International Conference on Medical Image Computing and Computer-Assisted Intervention

MICCAI 2015: Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015 pp 442-449 | Cite as

Vito – A Generic Agent for Multi-physics Model Personalization: Application to Heart Modeling

  • Dominik Neumann
  • Tommaso Mansi
  • Lucian Itu
  • Bogdan Georgescu
  • Elham Kayvanpour
  • Farbod Sedaghat-Hamedani
  • Jan Haas
  • Hugo Katus
  • Benjamin Meder
  • Stefan Steidl
  • Joachim Hornegger
  • Dorin Comaniciu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9350)

Abstract

Precise estimation of computational physiological model parameters from patient data is one of the main hurdles towards their clinical applicability. Designing robust estimation algorithms is often a tedious and model-specific process. We propose to use, for the first time to our knowledge, artificial intelligence (AI) concepts to learn how to personalize a computational model, inspired by how an expert manually personalizes. We reformulate the parameter estimation problem in terms of Markov decision process and reinforcement learning. In an off-line phase, the artificial agent, called Vito, automatically learns a representative state-action-state model through data-driven exploration of the computational model under consideration. In other words, Vito learns how the model behaves under change of parameters and how to personalize it. Vito then controls the on-line personalization by exploiting its automatically derived action policy. Because the algorithm is model-independent, personalizing a completely new model would require only adjusting some simple parameters of the agent and defining the observations to match, without the full knowledge of the model itself. Vito was evaluated on two challenging problems: the inverse problem of cardiac electrophysiology and the personalization of a lumped-parameter whole-body circulation model. Obtained results suggested that Vito could achieve equivalent goodness of fit than standard methods, while being more robust (up to 25% higher success rates) and with faster (up to three times) convergence rate. Our AI approach could thus make model personalization algorithms generalizable and self-adaptable to any patient, like a human operator.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Trayanova, N.A.: Whole-heart modeling applications to cardiac electrophysiology and electromechanics. Circulation Research 108(1), 113–128 (2011)CrossRefGoogle Scholar
  2. 2.
    Nordsletten, D., Niederer, S., Nash, M., Hunter, P., Smith, N.: Coupling multi-physics models to cardiac mechanics. PBMB 104(1), 77–88 (2011)Google Scholar
  3. 3.
    Wallman, M., Smith, N.P., Rodriguez, B.: Computational methods to reduce uncertainty in the estimation of cardiac conduction properties from electroanatomical recordings. Med. Image Anal. 18(1), 228–240 (2014)CrossRefGoogle Scholar
  4. 4.
    Wong, K.C., Sermesant, M., Rhode, K., Ginks, M., Rinaldi, C.A., Razavi, R., Delingette, H., Ayache, N.: Velocity-based cardiac contractility personalization from images using derivative-free optimization. J. Mech. Behav. Biomed. 43 (2015)Google Scholar
  5. 5.
    Seegerer, P., et al.: Estimation of regional electrical properties of the heart from 12-lead ECG and images. In: Camara, O., Mansi, T., Pop, M., Rhode, K., Sermesant, M., Young, A. (eds.) STACOM 2014. LNCS, vol. 8896, pp. 204–212. Springer, Heidelberg (2015)Google Scholar
  6. 6.
    Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press (1998)Google Scholar
  7. 7.
    Kveton, B., Theocharous, G.: Kernel-based reinforcement learning on representative states. In: Association for the Advancement of Artificial Intelligence (2012)Google Scholar
  8. 8.
    Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)CrossRefGoogle Scholar
  9. 9.
    Neumann, D., et al.: Robust image-based estimation of cardiac tissue parameters and their uncertainty from noisy data. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014, Part II. LNCS, vol. 8674, pp. 9–16. Springer, Heidelberg (2014)Google Scholar
  10. 10.
    Wallman, M., Smith, N.P., Rodriguez, B.: A comparative study of graph-based, eikonal, and monodomain simulations for the estimation of cardiac activation times. IEEE Transactions on Biomedical Engineering 59(6), 1739–1748 (2012)CrossRefGoogle Scholar
  11. 11.
    Zettinig, O., Mansi, T., Neumann, D., Georgescu, B., Rapaka, S., Seegerer, P., Kayvanpour, E., Sedaghat-Hamedani, F., Amr, A., Haas, J., Steen, H., Meder, B., Navab, N., Kamen, A., Comaniciu, D.: Data-driven estimation of cardiac electrical diffusivity from 12-lead ECG signals. Med. Image Anal. 18(8), 1361–1376 (2014)CrossRefGoogle Scholar
  12. 12.
    Itu, L., Sharma, P., Georgescu, B., Kamen, A., Suciu, C., Comaniciu, D.: Model based non-invasive estimation of PV loop from echocardiography. In: Engineering in Medicine and Biology Society (EMBC), pp. 6774–6777 (2014)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Dominik Neumann
    • 1
    • 2
  • Tommaso Mansi
    • 1
  • Lucian Itu
    • 3
  • Bogdan Georgescu
    • 1
  • Elham Kayvanpour
    • 4
  • Farbod Sedaghat-Hamedani
    • 4
  • Jan Haas
    • 4
  • Hugo Katus
    • 4
  • Benjamin Meder
    • 4
  • Stefan Steidl
    • 2
  • Joachim Hornegger
    • 2
  • Dorin Comaniciu
    • 1
  1. 1.Imaging and Computer VisionSiemens Corporate TechnologyPrincetonUSA
  2. 2.Pattern Recognition LabFAU Erlangen-NürnbergErlangenGermany
  3. 3.Imaging and Computer VisionSiemens Corporate TechnologyChennaiRomania
  4. 4.Department of Internal Medicine IIIUniversity Hospital HeidelbergHeidelbergGermany

Personalised recommendations