Advertisement

Learning-Based Spatiotemporal Regularization and Integration of Tracking Methods for Regional 4D Cardiac Deformation Analysis

  • Allen LuEmail author
  • Maria Zontak
  • Nripesh Parajuli
  • John C. Stendahl
  • Nabil Boutagy
  • Melissa Eberle
  • Imran Alkhalil
  • Matthew O’Donnell
  • Albert J. Sinusas
  • James S. Duncan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10434)

Abstract

Dense cardiac motion tracking and deformation analysis from echocardiography is important for detection and localization of myocardial dysfunction. However, tracking methods are often unreliable due to inherent ultrasound imaging properties. In this work, we propose a new data-driven spatiotemporal regularization strategy. We generate 4D Lagrangian displacement patches from different input sources as training data and learn the regularization procedure via a multi-layered perceptron (MLP) network. The learned regularization procedure is applied to initial noisy tracking results. We further propose a framework for integrating tracking methods to produce better overall estimations. We demonstrate the utility of this approach on block-matching, surface tracking, and free-form deformation-based methods. Finally, we quantitatively and qualitatively evaluate our performance on both tracking and strain accuracy using both synthetic and in vivo data.

Notes

Acknowledgment

This work was supported by the National Institute of Health (NIH) grant number R01HL121226.

References

  1. 1.
    Chen, X., Xie, H., Erkamp, R., Kim, K., Jia, C., Rubin, J., O’Donnell, M.: 3-D correlation-based speckle tracking. Ultrason. Imaging 27(1), 21–36 (2005)CrossRefGoogle Scholar
  2. 2.
    Alessandrini, M., Liebgott, H., Barbosa, D., Bernard, O.: Monogenic phase based optical flow computation for myocardial motion analysis in 3D echocardiography. In: Camara, O., Mansi, T., Pop, M., Rhode, K., Sermesant, M., Young, A. (eds.) STACOM 2012. LNCS, vol. 7746, pp. 159–168. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-36961-2_19CrossRefGoogle Scholar
  3. 3.
    Ledesma-Carbayo, M.J., Kybic, J., Desco, M., Santos, A., Suhling, M., Hunziker, P., Unser, M.: Spatio-temporal nonrigid registration for ultrasound cardiac motion estimation. IEEE Trans. Med. Imaging 24(9), 1113–1126 (2005)CrossRefGoogle Scholar
  4. 4.
    De Craene, M., Piella, G., Camara, O., Duchateau, N., Silva, E., Doltra, A., Dhooge, J., Brugada, J., Sitges, M., Frangi, A.F.: Temporal diffeomorphic free-form deformation: application to motion and strain estimation from 3D echocardiography. Med. Image Anal. 16(2), 427–450 (2012)CrossRefGoogle Scholar
  5. 5.
    Lu, A., Zontak, M., Parajuli, N., Stendahl, J.C., Boutagy, N., Eberle, M., ODonnell, M., Sinusas, A.J., Duncan, J.S.: Dictionary learning-based spatiotemporal regularization for 3D dense speckle tracking. In: SPIE Medical Imaging, International Society for Optics and Photonics, p. 1013904 (2017)Google Scholar
  6. 6.
    Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2(5), 359–366 (1989)CrossRefGoogle Scholar
  7. 7.
    Rueckert, D., Sonoda, L.I., Hayes, C., Hill, D.L., Leach, M.O., Hawkes, D.J.: Nonrigid registration using free-form deformations: application to breast MR images. IEEE Trans. Med. Imaging 18(8), 712–721 (1999)CrossRefGoogle Scholar
  8. 8.
    Parajuli, N., Lu, A., Stendahl, J.C., Zontak, M., Boutagy, N., Eberle, M., Alkhalil, I., ODonnell, M., Sinusas, A.J., Duncan, J.S.: Flow network based cardiac motion tracking leveraging learned feature matching. In: International Conference on Medical Image Computing and Computer-Assisted Intervention (2017)Google Scholar
  9. 9.
    Sun, S.: A survey of multi-view machine learning. Neural Comput. Appl. 23(7–8), 2031–2038 (2013)CrossRefGoogle Scholar
  10. 10.
    Alessandrini, M., De Craene, M., Bernard, O., Giffard-Roisin, S., Allain, P., Waechter-Stehle, I., Weese, J., Saloux, E., Delingette, H., et al.: A pipeline for the generation of realistic 3D synthetic echocardiographic sequences: methodology and open-access database. IEEE Trans. Med. Imaging. 34(7), 1436–1451 (2015)CrossRefGoogle Scholar
  11. 11.
    Alessandrini, M., Heyde, B., Queirós, S., Cygan, S., Zontak, M., Somphone, O., Bernard, O., Sermesant, M., Delingette, H., Barbosa, D., et al.: Detailed evaluation of five 3D speckle tracking algorithms using synthetic echocardiographic recordings. IEEE Trans. Med. Imaging 35(8), 1915–1926 (2016)CrossRefGoogle Scholar
  12. 12.
    Parajuli, N., Compas, C.B., Lin, B.A., Sampath, S., O’Donnell, M., Sinusas, A.J., Duncan, J.S.: Sparsity and biomechanics inspired integration of shape and speckle tracking for cardiac deformation analysis. In: van Assen, H., Bovendeerd, P., Delhaas, T. (eds.) FIMH 2015. LNCS, vol. 9126, pp. 57–64. Springer, Cham (2015). doi: 10.1007/978-3-319-20309-6_7CrossRefGoogle Scholar
  13. 13.
    He, R., Hu, B., Yuan, X., Wang, L.: Robust Recognition via Information Theoretic Learning. SCS. Springer, Cham (2014)CrossRefGoogle Scholar
  14. 14.
    Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Allen Lu
    • 1
    Email author
  • Maria Zontak
    • 6
  • Nripesh Parajuli
    • 2
  • John C. Stendahl
    • 3
  • Nabil Boutagy
    • 3
  • Melissa Eberle
    • 3
  • Imran Alkhalil
    • 3
  • Matthew O’Donnell
    • 5
  • Albert J. Sinusas
    • 3
    • 4
  • James S. Duncan
    • 1
    • 2
    • 4
  1. 1.Department of Biomedical EngineeringYale UniversityNew HavenUSA
  2. 2.Department of Electrical EngineeringYale UniversityNew HavenUSA
  3. 3.Department of Internal MedicineYale UniversityNew HavenUSA
  4. 4.Department of Radiology and Biomedical ImagingYale UniversityNew HavenUSA
  5. 5.Department of BioengineeringUniversity of WashingtonSeattleUSA
  6. 6.College of Computer and Information ScienceNortheastern UniversitySeattleUSA

Personalised recommendations