Show simple item record

A geodesic voting method for the segmentation of tubular tree and centerlines

dc.contributor.authorRouchdy, Youssef
dc.contributor.authorCohen, Laurent D.
HAL ID: 738939
dc.date.accessioned2012-02-03T15:57:45Z
dc.date.available2012-02-03T15:57:45Z
dc.date.issued2011
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/8029
dc.language.isoenen
dc.subjectBiomedical Imagingen
dc.subject3D imagesen
dc.subjectcenterlinesen
dc.subjectsegmentation of tubularen
dc.subjectgeodesic voting methoden
dc.subject.ddc006.3en
dc.titleA geodesic voting method for the segmentation of tubular tree and centerlinesen
dc.typeCommunication / Conférence
dc.description.abstractenThis paper presents a geodesic voting method to segment tree structures, such as cardiac or cerebral blood vessels. Many authors have used minimal cost paths, or similarly geodesics relative to a weight potential P, to find a vessel between two end points. Our goal focuses on the use of a set of such geodesic paths for finding a tubular tree structure, using minimal interaction. This work adapts the geodesic voting method that we have introduced for the segmentation of thin tree structures to the segmentation of centerlines and tubular trees. The original approach of geodesic voting consists in computing geodesics from a set of end points scattered in the image to a given source point. The target structure corresponds to image points with a high geodesic density. Since the potential takes low values on the tree structure, geodesics will locate preferably on this structure and thus the geodesic density should be high. Geodesic voting method gives a good approximation of the localization of the tree branches, but it does not allow to extract the tubular aspect of the tree. Furthermore, geodesic voting does not guarantee that the extracted tree corresponds to the centerline of the tree. Here, we introduce an explicit constraint that moves the high geodesic density to the centerline of the tree and simultaneously approximates the localization of the boundary of the tubular structure. We show results of the segmentation with this approach on 2D angiogram images. This approach can be extended to 3D images in a straight forward manner.en
dc.identifier.citationpages979 - 983en
dc.relation.ispartoftitle8th IEEE International Symposium on Biomedical Imaging, from nano to macroen
dc.relation.ispartofpublnameIEEEen
dc.relation.ispartofpublcityPiscatawayen
dc.relation.ispartofdate2011
dc.relation.ispartofpages2160en
dc.description.sponsorshipprivateouien
dc.subject.ddclabelIntelligence artificielleen
dc.relation.ispartofisbn978-1-4244-4128-0en
dc.relation.conftitleISBI' 2011en
dc.relation.confdate2011-03
dc.relation.confcityChicagoen
dc.relation.confcountryÉtats-Unisen


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