Support Vector Driven Markov Random Fields towards DTI Segmentation of the Human Skeletal Muscle

Radhouène Neji (1, 2, 3) , Gilles Fleury (1) , J.-F. Deux (4) , A. Rahmouni (4) , G. Bassez (4) , A. Vignaud (5) , Nikolaos Paragios (2, 3)

1 SUPELEC-Campus Gif
2 MAS - Mathématiques Appliquées aux Systèmes - EA 4037
3 GALEN - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content
4 Hôpital Henri Mondor
5 Siemens Medical Solutions

In this paper we propose a classification-based method towards the segmentation of diffusion tensor images. We use Support Vector Machines to classify diffusion tensors and we extend linear classification to the non linear case. To this end, we discuss and evaluate three different classes of kernels on the space of symmetric definite positive matrices that are well suited for the classification of tensor data. We impose spatial constraints by means of a Markov random field model that takes into account the result of SVM classification. Experimental results are provided for diffusion tensor images of human skeletal muscles. They demonstrate the potential of our method in discriminating the different muscle groups.

Keywords: Diffusion Tensor Imaging; Support Vector Machines; Kernels; Markov Random Fields; Human Skeletal Muscle

Domains: Mathematics [math]; Optimization and Control [math.OC]; Engineering Sciences [physics]; Signal and Image processing; Computer Science [cs]; Signal and Image Processing

Radhouène Neji, Gilles Fleury, J.-F. Deux, A. Rahmouni, G. Bassez, et al.. Support Vector Driven Markov Random Fields towards DTI Segmentation of the Human Skeletal Muscle. ISBI International Symposium on Biomedical Imaging, May 2008, Paris, France. pp. 923-926, ⟨10.1109/ISBI.2008.4541148⟩. ⟨hal-00267032⟩