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

Radhouène Neji; Gilles Fleury; J.-F. Deux; A. Rahmouni; G. Bassez; A. Vignaud; Nikolaos Paragios

doi:10.1109/ISBI.2008.4541148

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

Inria Saclay - Ile de France, Ecole Centrale Paris

4 Hôpital Henri Mondor

5 Siemens Medical Solutions

Abstract : 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

Document type :

Conference papers

Domain :

Mathematics [math] / Optimization and Control [math.OC]

Engineering Sciences [physics] / Signal and Image processing

Computer Science [cs] / Signal and Image Processing

Liste complète des métadonnées

Cited literature [17 references] Display Hide Download

https://hal-supelec.archives-ouvertes.fr/hal-00267032
Contributor : Karine El Rassi <>
Submitted on : Thursday, March 27, 2008 - 11:03:22 AM
Last modification on : Tuesday, February 26, 2019 - 10:12:33 AM
Document(s) archivé(s) le : Friday, May 21, 2010 - 12:53:38 AM

ISBI08.pdf

Files produced by the author(s)

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

File

Identifiers

Collections

Citation

Export

Metrics

612

258

Contact

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

File

Identifiers

Collections

Citation

Export

Share

Metrics

612

258

Contact