Manifold-driven Grouping of Skeletal Muscle Fibers

Radhouene Neji; Jean-Francois Deux; Ahmed Besbes; Nikos Komodakis; Georg Langs; Mezri Maatouk; Alain Rahmouni; Guillaume Bassez; Gilles Fleury; Nikolaos Paragios

inria-00358691, version 2

Manifold-driven Grouping of Skeletal Muscle Fibers

Radhouene Neji ( Auteur à contacter de préférence ) ^1, 2, 3, Jean-Francois Deux ⁴, Ahmed Besbes ^2, 3, Nikos Komodakis ⁵, Georg Langs ⁶, Mezri Maatouk ⁴, Alain Rahmouni ⁴, Guillaume Bassez ^4, 7, 8, Gilles Fleury ¹, Nikolaos Paragios ^2, 3

N° RR-6825 (2009)

Résumé : In this report, we present a manifold clustering method for the classification of fibers obtained from diffusion tensor images (DTI) of the human skeletal muscle. To this end, we propose the use of angular Hilbertian metrics between multivariate normal distributions to define a family of distances between tensors that we generalize to fibers. The obtained metrics between fiber tracts encompasses both diffusion and localization information. As far as clustering is concerned, we use two methods. The first approach is based on diffusion maps and k-means clustering in the spectral embedding space. The second approach uses a linear programming formulation of prototype-based clustering. This formulation allows for classification over manifolds without the necessity to embed the data in low dimensional spaces and determines automatically the number of clusters. The experimental validation of the proposed framework is done using a manually annotated significant dataset of DTI of the calf muscle for healthy and diseased subjects.

1 : Supélec Sciences des Systèmes - EA4454 (E3S)
SUPELEC
2 : Mathématiques Appliquées aux Systèmes - EA 4037 (MAS)
Ecole Centrale Paris
3 : GALEN (INRIA Saclay - Ile de France)
INRIA – Ecole Centrale Paris
4 : Hôpital Henri Mondor
Assistance publique - Hôpitaux de Paris (AP-HP) – Hôpital Henri Mondor – Université Paris-Est Créteil Val-de-Marne (UPEC)
5 : Computer Science Department (CSD-UOC)
Institute of Computer Science – University of Crete
6 : Computational Image Analysis and Radiology (CIR lab)
Medical University of Vienna
7 : Institut Mondor de recherche biomédicale (IMRB)
INSERM : U841 – Université Paris-Est Créteil Val-de-Marne (UPEC)
8 : Service d'anatomie et cytologie pathologiques [Mondor]
Assistance publique - Hôpitaux de Paris (AP-HP) – Hôpital Henri Mondor – Université Paris-Est Créteil Val-de-Marne (UPEC)

inria-00358691, version 2
http://hal.inria.fr/inria-00358691
oai:hal.inria.fr:inria-00358691
Contributeur : Radhouene Neji <>
Soumis le : Jeudi 19 Février 2009, 18:00:01
Dernière modification le : Jeudi 2 Avril 2009, 11:00:00

Voir la fiche détaillée

Documents associés

PDF :

Exporter

Bibtex EndNote TEI RefWorks

%% inria-00358691, version 2
%% http://hal.inria.fr/inria-00358691
@techreport{neji:inria-00358691,
    hal_id = {inria-00358691},
    url = {http://hal.inria.fr/inria-00358691},
    title = {{Manifold-driven Grouping of Skeletal Muscle Fibers}},
    author = {Neji, Radhouene and Deux, Jean-Francois and Besbes, Ahmed and Komodakis, Nikos and Langs, Georg and Maatouk, Mezri and Rahmouni, Alain and Bassez, Guillaume and Fleury, Gilles and Paragios, Nikolaos},
    abstract = {{In this report, we present a manifold clustering method for the classification of fibers obtained from diffusion tensor images (DTI) of the human skeletal muscle. To this end, we propose the use of angular Hilbertian metrics between multivariate normal distributions to define a family of distances between tensors that we generalize to fibers. The obtained metrics between fiber tracts encompasses both diffusion and localization information. As far as clustering is concerned, we use two methods. The first approach is based on diffusion maps and k-means clustering in the spectral embedding space. The second approach uses a linear programming formulation of prototype-based clustering. This formulation allows for classification over manifolds without the necessity to embed the data in low dimensional spaces and determines automatically the number of clusters. The experimental validation of the proposed framework is done using a manually annotated significant dataset of DTI of the calf muscle for healthy and diseased subjects.}},
    keywords = {DTI, Diffusion tensor; Fiber; Hilbertian Metrics,; Linear Programming; Diffusion Maps,; Clustering; Human Skeletal Muscle},
    language = {Anglais},
    affiliation = {Sup{\'e}lec Sciences des Syst{\`e}mes - EA4454 - E3S , Math{\'e}matiques Appliqu{\'e}es aux Syst{\`e}mes - EA 4037 - MAS , GALEN - INRIA Saclay - Ile de France , H{\^o}pital Henri Mondor , Computer Science Department - CSD-UOC , Computational Image Analysis and Radiology - CIR lab , Institut Mondor de recherche biom{\'e}dicale - IMRB , Service d'anatomie et cytologie pathologiques [Mondor]},
    type = {Rapport de recherche},
    institution = {INRIA},
    number = {RR-6825},
    year = {2009},
    pdf = {http://hal.inria.fr/inria-00358691/PDF/RR-6825.pdf},
}

<?xml version="1.0" encoding="UTF-8"?>
<listBibl xmlns="http://www.tei-c.org/ns/1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML">
<listBibl type="report"><head>Rapports</head>
<biblStruct type="report" xml:id="inria-00358691"><monogr>
<author><persName><forename>Radhouene</forename><surname>Neji</surname></persName>
<affiliation>
<orgName type="laboratory">E3S</orgName>
<orgName type="team">Supélec Sciences des Systèmes - EA4454</orgName>
<country>FR</country>
<orgName type="institution">SUPELEC</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">MAS</orgName>
<orgName type="team">Mathématiques Appliquées aux Systèmes - EA 4037</orgName>
<country>FR</country>
<orgName type="institution">Ecole Centrale Paris</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">INRIA Saclay - Ile de France</orgName>
<orgName type="team">GALEN</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">Ecole Centrale Paris</orgName>
</affiliation>
</author>
<author><persName><forename>Jean-Francois</forename><surname>Deux</surname></persName>
<affiliation>
<orgName type="team">Hôpital Henri Mondor</orgName>
<country>FR</country>
<orgName type="institution">Assistance publique - Hôpitaux de Paris (AP-HP)</orgName>
<orgName type="institution">Hôpital Henri Mondor</orgName>
<orgName type="institution">Université Paris-Est Créteil Val-de-Marne (UPEC)</orgName>
</affiliation>
</author>
<author><persName><forename>Ahmed</forename><surname>Besbes</surname></persName>
<affiliation>
<orgName type="laboratory">MAS</orgName>
<orgName type="team">Mathématiques Appliquées aux Systèmes - EA 4037</orgName>
<country>FR</country>
<orgName type="institution">Ecole Centrale Paris</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">INRIA Saclay - Ile de France</orgName>
<orgName type="team">GALEN</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">Ecole Centrale Paris</orgName>
</affiliation>
</author>
<author><persName><forename>Nikos</forename><surname>Komodakis</surname></persName>
<affiliation>
<orgName type="laboratory">CSD-UOC</orgName>
<orgName type="team">Computer Science Department</orgName>
<country>GR</country>
<orgName type="institution">Institute of Computer Science</orgName>
<orgName type="institution">University of Crete</orgName>
</affiliation>
</author>
<author><persName><forename>Georg</forename><surname>Langs</surname></persName>
<affiliation>
<orgName type="laboratory">CIR lab</orgName>
<orgName type="team">Computational Image Analysis and Radiology</orgName>
<country>AT</country>
<orgName type="institution">Medical University of Vienna</orgName>
</affiliation>
</author>
<author><persName><forename>Mezri</forename><surname>Maatouk</surname></persName>
<affiliation>
<orgName type="team">Hôpital Henri Mondor</orgName>
<country>FR</country>
<orgName type="institution">Assistance publique - Hôpitaux de Paris (AP-HP)</orgName>
<orgName type="institution">Hôpital Henri Mondor</orgName>
<orgName type="institution">Université Paris-Est Créteil Val-de-Marne (UPEC)</orgName>
</affiliation>
</author>
<author><persName><forename>Alain</forename><surname>Rahmouni</surname></persName>
<affiliation>
<orgName type="team">Hôpital Henri Mondor</orgName>
<country>FR</country>
<orgName type="institution">Assistance publique - Hôpitaux de Paris (AP-HP)</orgName>
<orgName type="institution">Hôpital Henri Mondor</orgName>
<orgName type="institution">Université Paris-Est Créteil Val-de-Marne (UPEC)</orgName>
</affiliation>
</author>
<author><persName><forename>Guillaume</forename><surname>Bassez</surname></persName>
<affiliation>
<orgName type="team">Hôpital Henri Mondor</orgName>
<country>FR</country>
<orgName type="institution">Assistance publique - Hôpitaux de Paris (AP-HP)</orgName>
<orgName type="institution">Hôpital Henri Mondor</orgName>
<orgName type="institution">Université Paris-Est Créteil Val-de-Marne (UPEC)</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">IMRB</orgName>
<orgName type="team">Institut Mondor de recherche biomédicale</orgName>
<country>FR</country>
<orgName type="institution">INSERM : U841</orgName>
<orgName type="institution">Université Paris-Est Créteil Val-de-Marne (UPEC)</orgName>
</affiliation>
<affiliation>
<orgName type="team">Service d'anatomie et cytologie pathologiques [Mondor]</orgName>
<country>FR</country>
<orgName type="institution">Assistance publique - Hôpitaux de Paris (AP-HP)</orgName>
<orgName type="institution">Hôpital Henri Mondor</orgName>
<orgName type="institution">Université Paris-Est Créteil Val-de-Marne (UPEC)</orgName>
</affiliation>
</author>
<author><persName><forename>Gilles</forename><surname>Fleury</surname></persName>
<affiliation>
<orgName type="laboratory">E3S</orgName>
<orgName type="team">Supélec Sciences des Systèmes - EA4454</orgName>
<country>FR</country>
<orgName type="institution">SUPELEC</orgName>
</affiliation>
</author>
<author><persName><forename>Nikolaos</forename><surname>Paragios</surname></persName>
<affiliation>
<orgName type="laboratory">MAS</orgName>
<orgName type="team">Mathématiques Appliquées aux Systèmes - EA 4037</orgName>
<country>FR</country>
<orgName type="institution">Ecole Centrale Paris</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">INRIA Saclay - Ile de France</orgName>
<orgName type="team">GALEN</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">Ecole Centrale Paris</orgName>
</affiliation>
</author>
<title type="main" level="m">Manifold-driven Grouping of Skeletal Muscle Fibers</title><title type="main" level="m">Manifold-driven Grouping of Skeletal Muscle Fibers</title><imprint><biblScope type="publicationDate">2009-00-00</biblScope></imprint></monogr><idno type="HALid">http://hal.inria.fr/inria-00358691</idno><idno type="HALFile">http://hal.inria.fr/inria-00358691/PDF/RR-6825.pdf</idno></biblStruct>
</listBibl>
</listBibl>