 (2017) Yang, G., et al.: DAGAN: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction. IEEE TMI 37, 1310–1321 (2017)
18.
go back to reference Zhu, B., et al.: Image reconstruction by domain-transform manifold learning. Nature 555(7697), 487 (2018) CrossRef Zhu, B., et al.: Image reconstruction by domain-transform manifold learning. Nature 555(7697), 487 (2018) CrossRef
Metadata
Title
Cardiac MR Motion Artefact Correction from K-space Using Deep Learning-Based Reconstruction
Authors
Ilkay Oksuz
James Clough
Aurelien Bustin
Gastao Cruz
Claudia Prieto
Rene Botnar
Daniel Rueckert
Julia A. Schnabel
Andrew P. King
Copyright Year
2018
DOI
https://doi.org/10.1007/978-3-030-00129-2_3

Premium Partner