Advertisement

Automatic Myocardial Strain Imaging in Echocardiography Using Deep Learning

  • Andreas Østvik
  • Erik Smistad
  • Torvald Espeland
  • Erik Andreas Rye Berg
  • Lasse Lovstakken
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11045)

Abstract

Recent studies in the field of deep learning suggest that motion estimation can be treated as a learnable problem. In this paper we propose a pipeline for functional imaging in echocardiography consisting of four central components, (i) classification of cardiac view, (ii) semantic partitioning of the left ventricle (LV) myocardium, (iii) regional motion estimates and (iv) fusion of measurements. A U-Net type of convolutional neural network (CNN) was developed to classify muscle tissue, and partitioned into a semantic measurement kernel based on LV length and ventricular orientation. Dense tissue motion was predicted using stacked U-Net architectures with image warping of intermediate flow, designed to tackle variable displacements. Training was performed on a mixture of real and synthetic data. The resulting segmentation and motion estimates was fused in a Kalman filter and used as basis for measuring global longitudinal strain. For reference, 2D ultrasound images from 21 subjects were acquired using a GE Vivid system. Data was analyzed by two specialists using a semi-automatic tool for longitudinal function estimates in a commercial system, and further compared to output of the proposed method. Qualitative assessment showed comparable deformation trends as the clinical analysis software. The average deviation for the global longitudinal strain was (\(-0.6\pm 1.6\))% for apical four-chamber view. The system was implemented with Tensorflow, and working in an end-to-end fashion without any ad-hoc tuning. Using a modern graphics processing unit, the average inference time is estimated to (\(115\pm 3\)) ms per frame.

Keywords

Deep learning Echocardiography Functional imaging 

References

  1. 1.
    Abadi, M., et al.: Tensorflow: a system for large-scale machine learning. OSDI 16, 265–283 (2016)Google Scholar
  2. 2.
    Bernard, O., et al.: Standardized evaluation system for left ventricular segmentation algorithms in 3D echocardiography. IEEE Trans. Med. Imaging 35(4), 967–977 (2016).  https://doi.org/10.1109/TMI.2015.2503890CrossRefGoogle Scholar
  3. 3.
    Dalen, H., et al.: Segmental and global longitudinal strain and strain rate based on echocardiography of 1266 healthy individuals: the hunt study in Norway. Eur. J. Echocardiogr. 11(2), 176–183 (2009)Google Scholar
  4. 4.
    Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2758–2766 (2015)Google Scholar
  5. 5.
    Farsalinos, K.E., Daraban, A.M., Ünlü, S., Thomas, J.D., Badano, L.P., Voigt, J.U.: Head-to-head comparison of global longitudinal strain measurements among nine different vendors: the EACVI/ASE inter-vendor comparison study. J. Am. Soc. Echocardiogr. 28(10), 1171–1181 (2015)CrossRefGoogle Scholar
  6. 6.
    Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  7. 7.
    Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: FlowNet 2.0: evolution of optical flow estimation with deep networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017. http://lmb.informatik.uni-freiburg.de//Publications/2017/IMKDB17
  8. 8.
    Kalman, R.E.: A new approach to linear filtering and prediction problems. J. Basic Eng. 82(1), 35–45 (1960)CrossRefGoogle Scholar
  9. 9.
    Madani, A., Arnaout, R., Mofrad, M., Arnaout, R.: Fast and accurate view classification of echocardiograms using deep learning. npj Digit. Med. 1(1), 6 (2018)Google Scholar
  10. 10.
    Mayer, N., et al.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4040–4048 (2016)Google Scholar
  11. 11.
    Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar
  12. 12.
    Smiseth, O.A., Torp, H., Opdahl, A., Haugaa, K.H., Urheim, S.: Myocardial strain imaging: how useful is it in clinical decision making? Eur. Heart J. 37(15), 1196–1207 (2016).  https://doi.org/10.1093/eurheartj/ehv529CrossRefGoogle Scholar
  13. 13.
    Smistad, E., Østvik, A., Haugen, B.O., Lovstakken, L.: 2D left ventricle segmentation using deep learning. In: 2017 IEEE International Ultrasonics Symposium (IUS), pp. 1–4. IEEE (2017)Google Scholar
  14. 14.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Andreas Østvik
    • 1
    • 2
    • 3
  • Erik Smistad
    • 1
    • 2
    • 3
  • Torvald Espeland
    • 1
    • 2
    • 4
  • Erik Andreas Rye Berg
    • 1
    • 2
    • 4
  • Lasse Lovstakken
    • 1
    • 2
  1. 1.Centre for Innovative Ultrasound SolutionsNTNUTrondheimNorway
  2. 2.Department of Circulation and Medical ImagingNTNUTrondheimNorway
  3. 3.Department of HealthSINTEF DigitalTrondheimNorway
  4. 4.Clinic of CardiologySt. Olavs HospitalTrondheimNorway

Personalised recommendations