Abstract
We consider the problem of segmenting fiber bundles in diffusion tensor images. We cast this problem as a manifold clustering problem in which different fiber bundles correspond to different submanifolds of the space of diffusion tensors. We first learn a local representation of the diffusion tensor data using a generalization of the locally linear embedding (LLE) algorithm from Euclidean to diffusion tensor data. Such a generalization exploits geometric properties of the space of symmetric positive semi-definite matrices, particularly its Riemannian metric. Then, under the assumption that different fiber bundles are physically distinct, we show that the null space of a matrix built from the local representation gives the segmentation of the fiber bundles. Our method is computationally simple, can handle large deformations of the principal direction along the fiber tracts, and performs automatic segmentation without requiring previous fiber tracking. Results on synthetic and real diffusion tensor images are also presented.
Chapter PDF
Similar content being viewed by others
Keywords
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
Arsigny, V., et al.: Log-Euclidean metrics for fast and simple calculus on diffusion tensors. Magnetic Resonance in Medicine 56, 411–421 (2006)
Fletcher, P.T., Joshi, S.: Riemannian geometry for the statistical analysis of diffusion tensor data. Signal Processing 87 (2007)
Pennec, X., Fillard, P., Ayache, N.: A Riemannian framework for tensor computing. International Journal of Computer Vision 66, 41–46 (2006)
Wang, Z., Vemuri, B.C.: DTI segmentation using an information theoretic tensor dissimilarity measure. IEEE Trans. on Med. Imag. 24, 1267–1277 (2005)
Kindlmann, G., et al.: Geodesic-loxodromes for diffusion tensor interpolation and difference measurement. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007, Part I. LNCS, vol. 4791, pp. 1–9. Springer, Heidelberg (2007)
Zhukov, L., et al.: Level set segmentation and modeling of DT-MRI human brain data. Journal of Electronic Imaging, 125–133 (2003)
Ding, Z., et al.: Classification and quantification of neuronal fiber pathways using diffusion tensor MRI. Magnetic Resonance in Medicine 49, 716–721 (2003)
Brun, A., et al.: Clustering fiber tracts using normalized cuts. In: Barillot, C., Haynor, D.R., Hellier, P. (eds.) MICCAI 2004. LNCS, vol. 3216, pp. 368–375. Springer, Heidelberg (2004)
Friman, O., Farneback, G., Westin, C.F.: A Bayesian approach for stochastic white matter tractography. IEEE Trans. on Med. Imag. 25, 965–978 (2006)
Perrin, M., et al.: Fiber tracking in q-ball fields using regularized particle trajectories. In: Information Processing in Medical Imaging (2005)
Wiegell, M., et al.: Automatic segmentation of thalamic nuclei from diffusion tensor magnetic resonance imaging. NeuroImage, 391–401 (2003)
Wang, Z., Vemuri, B.: Tensor field segmentation using region based active contour model. In: European Conference on Computer Vision, pp. 304–315 (2004)
Jonasson, L., et al.: A level set method for segmentation of the thalamus and its nuclei in DT-MRI. Signal Processing 87, 309–321 (2007)
Ziyan, U., Tuch, D., Westin, C.F.: Segmentation of thalamic nuclei from DTI using spectral clustering. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4191, pp. 807–814. Springer, Heidelberg (2006)
Lenglet, C., et al.: A Riemannian approach to diffusion tensor images segmentation. In: Information Processing in Medical Imaging (2005)
Melonakos, J., et al.: Locally-constrained region-based methods for DW-MRI segmentation. In: MMBIA (2007)
Melonakos, J., et al.: Finsler tractography for white matter connectivity analysis of the cingulum bundle. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007, Part I. LNCS, vol. 4791, pp. 36–43. Springer, Heidelberg (2007)
Awate, S., et al.: A fuzzy, nonparametric segmentation framework for DTI and MRI analysis. IEEE Trans. on Med. Imag. 26, 1525–1536 (2007)
Roweis, S., Saul, L.: Think globally, fit locally: Unsupervised learning of low dimensional manifolds. Journal of Machine Learning Research 4, 119–155 (2003)
Goh, A., Vidal, R.: Clustering and dimensionality reduction on Riemannian manifolds. In: IEEE CVPR (2008)
Goh, A., Vidal, R.: Unsupervised Riemannian clustering of probability density functions. In: ECML PKDD (2008)
Wassermann, D., et al.: Diffusion maps clustering for magnetic resonance Q-Ball imaging segmentation. International Journal in Biomedical Imaging (2008)
Haro, G., Lenglet, C., Sapiro, G., Thompson, P.M.: On the non-uniform complexity of brain connectivity. In: ISBI, pp. 887–890 (2008)
Belkin, M., Niyogi, P.: Laplacian eigenmaps and spectral techniques for embedding and clustering. Neural Information Processing Systems, 585–591 (2002)
Donoho, D., Grimes, C.: Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data. PNAS 100, 5591–5596 (2003)
Tenenbaum, J.B., de Silva, V., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290, 2319–2323 (2000)
von Luxburg, U.: A tutorial on spectral clustering. Stat. and Computing 17 (2007)
Horn, R., Johnson, C.: Matrix Analysis. Cambridge University Press, Cambridge (1985)
Toussaint, N., et al.: MedINRIA: Medical image navigation and research tool by INRIA. In: Proc. of MICCAI 2007 Workshop on Interaction in med. image analysis and vis. (2007), http://www-sop.inria.fr/asclepios/software/MedINRIA
Weinstein, D., et al.: Tensorlines: Advection-diffusion based propagation through diffusion tensor fields. In: IEEE Visualization, San Francisco, pp. 249–254 (1999)
Xie, S., et al.: Evaluation of bilateral cingulum with tractography in patients with Alzheimer’s disease. Neuroreport 16, 1275–1278 (2005)
Foong, J., et al.: Investigating regional white matter in schizophrenia using diffusion tensor imaging. Neuroreport 13, 333–336 (2002)
Alexander, A., et al.: Diffusion tensor imaging of the corpus callosum in autism. Neuroimage 34, 61–73 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Goh, A., Vidal, R. (2008). Segmenting Fiber Bundles in Diffusion Tensor Images. In: Forsyth, D., Torr, P., Zisserman, A. (eds) Computer Vision – ECCV 2008. ECCV 2008. Lecture Notes in Computer Science, vol 5304. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-88690-7_18
Download citation
DOI: https://doi.org/10.1007/978-3-540-88690-7_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-88689-1
Online ISBN: 978-3-540-88690-7
eBook Packages: Computer ScienceComputer Science (R0)