Synthetic Echocardiographic Image Sequences for Cardiac Inverse Electro-Kinematic Learning

  • Adityo Prakosa
  • Maxime Sermesant
  • Hervé Delingette
  • Eric Saloux
  • Pascal Allain
  • Pascal Cathier
  • Patrick Etyngier
  • Nicolas Villain
  • Nicholas Ayache
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6891)

Abstract

In this paper, we propose to create a rich database of synthetic time series of 3D echocardiography (US) images using simulations of a cardiac electromechanical model, in order to study the relationship between electrical disorders and kinematic patterns visible in medical images. From a real 4D sequence, a software pipeline is applied to create several synthetic sequences by combining various steps including motion tracking and segmentation. We use here this synthetic database to train a machine learning algorithm which estimates the depolarization times of each cardiac segment from invariant kinematic descriptors such as local displacements or strains. First experiments on the inverse electro-kinematic learning are demonstrated on the synthetic 3D US database and are evaluated on clinical 3D US sequences from two patients with Left Bundle Branch Block.

Keywords

Root Mean Square Right Ventricle American Heart Association Left Bundle Branch Block Cardiac Motion 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Cawley, G.C.: Leave-one-out cross-validation based model selection criteria for weighted LS-SVMs. In: IJCNN 2006, pp. 1661–1668. IEEE, Vancouver (2006)Google Scholar
  2. 2.
    Duan, Q., Moireau, P., Angelini, E.D., Chapelle, D., Laine, A.F.: Simulation of 3D ultrasound with a realistic electro-mechanical model of the heart. In: Sachse, F.B., Seemann, G. (eds.) FIHM 2007. LNCS, vol. 4466, pp. 463–473. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  3. 3.
    Elen, A., Choi, H.F., Loeckx, D., Gao, H., Claus, P., Suetens, P., Maes, F., D’hooge, J.: Three-dimensional cardiac strain estimation using spatio-temporal elastic registration of ultrasound images: A feasibility study. IEEE Trans. Med. Imaging 27, 1580–1591 (2008)CrossRefGoogle Scholar
  4. 4.
    Mansi, T., Pennec, X., Sermesant, M., Delingette, H., Ayache, N.: iLogDemons: A demons-based registration algorithm for tracking incompressible elastic biological tissues. Int. J. of Comput. Vision 92, 92–111 (2011)CrossRefGoogle Scholar
  5. 5.
    Prakosa, A., Sermesant, M., Delingette, H., Saloux, E., Allain, P., Cathier, P., Etyngier, P., Villain, N., Ayache, N.: Non-invasive activation times estimation using 3D echocardiography. In: Camara, O., Pop, M., Rhode, K., Sermesant, M., Smith, N., Young, A. (eds.) STACOM 2010. LNCS, vol. 6364, pp. 212–221. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  6. 6.
    Provost, J., Lee, W., Fujikura, K., Konofagou, E.: Electromechanical wave imaging of normal and ischemic hearts in vivo. IEEE Trans. Med. Imaging 29, 625–635 (2010)CrossRefGoogle Scholar
  7. 7.
    Sanchez-Ortiz, G., Sermesant, M., Chandrashekara, R., Rhode, K., Razavi, R., Hill, D., Rueckert, D.: Detecting the onset of myocardial contraction for establishing inverse electro-mechanical coupling in XMR guided RF ablation. In: ISBI 2004, pp. 1055–1058. IEEE, Arlington (2004)Google Scholar
  8. 8.
    Sermesant, M., Delingette, H., Ayache, N.: An electromechanical model of the heart for image analysis and simulation. IEEE Trans. Med. Imaging 25, 612–625 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Adityo Prakosa
    • 1
  • Maxime Sermesant
    • 1
  • Hervé Delingette
    • 1
  • Eric Saloux
    • 2
  • Pascal Allain
    • 3
  • Pascal Cathier
    • 3
  • Patrick Etyngier
    • 3
  • Nicolas Villain
    • 3
  • Nicholas Ayache
    • 1
  1. 1.Asclepios Research ProjectINRIA Sophia-AntipolisFrance
  2. 2.Service de CardiologieCHU CaenFrance
  3. 3.MedisysPhilips Healthcare SuresnesFrance

Personalised recommendations