Prior Knowledge, Random Walks and Human Skeletal Muscle Segmentation

Pierre-Yves Baudin (1, 2) , Noura Azzabou (3, 4, 5) , Pierre G. Carlier (3, 4, 5) , Nikos Paragios (1, 6, 7, 8, 9, 10)

1 GALEN - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content
2 CVN - Centre de vision numérique
3 Institut de Myologie
4 MIRCEN - Molecular Imaging Research Center [Fontenay-aux-Roses]
5 UPMC - Université Pierre et Marie Curie - Paris 6
6 imagine [Marne-la-Vallée]
7 LIGM - Laboratoire d'Informatique Gaspard-Monge
8 UPEM - Université Paris-Est Marne-la-Vallée
9 ENPC - École des Ponts ParisTech
10 MAS - Mathématiques Appliquées aux Systèmes - EA 4037

In this paper, we propose a novel approach for segmenting the skeletal muscles in MRI automatically. In order to deal with the absence of contrast between the different muscle classes, we proposed a principled mathematical formulation that integrates prior knowledge with a random walks graph-based formulation. Prior knowledge is repre- sented using a statistical shape atlas that once coupled with the random walks segmentation leads to an efficient iterative linear optimization sys- tem. We reveal the potential of our approach on a challenging set of real clinical data.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement des images [eess.IV]

Pierre-Yves Baudin, Noura Azzabou, Pierre G. Carlier, Nikos Paragios. Prior Knowledge, Random Walks and Human Skeletal Muscle Segmentation. Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2012, France. pp.569-576. ⟨hal-00773665⟩