No Cover Image

Book chapter 982 views

Shape Prior Model for Media-Adventitia Border Segmentation in IVUS Using Graph Cut

Ehab Essa, Xianghua Xie, Igor Sazonov Orcid Logo, Perumal Nithiarasu, Dave Smith

Medical Computer Vision. Recognition Techniques and Applications in Medical Imaging, Volume: 7766

Swansea University Author: Igor Sazonov Orcid Logo

Full text not available from this repository: check for access using links below.

DOI (Published version): 10.1007/978-3-642-36620-8_12

Abstract

We present a shape prior based graph cut method which does not require user initialisation. The shape prior is generalised from multiple training shapes, rather than using singular templates as priors. Weighted directed graph construction is used to impose geometrical andsmooth constraints learned f...

Full description

Published in: Medical Computer Vision. Recognition Techniques and Applications in Medical Imaging
Published: 2013
URI: https://cronfa.swan.ac.uk/Record/cronfa28864
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2016-06-14T12:24:55Z
last_indexed 2018-02-09T05:13:25Z
id cronfa28864
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2016-06-14T12:56:13.3427851</datestamp><bib-version>v2</bib-version><id>28864</id><entry>2016-06-14</entry><title>Shape Prior Model for Media-Adventitia Border Segmentation in IVUS Using Graph Cut</title><swanseaauthors><author><sid>05a507952e26462561085fb6f62c8897</sid><ORCID>0000-0001-6685-2351</ORCID><firstname>Igor</firstname><surname>Sazonov</surname><name>Igor Sazonov</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2016-06-14</date><deptcode>AERO</deptcode><abstract>We present a shape prior based graph cut method which does not require user initialisation. The shape prior is generalised from multiple training shapes, rather than using singular templates as priors. Weighted directed graph construction is used to impose geometrical andsmooth constraints learned from priors. The proposed cost function is built upon combining selective feature extractors. A SVM classiffier is used to determine an optimal combination of features in presence of calcification, fibrotic tissues, soft plaques, and metallic stent, each of which has its own characteristics in ultrasound images. Comparative analysis on manually labelled ground-truth shows superior performance of the proposed method compared to conventional graph cut methods.</abstract><type>Book chapter</type><journal>Medical Computer Vision. Recognition Techniques and Applications in Medical Imaging</journal><volume>7766</volume><paginationEnd>123</paginationEnd><publisher/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords/><publishedDay>31</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2013</publishedYear><publishedDate>2013-12-31</publishedDate><doi>10.1007/978-3-642-36620-8_12</doi><url/><notes/><college>COLLEGE NANME</college><department>Aerospace Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>AERO</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2016-06-14T12:56:13.3427851</lastEdited><Created>2016-06-14T11:07:55.1055300</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Aerospace Engineering</level></path><authors><author><firstname>Ehab</firstname><surname>Essa</surname><order>1</order></author><author><firstname>Xianghua</firstname><surname>Xie</surname><order>2</order></author><author><firstname>Igor</firstname><surname>Sazonov</surname><orcid>0000-0001-6685-2351</orcid><order>3</order></author><author><firstname>Perumal</firstname><surname>Nithiarasu</surname><order>4</order></author><author><firstname>Dave</firstname><surname>Smith</surname><order>5</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2016-06-14T12:56:13.3427851 v2 28864 2016-06-14 Shape Prior Model for Media-Adventitia Border Segmentation in IVUS Using Graph Cut 05a507952e26462561085fb6f62c8897 0000-0001-6685-2351 Igor Sazonov Igor Sazonov true false 2016-06-14 AERO We present a shape prior based graph cut method which does not require user initialisation. The shape prior is generalised from multiple training shapes, rather than using singular templates as priors. Weighted directed graph construction is used to impose geometrical andsmooth constraints learned from priors. The proposed cost function is built upon combining selective feature extractors. A SVM classiffier is used to determine an optimal combination of features in presence of calcification, fibrotic tissues, soft plaques, and metallic stent, each of which has its own characteristics in ultrasound images. Comparative analysis on manually labelled ground-truth shows superior performance of the proposed method compared to conventional graph cut methods. Book chapter Medical Computer Vision. Recognition Techniques and Applications in Medical Imaging 7766 123 31 12 2013 2013-12-31 10.1007/978-3-642-36620-8_12 COLLEGE NANME Aerospace Engineering COLLEGE CODE AERO Swansea University 2016-06-14T12:56:13.3427851 2016-06-14T11:07:55.1055300 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Aerospace Engineering Ehab Essa 1 Xianghua Xie 2 Igor Sazonov 0000-0001-6685-2351 3 Perumal Nithiarasu 4 Dave Smith 5
title Shape Prior Model for Media-Adventitia Border Segmentation in IVUS Using Graph Cut
spellingShingle Shape Prior Model for Media-Adventitia Border Segmentation in IVUS Using Graph Cut
Igor Sazonov
title_short Shape Prior Model for Media-Adventitia Border Segmentation in IVUS Using Graph Cut
title_full Shape Prior Model for Media-Adventitia Border Segmentation in IVUS Using Graph Cut
title_fullStr Shape Prior Model for Media-Adventitia Border Segmentation in IVUS Using Graph Cut
title_full_unstemmed Shape Prior Model for Media-Adventitia Border Segmentation in IVUS Using Graph Cut
title_sort Shape Prior Model for Media-Adventitia Border Segmentation in IVUS Using Graph Cut
author_id_str_mv 05a507952e26462561085fb6f62c8897
author_id_fullname_str_mv 05a507952e26462561085fb6f62c8897_***_Igor Sazonov
author Igor Sazonov
author2 Ehab Essa
Xianghua Xie
Igor Sazonov
Perumal Nithiarasu
Dave Smith
format Book chapter
container_title Medical Computer Vision. Recognition Techniques and Applications in Medical Imaging
container_volume 7766
publishDate 2013
institution Swansea University
doi_str_mv 10.1007/978-3-642-36620-8_12
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Aerospace Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Aerospace Engineering
document_store_str 0
active_str 0
description We present a shape prior based graph cut method which does not require user initialisation. The shape prior is generalised from multiple training shapes, rather than using singular templates as priors. Weighted directed graph construction is used to impose geometrical andsmooth constraints learned from priors. The proposed cost function is built upon combining selective feature extractors. A SVM classiffier is used to determine an optimal combination of features in presence of calcification, fibrotic tissues, soft plaques, and metallic stent, each of which has its own characteristics in ultrasound images. Comparative analysis on manually labelled ground-truth shows superior performance of the proposed method compared to conventional graph cut methods.
published_date 2013-12-31T03:35:14Z
_version_ 1763751508437893120
score 11.013171

Similar Items