Conditional Random Fields for tubulin-microtubule segmentation in cryo-electron tomography

Charles Kervrann 1 Sophie Blestel 1 Denis Chrétien 2
1 SERPICO - Space-timE RePresentation, Imaging and cellular dynamics of molecular COmplexes
Inria Rennes – Bretagne Atlantique
2 IGDR - Institut de Génétique et Développement de Rennes
Abstract : Cryo-electron tomography allows 3D observation of biological specimens in their native and hydrated state at high spatial resolution (4-5 nanometers). Traditionally cryo-tomograms have very low signal-to-noise ratios and conventional image segmentation methods are limited yet. In this paper, we formulate the segmentation problem of both small tubulin aggregates and microtubules against the background as a two class labeling problem in the Conditional Random Field framework. In our approach, we exploit image patches to take into account spatial contexts and to improve robustness to noise. Because of the contrast anisotropy in the specimen thickness direction, each 2D section of the 3D tomogram is segmented separately with an optional update of reference patches. This method is evaluated on synthetic data and on cryo-electron tomograms of in vitro microtubules.
Keywords : Conditional Random Fields segmentation microtubules Cryo-electron tomography
Type de document :
Communication dans un congrès
IEEE International Conference on Image Processing (top 10%” papers in ICIP 2014), Oct 2014, Paris, France. pp.2080 - 2084, 2014, 〈10.1109/ICIP.2014.7025417〉
Liste complète des métadonnées

Littérature citée [22 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/hal-01103330
Contributeur : Charles Kervrann <>
Soumis le : vendredi 23 janvier 2015 - 18:27:52
Dernière modification le : mercredi 16 mai 2018 - 11:23:52
Document(s) archivé(s) le : vendredi 24 avril 2015 - 10:55:57

Fichier

2014-icip-cryoseg.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

UNIV-RENNES1 | INRIA | IGDR | BIOSIT | UR1-UFR-SVE | UNIV-RENNES

Citation

Charles Kervrann, Sophie Blestel, Denis Chrétien. Conditional Random Fields for tubulin-microtubule segmentation in cryo-electron tomography. IEEE International Conference on Image Processing (top 10%” papers in ICIP 2014), Oct 2014, Paris, France. pp.2080 - 2084, 2014, 〈10.1109/ICIP.2014.7025417〉. 〈hal-01103330〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

254

Téléchargements de fichiers

189

Contact


archive-ouverte@inria.fr