3D Active Surfaces for Liver Segmentation in Multisequence MRI Images

Simple item page
dc.contributor.authorBereciartua, Arantza
dc.contributor.authorPicon, Artzai
dc.contributor.authorGaldran, Adrian
dc.contributor.authorIriondo, Pedro M.
dc.contributor.institutionCOMPUTER_VISION
dc.contributor.institutionTecnalia Research & Innovation
dc.date.issued2016-08-01
dc.descriptionPublisher Copyright: © 2016 Elsevier Ireland Ltd.
dc.description.abstractBiopsies for diagnosis can sometimes be replaced by non-invasive techniques such as CT and MRI. Surgeons require accurate and efficient methods that allow proper segmentation of the organs in order to ensure the most reliable intervention planning. Automated liver segmentation is a difficult and open problem where CT has been more widely explored than MRI. MRI liver segmentation represents a challenge due to the presence of characteristic artifacts, such as partial volumes, noise and low contrast. In this paper, we present a novel method for multichannel MRI automatic liver segmentation. The proposed method consists of the minimization of a 3D active surface by means of the dual approach to the variational formulation of the underlying problem. This active surface evolves over a probability map that is based on a new compact descriptor comprising spatial and multisequence information which is further modeled by means of a liver statistical model. This proposed 3D active surface approach naturally integrates volumetric regularization in the statistical model. The advantages of the compact visual descriptor together with the proposed approach result in a fast and accurate 3D segmentation method. The method was tested on 18 healthy liver studies and results were compared to a gold standard made by expert radiologists. Comparisons with other state-of-the-art approaches are provided by means of nine well established quality metrics. The obtained results improve these methodologies, achieving a Dice Similarity Coefficient of 98.59.en
dc.description.statusPeer reviewed
dc.format.extent12
dc.format.extent732104
dc.identifier.citationBereciartua , A , Picon , A , Galdran , A & Iriondo , P M 2016 , ' 3D Active Surfaces for Liver Segmentation in Multisequence MRI Images ' , unknown , vol. unknown , pp. 149-160 . https://doi.org/10.1016/j.cmpb.2016.04.028
dc.identifier.doi10.1016/j.cmpb.2016.04.028
dc.identifier.otherresearchoutputwizard: 11556/306
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=84966440726&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofunknown
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subject.keywordsMedical imaging
dc.subject.keywords3D active contours
dc.subject.keywordsliver segmentation
dc.subject.keywordsactive surface
dc.subject.keywordsmagnetic resonance imaging
dc.subject.keywordsvariational techniques
dc.subject.keywordsmultichannel
dc.subject.keywordsmultivariate image descriptors
dc.subject.keywordsMedical imaging
dc.subject.keywords3D active contours
dc.subject.keywordsliver segmentation
dc.subject.keywordsactive surface
dc.subject.keywordsmagnetic resonance imaging
dc.subject.keywordsvariational techniques
dc.subject.keywordsmultichannel
dc.subject.keywordsmultivariate image descriptors
dc.subject.keywordsSoftware
dc.subject.keywordsComputer Science Applications
dc.subject.keywordsHealth Informatics
dc.subject.keywordsFunding Info
dc.subject.keywordsHEPATOOL project - Spanish Department of Science and Innovation, IPT-2011-1514-900000
dc.subject.keywordsHEPATOOL project - Spanish Department of Science and Innovation, IPT-2011-1514-900000
dc.title3D Active Surfaces for Liver Segmentation in Multisequence MRI Imagesen
dc.typejournal article
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
3D Active Surfaces for Liver Segmentation in Multisequence MRI images.pdf
Size:
714.95 KB
Format:
Adobe Portable Document Format
Description:
Main article
Download