Abstract
We propose a multiscale spatio-temporal graph convolutional network (MST-GCN) approach to learn the left ventricular (LV) motion patterns from cardiac MR image sequences. The MST-GCN follows an encoder-decoder framework. The encoder uses a sequence of multiscale graph computation units (MGCUs). The myocardial geometry is represented as a graph. The network models the internal relations of the graph nodes via feature extraction at different scales and fuses the feature across scales to form a global representation of the input cardiac motion. Based on this, the decoder employs a graph-based gated recurrent unit (G-GRU) to predict future cardiac motion. We show that the MST-GCN can automatically quantify the spatio-temporal patterns in cardiac MR that characterise cardiac motion. Experiments are performed on mid-ventricular short-axis view cardiac MR image sequence from the UK Biobank dataset. We compare the performance of cardiac motion prediction of the proposed method with ten different architectures and parameter settings. Experiments show that the proposed method inputting node positions and node velocities with multiscale graphs achieves the best performance with a mean squared error of 0.25 pixel between the ground truth node locations and our prediction. We also show that the proposed method can estimate a number of motion-related metrics, including endocardial radii, thickness and strain which are useful for regional LV function assessment.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
UK BioBank. https://www.ukbiobank.ac.uk/.
References
Bai, W., et al.: Automated cardiovascular magnetic resonance image analysis with fully convolutional networks. JCMR 20(1), 65 (2018)
Cerqueira, M.D., et al.: Standardized myocardial segmentation and nomenclature for tomographic imaging of the heart: a statement for healthcare professionals from the cardiac imaging committee of the council on clinical cardiology of the american heart association. Circulation 105(4), 539–542 (2002)
Lang, Y., et al.: Automatic localization of landmarks in craniomaxillofacial CBCT Images using a local attention-based graph convolution network. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12264, pp. 817–826. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59719-1_79
Li, M., et al.: Dynamic multiscale graph neural networks for 3d skeleton based human motion prediction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 214–223 (2020)
Lu, P., et al: Dynamic spatio-temporal graph convolutional networks for cardiac motion analysis. In: ISBI 2021, pp. 122-125. IEEE (2021)
Lu, P., Bai, W., Rueckert, D., Noble, J.A.: Modelling cardiac motion via spatio-temporal graph convolutional networks to boost the diagnosis of heart conditions. In: Puyol Anton, E., Pop, M., Sermesant, M., Campello, V., Lalande, A., Lekadir, K., Suinesiaputra, A., Camara, O., Young, A. (eds.) STACOM 2020. LNCS, vol. 12592, pp. 56–65. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-68107-4_6
Lu, P., Qiu, H., Qin, C., Bai, W., Rueckert, D., Noble, J.A.: Going deeper into cardiac motion analysis to model fine spatio-temporal features. In: Papież, B.W., Namburete, A.I.L., Yaqub, M., Noble, J.A. (eds.) MIUA 2020. CCIS, vol. 1248, pp. 294–306. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-52791-4_23
Noh, K.J., Park, S.J., Lee, S.: Combining fundus images and fluorescein angiography for artery/vein classification using the hierarchical vessel graph network. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12265, pp. 595–605. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59722-1_57
Qin, C., et al.: Joint learning of motion estimation and segmentation for cardiac MR image sequences. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11071, pp. 472–480. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00934-2_53
Yan, S., et al.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-second AAAI conference on artificial intelligence (2018)
Zheng, Q., et al.: Explainable cardiac pathology classification on cine MRI with motion characterization by semi-supervised learning of apparent flow. Medical image analysis (2019)
Acknowledgements
This work is supported by SmartHeart. EPSRC grant EP/P001009/1. This study used data from the UK Biobank Resource under Application Number 40119. The authors declare no conflicts of interest related to this research study.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Lu, P., Bai, W., Rueckert, D., Noble, J.A. (2021). Multiscale Graph Convolutional Networks for Cardiac Motion Analysis. In: Ennis, D.B., Perotti, L.E., Wang, V.Y. (eds) Functional Imaging and Modeling of the Heart. FIMH 2021. Lecture Notes in Computer Science(), vol 12738. Springer, Cham. https://doi.org/10.1007/978-3-030-78710-3_26
Download citation
DOI: https://doi.org/10.1007/978-3-030-78710-3_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-78709-7
Online ISBN: 978-3-030-78710-3
eBook Packages: Computer ScienceComputer Science (R0)