Advertisement

A Large-Scale Manifold Learning Approach for Brain Tumor Progression Prediction

  • Loc Tran
  • Deb Banerjee
  • Xiaoyan Sun
  • Jihong Wang
  • Ashok J. Kumar
  • David Vinning
  • Frederic D. McKenzie
  • Yaohang Li
  • Jiang Li
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7009)

Abstract

We present a novel manifold learning approach to efficiently identify low-dimensional structures, known as manifolds, embedded in large-scale, high dimensional MRI datasets for brain tumor growth prediction. The datasets consist of a series of MRI scans for three patients with tumor and progressed regions identified. We attempt to identify low dimensional manifolds for tumor, progressed and normal tissues, and most importantly, to verify if the progression manifold exists - the bridge between tumor and normal manifolds. By mapping the bridge manifold back to MRI image space, this method has the potential to predict tumor progression, thereby, greatly benefiting patient management. Preliminary results supported our hypothesis: normal and tumor manifolds are well separated in a low dimensional space and the progressed manifold is found to lie roughly between them but closer to the tumor manifold.

Keywords

Diffusion Tensor Imaging Tumor Region Locally Linear Embedding Fisher Score Nonlinear Dimensionality Reduction 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Pauleit, D., Langen, K.J., et al.: Can the Apparent Diffusion Coefficient be Used as A Noninvasive Parameter to Distinguish Tumor Tissue from Peritumoral Tissue in Cerebral Gliomas? J. Magn. Reson. Imaging (20), 758–764 (2004)CrossRefGoogle Scholar
  2. 2.
    Bode, M.K., Ruohonen, J., et al.: Potential of Diffusion Imaging in Brain Tumors: A Review. Acta Radiol. (47), 585–594 (2006)CrossRefGoogle Scholar
  3. 3.
    Deshpande, A., Rademacher, L., et al.: Matrix approximation and projective clustering via Volume Sampling. In: Symposium on Discrete Algorithms, vol. (2), pp. 225–247 (2006)Google Scholar
  4. 4.
    Drineas, P., Mahomey, M.W.: On the Nystrom Method for Approximating a Gram Matrix for Improved Kernel-Based Learning. JMLR (6), 2153–2175 (2005)MathSciNetzbMATHGoogle Scholar
  5. 5.
    Wang, S., Yao, J., et al.: Improved classifier for computer-aided polyp detection in CT colonography by nonlinear dimensionality reduction. Med. Phys. 35(4), 1377–1386 (2008)CrossRefGoogle Scholar
  6. 6.
    Silva, V., Tenenbaum, J.B.: Global Versus Local Methods in Nonlinear Dimensionality Reduction. In: NIPS, vol. 15, pp. 721–728 (2003)Google Scholar
  7. 7.
    Hatzikirou, H., Deutsch, A., et al.: Mathematical Modelling of Glioblastoma Tumor Developement: A Review. Mathematical Models and Methods in Applied Sciences 15(11), 1779–1794 (2005)MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Murray, J.: Mathematical Biology. Springer, Heidelberg (1989)CrossRefzbMATHGoogle Scholar
  9. 9.
    Atuegwu, N.C., et al.: The integration of quantitative multi-modality imaging data into mathematical models of tumors. Physics in Medicine and Biology 55, 2429–2449 (2010)CrossRefGoogle Scholar
  10. 10.
    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
  11. 11.
    Zhang, Z., et al.: Principal manifolds and nonlinear dimensionality reduction via local tangent space alignment. SIAM Journal of Scientific Computing 26(1), 313–338 (2004)CrossRefzbMATHGoogle Scholar
  12. 12.
    Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)CrossRefGoogle Scholar
  13. 13.
    Hartkens, T., Ruechert, D., et al.: VTK CISG Registration Toolkit: An open source software package for affine and non-rigid registration of single- and multimodal 3D images. In: Workshop Bildverarbeitung fur die Medizin, pp. 409–412 (2002)Google Scholar
  14. 14.
    Duda, R., Hart, P.: Pattern Classification and Scene Analysis, pp. 114–129 (1973)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Loc Tran
    • 1
  • Deb Banerjee
    • 1
  • Xiaoyan Sun
    • 1
  • Jihong Wang
    • 4
  • Ashok J. Kumar
    • 4
  • David Vinning
    • 4
  • Frederic D. McKenzie
    • 3
  • Yaohang Li
    • 2
  • Jiang Li
    • 1
  1. 1.Department of ECEOld Dominion UniversityNorfolk
  2. 2.Department of CSOld Dominion UniversityNorfolk
  3. 3.Department of MSVEOld Dominion UniversityNorfolk
  4. 4.Diagnostic ImagingUniversity of Texas MD Anderson Cancer CenterHouston

Personalised recommendations