Skip to main content

Deep Video Networks for Automatic Assessment of Aortic Stenosis in Echocardiography

  • 1221 Accesses

Part of the Lecture Notes in Computer Science book series (LNIP,volume 12967)

Abstract

Aortic valve stenosis (AS) is the narrowing of the heart’s aortic valve opening, which restricts blood flow from the left ventricle to the aorta. Accurate diagnosis and timely intervention of AS are crucial since the mortality rate of this condition rapidly increases as symptoms begin to develop. Automated AS estimation in echocardiography faces several challenges, including generalization from diverse medical data, access to high-quality Doppler imaging, and noisy training labels. In this paper, we propose a method for automatic Aortic Stenosis assessment in echocardiography, which is, to the best of our knowledge, the first deep learning pipeline to automate the identification and grading of AS using cardiac ultrasound. Trained and evaluated on a large dataset of 9,117 echocardiograms obtained from 2,247 patients, our method achieves a mean \(F_1\) score of 96.5% for the identification of AS and a mean \(F_1\) score of 73% for grading AS. We use a multi-task training scheme to predict AS severity and key parameters used in clinical AS assessment along with their aleatoric uncertainties. Compared to a baseline that only predicts AS severity, our results show that our multi-task uncertainty-aware inference method achieves comparable classification performance while improving the ability to detect out-of-distribution examples. This is crucial for the clinical deployment of our method in point-of-care settings, where ultrasound operators have less experience in acquiring high-quality echocardiograms.

Keywords

  • Deep learning
  • Echocardiography
  • Ultrasound
  • Uncertainty estimation
  • Multi-task learning
  • Point-of-care

T. Ginsberg, R. Tal and M. Tsang—Joint first authors.

P. Abolmaesumi and T. Tsang—Joint senior authors.

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-87583-1_20
  • Chapter length: 9 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   54.99
Price excludes VAT (USA)
  • ISBN: 978-3-030-87583-1
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   69.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.

References

  1. Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? (2021)

    Google Scholar 

  2. Brown, M.L., et al.: The benefits of early valve replacement in asymptomatic patients with severe aortic stenosis. J. Thorac. Cardiovasc. Surg. 135(2), 308–315 (2008)

    CrossRef  Google Scholar 

  3. Carabello, B.A., Paulus, W.J.: Aortic stenosis. Lancet 373(9667), 956–966 (2009)

    CrossRef  Google Scholar 

  4. Caruana, R.: Multitask learning. Learning to Learn, pp. 95–133 (1998)

    Google Scholar 

  5. Chen, C., et al.: Deep learning for cardiac image segmentation: a review. Front. Cardiovasc. Med. 7, 25 (2020)

    CrossRef  Google Scholar 

  6. Clavel, M.A., et al.: The complex nature of discordant severe calcified aortic valve disease grading: new insights from combined doppler echocardiographic and computed tomographic study. J. Am. Coll. Cardiol. 62(24), 2329–2338 (2013)

    CrossRef  Google Scholar 

  7. Crawshaw, M.: Multi-task learning with deep neural networks: a survey (2020)

    Google Scholar 

  8. Czarnecki, A., et al.: Trends in the incidence and outcomes of patients with aortic stenosis hospitalization. Am. Heart J. 199, 144–149 (2018)

    CrossRef  Google Scholar 

  9. Dezaki, F.T., et al.: Echo-SyncNet: self-supervised cardiac view synchronization in echocardiography. IEEE Trans. Med. Imag. 40, 2092–2104 (2021). https://doi.org/10.1109/TMI.2021.3071951

    CrossRef  Google Scholar 

  10. Kazemi Esfeh, M.M., Luong, C., Behnami, D., Tsang, T., Abolmaesumi, P.: A deep Bayesian video analysis framework: towards a more robust estimation of ejection fraction. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12262, pp. 582–590. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59713-9_56

    CrossRef  Google Scholar 

  11. Fort, S., Hu, H., Lakshminarayanan, B.: Deep ensembles: a loss landscape perspective (2020)

    Google Scholar 

  12. Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning (2016)

    Google Scholar 

  13. Jafari, M.H., et al.: U-LanD: uncertainty-driven video landmark detection (2021)

    Google Scholar 

  14. Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? CoRR abs/1703.04977 (2017)

    Google Scholar 

  15. Liao, Z., et al.: On modelling label uncertainty in deep neural networks: automatic estimation of intra-observer variability in 2d echocardiography quality assessment (2019)

    Google Scholar 

  16. Mitros, J., Namee, B.M.: On the validity of Bayesian neural networks for uncertainty estimation (2019)

    Google Scholar 

  17. Ouyang, D., et al.: Video-based AI for beat-to-beat assessment of cardiac function. Nature 580(7802), 252–256 (2020)

    CrossRef  Google Scholar 

  18. Ruder, S.: An overview of multi-task learning in deep neural networks (2017)

    Google Scholar 

  19. Strange, G., et al.: Poor long-term survival in patients with moderate aortic stenosis. J. Am. Coll. Cardiol. 74(15), 1851–1863 (2019)

    CrossRef  Google Scholar 

  20. Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition (2018)

    Google Scholar 

  21. Wang, G., Li, W., Aertsen, M., Deprest, J., Ourselin, S., Vercauteren, T.: Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks. Neurocomputing 338, 34–45 (2019)

    CrossRef  Google Scholar 

  22. Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks (2018)

    Google Scholar 

  23. Wu, S., Zhang, H.R., Ré, C.: Understanding and improving information transfer in multi-task learning. arXiv e-prints arXiv:2005.00944, May 2020

  24. Zamir, A., Sax, A., Shen, W., Guibas, L., Malik, J., Savarese, S.: Taskonomy: disentangling task transfer learning (2018)

    Google Scholar 

  25. Zamzmi, G., Rajaraman, S., Antani, S.: UMS-Rep: unified modality-specific representation for efficient medical image analysis. Inform. Med. Unlocked 24, 100571 (2021). https://doi.org/10.1016/j.imu.2021.100571. https://www.sciencedirect.com/science/article/pii/S2352914821000617

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Tom Ginsberg .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Ginsberg, T. et al. (2021). Deep Video Networks for Automatic Assessment of Aortic Stenosis in Echocardiography. In: Noble, J.A., Aylward, S., Grimwood, A., Min, Z., Lee, SL., Hu, Y. (eds) Simplifying Medical Ultrasound. ASMUS 2021. Lecture Notes in Computer Science(), vol 12967. Springer, Cham. https://doi.org/10.1007/978-3-030-87583-1_20

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-87583-1_20

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-87582-4

  • Online ISBN: 978-3-030-87583-1

  • eBook Packages: Computer ScienceComputer Science (R0)