An optimization approach to segment breast lesions in ultra-sound images using clinically validated visual cues

Joan Massich 1, * Guillaume Lemaitre 2, 1 Mojdeh Rastrgoo 1, 2 Anke Meyer-Baese 3 Joan Martí 2 Fabrice Mériaudeau 1
* Auteur correspondant
1 Le2i - Laboratoire Electronique, Informatique et Image [UMR6303]
2 VICOROB - Research institute of Computer Vision and Robotics [Girona]
3 FSU - Florida State University [Tallahassee]
Abstract : As long as breast cancer remains the leading cause of cancer deaths among female population world wide, developing tools to assist radiologists during the diagnosis process is necessary. However, most of the technologies developed in the imaging laboratories are rarely integrated in this assessing process, as they are based on information cues differing from those used by clinicians. In order to grant Computer Aided Diagnosis (CAD) systems with these information cues when performing non-aided diagnosis, better segmentation strategies are needed to automatically produce accurate delineations of the breast structures. This paper proposes a highly modular and flexible framework for segmenting breast tissues and lesions present in Breast Ultra-Sound (BUS) images. This framework relies on an optimization strategy and high-level de-scriptors designed analogously to the visual cues used by radiologists. The methodology is comprehensively compared to other sixteen published methodologies developed for segmenting lesions in BUS images. The proposed methodology achieves similar results than reported in the state-of-the-art.
Keywords : Breast Ultra-Sound BI-RADS lexicon Optimization based Segmentation Machine-Learning based Segmentation Graph-Cuts
Type de document :
Communication dans un congrès
Liste complète des métadonnées

Littérature citée [9 références]  Voir  Masquer  Télécharger
https://hal-univ-bourgogne.archives-ouvertes.fr/hal-01235871
Contributeur : Guillaume Lemaitre <>
Soumis le : lundi 30 novembre 2015 - 19:46:40
Dernière modification le : mercredi 12 septembre 2018 - 01:27:48
Document(s) archivé(s) le : samedi 29 avril 2017 - 02:24:35

Fichier

master(1).pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01235871, version 1

Collections

UNIV-BOURGOGNE | LE2I | ICB | UNIV-HESAM

Citation

Joan Massich, Guillaume Lemaitre, Mojdeh Rastrgoo, Anke Meyer-Baese, Joan Martí, et al.. An optimization approach to segment breast lesions in ultra-sound images using clinically validated visual cues. Breast Image Analysis Workshop (BIA), Medical Image Computing and Computer Assisted Interventions (MICCAI) 2015, Oct 2015, Munich, Germany. ⟨hal-01235871⟩

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

268

Téléchargements de fichiers

76

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD