Cardiac MR Motion Artefact Correction from K-space Using Deep Learning-Based Reconstruction
- 1.8k Downloads
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.
KeywordsCardiac MR Image reconstruction Deep learning UK Biobank Image artefacts Image quality Automap
This work was supported by an EPSRC programme Grant (EP/P001009/1) and the Wellcome EPSRC Centre for Medical Engineering at the School of Biomedical Engineering and Imaging Sciences, King’s College London (WT 203148/Z/16/Z). This research has been conducted using the UK Biobank Resource under Application Number 17806. The GPU used in this research was generously donated by the NVIDIA Corporation.
- 1.Adler, J., et al.: Learning to solve inverse problems using Wasserstein loss. arXiv:1710.10898 (2017)
- 2.Ferreira, P.F., et al.: Cardiovascular magnetic resonance artefacts. JCMR 15, 1–41 (2013)Google Scholar
- 3.Frogner, C., et al.: Learning with a Wasserstein loss. In: NIPS, pp. 2053–2061 (2015)Google Scholar
- 4.Han, Y., et al.: k-Space deep learning for accelerated MRI. arXiv:1805.03779 (2018)
- 11.Oksuz, I., et al.: Deep learning using K-space based data augmentation for automated cardiac MR motion artefact detection. In: MICCAI (2018)Google Scholar
- 14.Schlemper, J., et al.: A deep cascade of convolutional neural networks for MR image reconstruction. In: IPMI (2017)Google Scholar
- 15.Schlemper, J., et al.: A deep cascade of convolutional neural networks for dynamic MR image reconstruction. IEEE TMI 37(2), 491–503 (2018)Google Scholar
- 17.Yang, G., et al.: DAGAN: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction. IEEE TMI 37, 1310–1321 (2017)Google Scholar