Skip to main content

A Generative Framework for Predicting Myocardial Strain from Cine-Cardiac Magnetic Resonance Imaging

  • Conference paper
  • First Online:
Medical Image Understanding and Analysis (MIUA 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13413))

Included in the following conference series:

  • 2754 Accesses

Abstract

Myocardial strain is an important measure of cardiac performance, which can be altered when ejection fraction (EF) and other ventricular volumetric indices remain normal, providing an additional indicator for early detection of cardiac dysfunction. Cardiac tagging MRI is the gold standard for myocardial strain quantification but requires additional sequence acquisition and relatively complex post-processing procedures, which limit its clinical application. In this paper, we propose a framework for learning a joint latent representation of cine MRI and tagging MRI, such that tagging MRI can be synthesised and used to derive myocardial strain, given just cine MRI as inputs. Specifically, we use a multi-channel variational autoencoder to simultaneously learn features from tagging MRI and cine MRI, and project the information from these distinct channels into a common latent space to jointly analyse the multi-sequence data information. The inference process generates tagging MRI using only cine MRI as input, by conditionally sampling from the learned latent representation. Finally, automated tag tracking was performed using a cardiac motion tag tracking network on the generated tagging MRI, and myocardial strain was estimated. Experiments on the UK Biobank dataset show that our proposed framework can generate tagging images from cine images alone, and in turn, can be used to estimate myocardial strain effectively.

N. Ravikumar and A. F. Frangi—Joint last authors.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Ibrahim, E.-S.H.: Myocardial tagging by cardiovascular magnetic resonance: evolution of techniques–pulse sequences, analysis algorithms, and applications. J. Cardiovasc. Magn. Reson. 13(1), 1–40 (2011). https://doi.org/10.1186/1532-429X-13-36

  2. Sutherland, G.R., Di Salvo, G., Claus, P., D'hooge, J., Bijnens, B.: Strain and strain rate imaging: a new clinical approach to quantifying regional myocardial function. J. Am. Soc. Echocardiogr. 17(7), 788–802 (2004). https://doi.org/10.1016/j.echo.2004.03.027

  3. Wu, L., Germans, T., Güçlü, A., Heymans, M.W., Allaart, C.P., van Rossum, A.C.: Feature tracking compared with tissue tagging measurements of segmental strain by cardiovascular magnetic resonance. J. Cardiovasc. Magn. Reson. 16(1), 1–11 (2014). https://doi.org/10.1186/1532-429X-16-10

  4. Götte, M.J., Germans, T., Rüssel, I.K., Zwanenburg, J.J., Marcus, J.T., van Rossum, A.C., et al.: Myocardial strain and torsion quantified by cardiovascular magnetic resonance tissue tagging: studies in normal and impaired left ventricular function 48(10), 2002–2011 (2006). https://doi.org/10.1016/j.jacc.2006.07.048

  5. Guttman, M.A., Prince, J.L., McVeigh, E.R.: Tag and contour detection in tagged MR images of the left ventricle 13(1), 74–88 (1994). https://doi.org/10.1109/42.276146

  6. Young, A.A., Kraitchman, D.L., Dougherty, L., Axel, L.: Tracking and finite element analysis of stripe deformation in magnetic resonance tagging. IEEE Trans. Med. Imaging 14(3), 413–421 (1995). https://doi.org/10.1109/42.414605

  7. O’Shea, K., Nash, R.: An introduction to convolutional neural networks. arXiv preprint arXiv:1511.08458 (2015)

  8. Pu, Y., Gan, Z., Henao, R., Yuan, X., Li, C., Stevens, A., et al.: Variational autoencoder for deep learning of images, labels and captions. In: 29th Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain, p. 29 (2016). https://doi.org/10.48550/arXiv.1609.08976

  9. Antelmi, L., Ayache, N., Robert, P., Lorenzi, M.: Sparse multi-channel variational autoencoder for the joint analysis of heterogeneous data. In: International Conference on Machine Learning, Long Beach, California (2019)

    Google Scholar 

  10. Liu, X., Xing, F., Prince, J.L., Carass, A., Stone, M., El Fakhri, G., et al.: Dual-cycle constrained bijective VAE-GAN for tagged-to-cine magnetic resonance image synthesis. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), IEEE, France (2021). https://doi.org/10.1109/ISBI48211.2021.9433852

  11. Loecher, M., Hannum, A.J., Perotti, L.E., Ennis, D.B.: Arbitrary point tracking with machine learning to measure cardiac strains in tagged MRI. In: Ennis, D.B., Perotti, L.E., Wang, V.Y. (eds.) FIMH 2021. LNCS, vol. 12738, pp. 213–222. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-78710-3_21

    Chapter  Google Scholar 

  12. Biobank U: About uk biobank (2014)

    Google Scholar 

  13. Petersen, S.E., Matthews, P.M., Bamberg, F., Bluemke, D.A., Francis, J.M., Friedrich, M.G., et al.: Imaging in population science: cardiovascular magnetic resonance in 100,000 participants of UK Biobank-rationale, challenges and approaches 15(1), 1–10 (2013). https://doi.org/10.1186/1532-429X-15-46

  14. Zheng, Q., Delingette, H., Duchateau, N., Ayache, N.: 3-D consistent and robust segmentation of cardiac images by deep learning with spatial propagation. IEEE Trans. Med. Imaging 37(9), 2137–48 (2018). https://doi.org/10.48550/arXiv.1804.09400

  15. Loecher, M., Perotti, L.E., Ennis, D.B.: Using synthetic data generation to train a cardiac motion tag tracking neural network. Med. Image Anal. 74,1022–1023 (2021). https://doi.org/10.1016/j.media.2021.102223

  16. Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami. IEEE (2009). https://doi.org/10.1109/CVPR.2009.5206848

  17. Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, USA, pp. 6450–6459 (2018)

    Google Scholar 

  18. Liu, R., Lehman, J., Molino, P., Petroski Such, F., Frank, E., Sergeev, A., et al.: An intriguing failing of convolutional neural networks and the coordconv solution, 31 (2018)

    Google Scholar 

  19. Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: 5th International Conference on Learning Representations (ICLR 2016), Toulon, France (2016)

    Google Scholar 

  20. Prakash, K.B., Kanagachidambaresan, G.R. (eds.): Programming with TensorFlow. EICC, Springer, Cham (2021). https://doi.org/10.1007/978-3-030-57077-4

    Book  Google Scholar 

  21. Wang, W., Lu, Y.: Analysis of the mean absolute error (MAE) and the root mean square error (RMSE) in assessing rounding model. In: IOP Conference Series: Materials Science and Engineering. IOP Publishing, (2018). https://doi.org/10.1088/1757-899X/324/1/012049

  22. Dosselmann, R., Yang, X.D.: A comprehensive assessment of the structural similarity index. Signal Image Video Process. 5(1), 81–91 (2011). https://doi.org/10.1007/s11760-009-0144-1

  23. Poobathy, D., Chezian, R.M.: Edge detection operators: peak signal to noise ratio based comparison. IJ Image Graph. Signal Process. 10, 55–61 (2014). https://doi.org/10.5815/ijigsp.2014.10.07

  24. Bunce, C.: Correlation, agreement, and Bland–Altman analysis: statistical analysis of method comparison studies. Am. J. Ophthalmol. 148(1), 4–6 (2009). https://doi.org/10.1016/j.ajo.2008.09.032

  25. Young, A.A., Li, B., Kirton, R.S., Cowan, B.R.: Generalized spatiotemporal myocardial strain analysis for DENSE and SPAMM imaging. Magn. Reson. Med. 67(6), 1590–159 (2012). https://doi.org/10.1002/mrm.23142

Download references

Acknowledgements

This research was conducted using data from the UK Biobank under access application 11350. AFF is funded by the Royal Academy of Engineering (INSILEX CiET1819\19), Engineering and Physical Sciences Research Council (EPSRC) programs TUSCA EP/V04799X/1, and the Royal Society Exchange Programme CROSSLINK IES\NSFC\201380, and was supported partly by China Scholarship Council Studentship with the University of Leeds.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Nishant Ravikumar .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Cheng, N., Bonazzola, R., Ravikumar, N., Frangi, A.F. (2022). A Generative Framework for Predicting Myocardial Strain from Cine-Cardiac Magnetic Resonance Imaging. In: Yang, G., Aviles-Rivero, A., Roberts, M., Schönlieb, CB. (eds) Medical Image Understanding and Analysis. MIUA 2022. Lecture Notes in Computer Science, vol 13413. Springer, Cham. https://doi.org/10.1007/978-3-031-12053-4_36

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-12053-4_36

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-12052-7

  • Online ISBN: 978-3-031-12053-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics