Advertisement

Quality Assessment of Echocardiographic Cine Using Recurrent Neural Networks: Feasibility on Five Standard View Planes

  • Amir H. AbdiEmail author
  • Christina Luong
  • Teresa Tsang
  • John Jue
  • Ken Gin
  • Darwin Yeung
  • Dale Hawley
  • Robert Rohling
  • Purang Abolmaesumi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10435)

Abstract

Echocardiography (echo) is a clinical imaging technique which is highly dependent on operator experience. We aim to reduce operator variability in data acquisition by automatically computing an echo quality score for real-time feedback. We achieve this with a deep neural network model, with convolutional layers to extract hierarchical features from the input echo cine and recurrent layers to leverage the sequential information in the echo cine loop. Using data from 509 separate patient studies, containing 2,450 echo cines across five standard echo imaging planes, we achieved a mean quality score accuracy of 85\(\%\) compared to the gold-standard score assigned by experienced echosonographers. The proposed approach calculates the quality of a given 20 frame echo sequence within 10 ms, sufficient for real-time deployment.

Keywords

Convolutional Recurrent Neural Network LSTM Deep learning Quality assessment Echocardiography Echo cine loop 

References

  1. 1.
    Abdi, A.H., et al.: Automatic quality assessment of apical four-chamber echocardiograms using deep convolutional neural networks. In: Proceedings of SPIE, vol. 10133, pp. 101330S–101330S-7 (2017)Google Scholar
  2. 2.
    Chen, H., Zheng, Y., Park, J.-H., Heng, P.-A., Zhou, S.K.: Iterative Multi-domain Regularized Deep Learning for Anatomical Structure Detection and Segmentation from Ultrasound Images. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 487–495. Springer, Cham (2016). doi: 10.1007/978-3-319-46723-8_56 CrossRefGoogle Scholar
  3. 3.
    Chollet, F.: Keras (2015). https://github.com/fchollet/keras
  4. 4.
    Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 677–691 (2017)CrossRefGoogle Scholar
  5. 5.
    El-Zehiry, N., Yan, M., Good, S., Fang, T., Zhou, S.K., Grady, L.: Learning the manifold of quality ultrasound acquisition. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013. LNCS, vol. 8149, pp. 122–130. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-40811-3_16 CrossRefGoogle Scholar
  6. 6.
    Gaudet, J., et al.: Focused critical care echocardiography: development and evaluation of an image acquisition assessment tool. Crit. Care Med. 44(6), e329–e335 (2016)CrossRefGoogle Scholar
  7. 7.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  8. 8.
    Huang, S.W., et al.: Detection and display of acoustic window for guiding and training cardiac ultrasound users. In: Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 9040, p. 904014 (2014)Google Scholar
  9. 9.
    Kingma, D.P., Ba, J.L.: Adam: a Method for Stochastic Optimization. In: International Conference on Learning Representations 2015, pp. 1–15 (2015)Google Scholar
  10. 10.
    Løvstakken, L., et al.: Real-time indication of acoustic window for phased-array transducers in ultrasound imaging. In: Proceedings of IEEE Ultrasonics Symposium, pp. 1549–1552 (2007)Google Scholar
  11. 11.
    Pavani, S.K., et al.: Quality metric for parasternal long axis B-mode echocardiograms. MICCAI 2015, 478–485 (2012)Google Scholar
  12. 12.
    Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. In: ICRL 2015, pp. 1–14 (2015)Google Scholar
  13. 13.
    Snare, S.R., et al.: Real-time scan assistant for echocardiography. IEEE Trans. Ultrason. Ferroelectr. Freq. Control 59(3), 583–589 (2012)CrossRefGoogle Scholar
  14. 14.
    Zhao, P., Zhang, T.: Accelerating minibatch stochastic gradient descent using stratified sampling. arXiv preprint arXiv:1405.3080, pp. 1–13 (2014)

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Amir H. Abdi
    • 1
    Email author
  • Christina Luong
    • 2
  • Teresa Tsang
    • 2
  • John Jue
    • 2
  • Ken Gin
    • 2
  • Darwin Yeung
    • 2
  • Dale Hawley
    • 2
  • Robert Rohling
    • 1
  • Purang Abolmaesumi
    • 1
  1. 1.Electrical and Computer Engineering DepartmentUniversity of British ColumbiaVancouverCanada
  2. 2.Cardiology LabVancouver General HospitalVancouverCanada

Personalised recommendations