Multi-tasking to Correct: Motion-Compensated MRI via Joint Reconstruction and Registration
This work addresses a central topic in Magnetic Resonance Imaging (MRI) which is the motion-correction problem in a joint reconstruction and registration framework. From a set of multiple MR acquisitions corrupted by motion, we aim at - jointly - reconstructing a single motion-free corrected image and retrieving the physiological dynamics through the deformation maps. To this purpose, we propose a novel variational model. First, we introduce an \(L^2\) fidelity term, which intertwines reconstruction and registration along with the weighted total variation. Second, we introduce an additional regulariser which is based on the hyperelasticity principles to allow large and smooth deformations. We demonstrate through numerical results that this combination creates synergies in our complex variational approach resulting in higher quality reconstructions and a good estimate of the breathing dynamics. We also show that our joint model outperforms in terms of contrast, detail and blurring artefacts, a sequential approach.
Keywords2D registration Reconstruction Joint model Motion correction Magnetic Resonance Imaging Nonlinear elasticity Weighted total variation
VC acknowledges the financial support of the Cambridge Cancer Centre. Support from the CMIH and CCIMI University of Cambridge is greatly acknowledged.
- 2.Aviles-Rivero, A.I., Williams, G., Graves, M.J., Schönlieb, C.B.: Compressed sensing plus motion (CS+M): a new perspective for improving undersampled MR image reconstruction. arXiv preprint arXiv:1810.10828 (2018)
- 11.Chun, S., Fessler, J.: Joint image reconstruction and nonrigid motion estimation with a simple penalty that encourages local invertibility. In: Proceedings of the SPIE, vol. 7258Google Scholar
- 22.Schumacher, H., Modersitzki, J., Fischer, B.: Combined reconstruction and motion correction in SPECT imaging. ITNS 56(1), 73–80 (2009)Google Scholar
- 25.de Vos, B.D., Berendsen, F.F., Viergever, M.A., Staring, M., Išgum, I.: End-to-end unsupervised deformable image registration with a convolutional neural network. In: Cardoso, M.J., et al. (eds.) DLMIA/ML-CDS -2017. LNCS, vol. 10553, pp. 204–212. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-67558-9_24CrossRefGoogle Scholar