A Kernel-based graphical model for diffusion tensor registration

A. Sotiras (1, 2) , Radhouène Neji (1, 2, 3) , Jean-François Deux (4) , N. Komodakis (5) , Gilles Fleury (3) , Nikolaos Paragios (1, 2)

1 MAS - Mathématiques Appliquées aux Systèmes - EA 4037
2 GALEN - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content
3 E3S - Supélec Sciences des Systèmes
4 Service d'imagerie médicale
5 CSD-UOC - Computer Science Department [Crete]

In this paper, we propose a novel method for the spatial normalization of diffusion tensor images. The proposed method takes advantage of both the diffusion information and the spatial location of tensor in order to define an appropriate metric in a probabilistic framework. A registration energy is defined in a Reproducing Kernel Hilbert Space (RKHS), encoding the image dissimilarity and the regularity of the deformation field in both the translation and the rotation space. The problem is reformulated as a graphical model where the latent variables are the rotation and the translation that should be applied to every tensor and the observed variables are the tensors themselves. Efficient linear programming is used to minimize the resulting energy. Quantitative and qualitative results on a manually annotated dataset of diffusion tensor images demonstrate the potential of the proposed method.

Mots clés: Diffusion tensor imaging; spatial normalization; kernels; markov random fields; discrete optimization

Domaines: Imagerie médicale; Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

A. Sotiras, Radhouène Neji, Jean-François Deux, N. Komodakis, Gilles Fleury, et al.. A Kernel-based graphical model for diffusion tensor registration. 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI 2010), Apr 2010, Rotterdam, Netherlands. pp.524-527, ⟨10.1109/ISBI.2010.5490295⟩. ⟨hal-00526570⟩