Diffusion Tensor Estimation, Regularization and Classification
In this chapter, we explore diffusion tensor estimation, regularization and classification. To this end, we introduce a variational method for joint estimation and regularization of diffusion tensor fields from noisy raw data as well as a Support Vector Machine (SVM) based classification framework.
In order to simultaneously estimate and regularize diffusion tensor fields from noisy observations, we integrate the classic quadratic data fidelity term derived from the Stejskal-Tanner equation with a new smoothness term leading to a convex objective function. The regularization term is based on the assumption that the signal can be reconstructed using a weighted average of observations on a local neighborhood. The weights measure the similarity between tensors and are computed directly from the diffusion images. We preserve the positive semi-definiteness constraint using a projected gradient descent.
The classification framework we consider in this chapter allows linear as well as non linear separation of diffusion tensors using kernels defined on the space of symmetric positive definite matrices. The kernels are derived from their counterparts on the statistical manifold of multivariate Gaussian distributions with zero mean or from distance substitution in the Gaussian Radial Basis Function (RBF) kernel. Experimental results on diffusion tensor images of the human skeletal muscle (calf) show the potential of our algorithms both in denoising and SVM-driven Markov random field segmentation.
KeywordsSupport Vector Machine Diffusion Tensor Imaging Diffusion Tensor Extensor Digitorum Longus Human Skeletal Muscle
- 1.N. Azzabou, N. Paragios, F. Guichard, and F. Cao. Variable bandwidth image denoising using image-based noise models. In CVPR, 2007.Google Scholar
- 2.S. Basu, P. T. Fletcher, and R. T. Whitaker. Rician noise removal in diffusion tensor mri. In MICCAI (1), pages 117–125, 2006.Google Scholar
- 5.S. Boughorbel, J.-P. Tarel, and F. Fleuret. Non-Mercer kernels for SVM object recognition. In BMVC, 2004.Google Scholar
- 6.C. A. Castano-Moraga, C. Lenglet, R. Deriche, and J. Ruiz-Alzola. A Riemannian approach to anisotropic filtering of tensor fields. Signal Processing [Special Issue on Tensor Signal Processing], 87(2):263–276, 2007.Google Scholar
- 8.R. Deriche, D. Tschumperle, C. Lenglet, and M. Rousson. Variational approaches to the estimation, regularization and segmentation of diffusion tensor images. In F. Paragios, Chen, editor, Mathematical Models in Computer Vision: The Handbook. Springer, 2005 edition, 2005.Google Scholar
- 9.P. Fillard, V. Arsigny, X. Pennec, and N. Ayache. Clinical DT-MRI estimation, smoothing and fiber tracking with log-Euclidean metrics. In Proceedings of the IEEE International Symposium on Biomedical Imaging (ISBI 2006), pages 786–789, Crystal Gateway Marriott, Arlington, Virginia, USA, Apr. 2006.Google Scholar
- 11.C. J. Galban, S. Maderwald, K. Uffmann, and M. E. Ladd. A diffusion tensor imaging analysis of gender differences in water diffusivity within human skeletal muscle. NMR in Biomedicine, 2005.Google Scholar
- 14.T. Joachims. Making large-scale support vector machine learning practical. In A. S. B. Schölkopf, C. Burges, editor, Advances in Kernel Methods: Support Vector Machines. MIT Press, Cambridge, MA, 1998.Google Scholar
- 15.P. Khurd, R. Verma, and C. Davatzikos. Kernel-based manifold learning for statistical analysis of diffusion tensor images. In IPMI, pages 581–593, 2007.Google Scholar
- 16.N. Komodakis, G. Tziritas, and N. Paragios. Fast, approximately optimal solutions for single and dynamic MRFs. In CVPR, 2007.Google Scholar
- 18.S. Lyu. Mercer kernels for object recognition with local features. In CVPR, 2005.Google Scholar
- 19.M. Maddah, W. E. L. Grimson, and S. K. Warfield. Statistical modeling and em clustering of white matter fiber tracts. In ISBI, pages 53–56, 2006.Google Scholar
- 20.M. Martin-Fernandez, C.-F. Westin, and C. Alberola-Lopez. 3D Bayesian regularization of diffusion tensor MRI using multivariate Gaussian Markov random fields. In MICCAI (1), pages 351–359, 2004.Google Scholar
- 23.R. Salvador, A. Pea, D. K. Menon, T. A. Carpenter, J. D. Pickard, and E. T. Bullmore. Formal characterization and extension of the linearized diffusion tensor model. Human Brain Mapping, 24(2):144–155, 2005.Google Scholar
- 25.K. Tsuda, G. Ratsch, and M. Warmuth. Matrix exponentiated gradient updates for on-line learning and Bregman projection. Journal of Machine Learning Research, 6:995–1018, 06 2005.Google Scholar
- 26.V. Vapnik. Statistical Learning Theory. Wiley, 1998.Google Scholar
- 27.F. Vos, M. Caan, K. Vermeer, C. Majoie, G. den Heeten, and L. van Vliet. Linear and kernel fisher discriminant analysis for studying diffusion tensor images in schizophrenia. In ISBI, pages 764–767, 2007.Google Scholar
- 29.J. Weickert, C. Feddern, M. Welk, B. Burgeth, and T. Brox. PDEs for tensor image processing. In J. Weickert and H. Hagen, editors, Visualization and Processing of Tensor Fields, pages 399–414. Springer, January 2006.Google Scholar