A new method for diffusion tensor MRI (DT-MRI) regularization is presented that relies on graph diffusion. We represent a DT image using a weighted graph, where the weights of edges are functions of the geodesic distances between tensors. Diffusion across this graph with time is captured by the heat-equation, and the solution, i.e. the heat kernel, is found by exponentiating the Laplacian eigen-system with time. Tensor regularization is accomplished by computing the Riemannian weighted mean using the heat kernel as its weights. The method can efficiently remove noise, while preserving the fine details of images. Experiments on synthetic and real-world datasets illustrate the effectiveness of the method.


Riemannian Manifold Heat Kernel Edge Weight Geodesic Distance Medical Image Analysis 
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.


  1. 1.
    Chefd’Hotel, C., Tschumperle, D., Deriche, R., Faugeras, O.: Constrained Flows of Matrix-Valued Functions: Application to Diffusion Tensor Regularization. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 251–265. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  2. 2.
    Pennec, X., Fillard, P., Ayache, N.: A riemannian framework for tensor computing. International Journal of Computer Vision 66(1), 41–66 (2006)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Poupon, C., Mangin, J., Clark, C., Frouin, V., Regis, J., Le Bihan, D., Bloch, I.: Towards inference of human brain connectivity from mr diffusion tensor data. Medical Image Analysis 5, 1–15 (2001)CrossRefGoogle Scholar
  4. 4.
    Tschumperle, D., Deriche, R.: Diffusion tensor regularization with constraints preservation. In: Proc. of CVPR, pp. 948–953 (2001)Google Scholar
  5. 5.
    Coulon, O., Alexander, D., Arridge, S.: Diffusion tensor magnetic resonance image regularization. Medical Image Analysis 8, 47–67 (2004)CrossRefGoogle Scholar
  6. 6.
    Wang, Z., Vemuri, B., Chen, Y., Mareci, T.: A constrained variational principle for direct estimation and smoothing of the diffusion tensor field from complex dwi. IEEE Trans. on Medical Imaging 23(8), 930–939 (2004)CrossRefGoogle Scholar
  7. 7.
    Kondor, R., Lafferty, J.: Diffusion kernels on graphs and other discrete structures. In: Proc. of ICML (2002)Google Scholar
  8. 8.
    Fletcher, P.T., Joshi, S.: Principal Geodesic Analysis on Symmetric Spaces: Statistics of Diffusion Tensors. In: Sonka, M., Kakadiaris, I.A., Kybic, J. (eds.) CVAMIA/MMBIA 2004. LNCS, vol. 3117, pp. 87–98. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  9. 9.
    Batchelor, P., Moakher, M., Atkinson, D., Calamante, F., Connelly, A.: A rigorous framework for diffusion tensor calculus. Mag. Res. in Medicine 53, 221–225 (2005)CrossRefGoogle Scholar
  10. 10.
    Skovgaard, L.: A riemannian geometry of the multivariate normal model. Scandinavian Jour. of Statistics 11, 211–223 (1984)MATHMathSciNetGoogle Scholar
  11. 11.
    Moakher, M.: A differential geometric approach to the geometric mean of symmetric positive-definite matrices. SIAM J. Mat. Anal. and App. 26, 735–747 (2005)MATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(8), 888–905 (2000)CrossRefGoogle Scholar
  13. 13.
    Chung, F.: Spectral Graph Theory. American Mathmatical Society, Providence, RI (1997)MATHGoogle Scholar
  14. 14.
    Westin, C., Maier, S., Mamata, H., Nabavi, A., Jolesz, F., Kikinis, R.: Processing and visualization for diffusion tensor mri. Medical Image Analysis 6, 93–108 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Fan Zhang
    • 1
  • Edwin R. Hancock
    • 1
  1. 1.Department of Computer ScienceUniversity of YorkYorkUK

Personalised recommendations