Show simple item record

Joint Co-segmentation and Registration of 3D Ultrasound Images

hal.structure.identifier
dc.contributor.authorArdon, Roberto*
hal.structure.identifier
dc.contributor.authorCohen, Laurent D.
HAL ID: 738939		*
hal.structure.identifier
dc.contributor.authorCorréas, Jean-Michel*
hal.structure.identifier
dc.contributor.authorCuingnet, Rémi*
hal.structure.identifier
dc.contributor.authorMory, Benoît*
hal.structure.identifier
dc.contributor.authorPrevost, Raphaël*
dc.date.accessioned2013-12-03T12:13:13Z
dc.date.available2013-12-03T12:13:13Z
dc.date.issued2013
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/12229
dc.language.isoenen
dc.subjectultrasound
dc.subjectrandom forests
dc.subjectkidney
dc.subjectregistration
dc.subjectco-segmentation
dc.subject.ddc006.3en
dc.titleJoint Co-segmentation and Registration of 3D Ultrasound Images
dc.typeCommunication / Conférence
dc.contributor.editoruniversityotherMedisysResearch Lab (Medisys) Philips Research;France
dc.description.abstractenContrast-enhanced ultrasound (CEUS) allows a visualization of the vascularization and complements the anatomical information provided by conventional ultrasound (US). However, these images are inherently subject to noise and shadows, which hinders standard segmentation algorithms. In this paper, we propose to use simultaneously the different information coming from 3D US and CEUS images to address the problem of kidney segmentation. To that end, we introduce a generic framework for joint co-segmentation and registration that seeks objects having the same shape in several images. From this framework, we derive both an ellipsoid co-detection and a model-based co-segmentation algorithm. These methods rely on voxel-classification maps that we estimate using random forests in a structured way. This yields a fast and fully automated pipeline, in which an ellipsoid is first estimated to locate the kidney in both US and CEUS volumes and then deformed to segment it accurately. The proposed method outperforms state-of-the-art results (by dividing the kidney volume error by two) on a clinically representative database of 64 images.
dc.identifier.citationpages782
dc.relation.ispartoftitleIPMI 2013
dc.relation.ispartofeditorZöllei, Lilla
dc.relation.ispartofpublnameSpringer
dc.relation.ispartofpublcityBerlin Heidelberg
dc.relation.ispartofdate2013
dc.subject.ddclabelIntelligence artificielleen
dc.relation.ispartofisbn978-3-642-3886
dc.relation.confcountryUNITED STATES
dc.description.ssrncandidatenon
dc.description.halcandidateoui
dc.description.readershiprecherche
dc.description.audienceInternational
dc.date.updated2017-02-24T18:27:18Z
hal.author.functionaut
hal.author.functionaut
hal.author.functionaut
hal.author.functionaut
hal.author.functionaut
hal.author.functionaut


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record