A Generative Approach for Image-Based Modeling of Tumor Growth

  • Bjoern H. Menze
  • Koen Van Leemput
  • Antti Honkela
  • Ender Konukoglu
  • Marc-André Weber
  • Nicholas Ayache
  • Polina Golland
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6801)


Extensive imaging is routinely used in brain tumor patients to monitor the state of the disease and to evaluate therapeutic options. A large number of multi-modal and multi-temporal image volumes is acquired in standard clinical cases, requiring new approaches for comprehensive integration of information from different image sources and different time points. In this work we propose a joint generative model of tumor growth and of image observation that naturally handles multi-modal and longitudinal data. We use the model for analyzing imaging data in patients with glioma. The tumor growth model is based on a reaction-diffusion framework. Model personalization relies only on a forward model for the growth process and on image likelihood. We take advantage of an adaptive sparse grid approximation for efficient inference via Markov Chain Monte Carlo sampling. The approach can be used for integrating information from different multi-modal imaging protocols and can easily be adapted to other tumor growth models.


Markov Chain Monte Carlo Sparse Grid Markov Chain Monte Carlo Sampling Magnetic Resonance Spectroscopic Image Tumor Segmentation 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Alvord, E.C., Swanson, K.R.: Using mathematical modeling to predict survival of low-grade gliomas. Ann. Neurol. 61, 496–497 (2007)CrossRefGoogle Scholar
  2. 2.
    Cuadra, B.B., Pollo, C., Bardera, A., Cuisenaire, O., Thiran, J.P.: Atlas-based segmentation of pathological brain MR images using a model of lesion growth. IEEE TMI 23, 1301–1314 (2004)Google Scholar
  3. 3.
    Bungartz, H.-J., Griebel, M.: Sparse grids. Acta Numerica 13, 147–269 (2004)MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    Caseiras, G.B., Ciccarelli, O., Altmann, D.R., Benton, C.E., Tozer, D.J., Tofts, P.S., Yousry, T.A., Rees, J., Waldman, A.D., Jäger, H.R.: Low-grade gliomas: six-month tumor growth predicts patient outcome better than admission tumor volume, relative cerebral blood volume, and apparent diffusion coefficient. Radiology 253, 505–512 (2009)CrossRefGoogle Scholar
  5. 5.
    Chaplain, M.A.J., Stuart, A.M.: A mathematical model for the diffusion of tumour angiogenesis factor into the surrounding host tissue. J. Math. Appl. Med. Biol. 8, 191–220 (1991)CrossRefzbMATHGoogle Scholar
  6. 6.
    Clatz, O., Sermesant, M., Bondiau, P.-Y., Delingette, H., Warfield, S.K., Malandain, G., Ayache, N.: Realistic simulation of the 3-D growth of brain tumors in MR images coupling diffusion with biomechanical deformation. IEEE TMI 24, 1334–1346 (2005)Google Scholar
  7. 7.
    Cobzas, D., Mosayebi, P., Murtha, A., Jagersand, M.: Tumor invasion margin on the riemannian space of brain fibers. In: Yang, G.-Z., Hawkes, D., Rueckert, D., Noble, A., Taylor, C. (eds.) MICCAI 2009. LNCS, vol. 5762, pp. 531–539. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  8. 8.
    Corso, J.J., Sharon, E., Dube, S., El-Saden, S., Sinha, U., Yuille, A.: Efficient multilevel brain tumor segmentation with integrated Bayesian model classification. IEEE TMI 9, 629–640 (2008)Google Scholar
  9. 9.
    Ganslandt, O., Stadlbauer, A., Fahlbusch, R., Kamada, K., Buslei, R., Blumcke, I., Moser, E., Nimsky, C.: 1H-MRSI integrated into image-guided surgery: correlation to standard MR imaging and tumor cell density. Neurosurg. 56, 291–298 (2005)Google Scholar
  10. 10.
    Gooya, A., Biros, G., Davatzikos, C.: Deformable registration of glioma images using EM algorithm and diffusion reaction modeling. IEEE TMI 30, 375–390 (2011)Google Scholar
  11. 11.
    Haario, H., Laine, M., Mira, A., Saksman, E.: DRAM: Efficient adaptive MCMC. Statistics and Computing 16, 339–354 (2006)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Hamamci, A., Unal, G., Kucuk, N., Engin, K.: Cellular automata segmentation of brain tumors on post contrast MR images. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010. LNCS, vol. 6363, pp. 137–146. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  13. 13.
    Hirsch, S., Szczerba, D., Lloyd, B., Bajka, M., Kuster, N., Székely, G.: A mechano-chemical model of a solid tumor for therapy outcome predictions. In: Allen, G., Nabrzyski, J., Seidel, E., van Albada, G.D., Dongarra, J., Sloot, P.M.A. (eds.) ICCS 2009. LNCS, vol. 5544, pp. 715–724. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  14. 14.
    Hogea, C., Davatzikos, C., Biros, G.: An image-driven parameter estimation problem for a reaction-diffusion glioma growth model with mass effects. J. Math. Biol. 56, 793–825 (2008)MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Klimke, A., Wohlmuth, B.: Piecewise multilinear hierarchical sparse grid interpolation in MATLAB. ACM Trans. Math. Software 31, 1–20 (2005)MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Konukoglu, E., Clatz, O., Menze, B.H., Weber, M.-A., Stieltjes, B., Mandonnet, E., Delingette, H., Ayache, N.: Image guided personalization of reaction-diffusion type tumor growth models using modified anisotropic Eikonal equations. IEEE TMI 29, 77–95 (2010)Google Scholar
  17. 17.
    Kyriacou, S.K., Davatzikos, C., Zinreich, S.J., Bryan, R.N.: Nonlinear elastic registration of brain images with tumor pathology using a biomechanical model. IEEE TMI 18, 580–592 (1999)Google Scholar
  18. 18.
    Ma, X., Zabaras, N.: An efficient Bayesian inference approach to inverse problems based on an adaptive sparse grid collocation method. Inverse Problems 25 (2009)Google Scholar
  19. 19.
    McCorquodale, P., Colella, P., Johansen, H.: A Cartesian grid embedded boundary method for the heat equation in irregular domains. J. Comp. Phys. 173(2), 620–635 (2001)CrossRefzbMATHGoogle Scholar
  20. 20.
    Menze, B.H., Stretton, E., Konukoglu, E., Ayache, N.: Image-based modeling of tumor growth in patients with glioma. In: Garbe, C.S., Rannacher, R., Platt, U., Wagner, T. (eds.) Optimal Control in Image Processing. Springer, Heidelberg (2011)Google Scholar
  21. 21.
    Mohamed, A., Zacharakib, E.I., Shena, D., Davatzikos, C.: Deformable registration of brain tumor images via a statistical model of tumor-induced deformation. MedIA 10, 752–763 (2006)Google Scholar
  22. 22.
    Pallud, J., Mandonnet, E., Duffau, H., Galanaud, D., Taillandier, L., Capelle, L.: Prognostic value of initial magnetic resonance imaging growth rates for World Health Organization grade II gliomas. Ann. Neurol. 60, 380–383 (2006)CrossRefGoogle Scholar
  23. 23.
    Prastawa, M., Bullitt, E., Gerig, G.: Simulation of brain tumors in MR images for evaluation of segmentation efficacy. MedIA 13, 297–311 (2009)Google Scholar
  24. 24.
    Swanson, K.R., Alvord, E.C., Murray, J.D.: A quantitative model for differential motility of gliomas in grey and white matter. Cell Prolif. 33, 317–329 (2000)CrossRefGoogle Scholar
  25. 25.
    Zacharaki, E., Shen, D., Mohamed, A., Davatzikos, C.: Registration of brain images with tumors: Towards the construction of statistical atlases for therapy planning. In: Proc. ISBI (2006)Google Scholar
  26. 26.
    Zacharaki, E.I., Hogea, C.S., Shen, D., Biros, G., Davatzikos, C.: Non-diffeomorphic registration of brain tumor images by simulating tissue loss and tumor growth. Neuroimage 46, 762–774 (2009)CrossRefGoogle Scholar
  27. 27.
    Zarabas, N.: Solving stochastic inverse problems: A sparse grid collocation approach. In: Biegler, L. (ed.) Large-Scale Inverse Problems and Quantification of Uncertainty. Wiley, Chichester (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Bjoern H. Menze
    • 1
    • 2
  • Koen Van Leemput
    • 1
    • 3
    • 4
  • Antti Honkela
    • 5
  • Ender Konukoglu
    • 6
  • Marc-André Weber
    • 7
  • Nicholas Ayache
    • 2
  • Polina Golland
    • 1
  1. 1.Computer Science and Artificial Intelligence LaboratoryMassachusetts Institute of TechnologyUSA
  2. 2.Asclepios Research ProjectINRIA Sophia-AntipolisFrance
  3. 3.Dept. of RadiologyMassachusetts General Hospital, Harvard Medical SchoolUSA
  4. 4.Department of Information and Computer ScienceAalto UniversityFinland
  5. 5.Helsinki Institute for Information Technology HIITUniversity of HelsinkiFinland
  6. 6.Machine Learning and Perception GroupMicrosoft ResearchCambridgeUK
  7. 7.Department of Diagnostic RadiologyHeidelberg University HospitalGermany

Personalised recommendations