No Cover Image

Conference Paper/Proceeding/Abstract 1228 views 238 downloads

Minimum s-Excess Graph for Segmenting and Tracking Multiple Borders with HMM

Ehab Essa, Xianghua Xie Orcid Logo, Jonathan Jones

International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Volume: 9350, Pages: 28 - 35

Swansea University Author: Xianghua Xie Orcid Logo

DOI (Published version): 10.1007/978-3-319-24571-3_4

Abstract

We present a novel HMM based approach to simultaneous segmentation of vessel walls in Lymphatic confocal images. The vessel borders are parameterized using RBFs to minimize the number of tracking points. The proposed method tracks the hidden states that indicate border locations for both the inner a...

Full description

Published in: International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)
ISBN: 978-3-319-24570-6 978-3-319-24571-3
Published: Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015. MICCAI 2015. Lecture Notes in Computer Science, vol 9350. Navab N., Hornegger J., Wells W., Frangi A. (eds). 2015
Online Access: http://link.springer.com/chapter/10.1007%2F978-3-319-24571-3_4
URI: https://cronfa.swan.ac.uk/Record/cronfa22241
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2015-07-02T02:07:57Z
last_indexed 2019-07-22T14:25:16Z
id cronfa22241
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2019-07-22T10:25:56.2859004</datestamp><bib-version>v2</bib-version><id>22241</id><entry>2015-07-01</entry><title>Minimum s-Excess Graph for Segmenting and Tracking Multiple Borders with HMM</title><swanseaauthors><author><sid>b334d40963c7a2f435f06d2c26c74e11</sid><ORCID>0000-0002-2701-8660</ORCID><firstname>Xianghua</firstname><surname>Xie</surname><name>Xianghua Xie</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2015-07-01</date><deptcode>SCS</deptcode><abstract>We present a novel HMM based approach to simultaneous segmentation of vessel walls in Lymphatic confocal images. The vessel borders are parameterized using RBFs to minimize the number of tracking points. The proposed method tracks the hidden states that indicate border locations for both the inner and outer walls. The observation for both borders is obtained using edge-based features from steerable filters. Two separate Gaussian probability distributions for the vessel borders and background are used to infer the emission probability, and the transmission probability is learned using a Baum-Welch algorithm. We transform the segmentation problem into a minimization of an s-excess graph cost, with each node in the graph corresponding to a hidden state and the weight for each node being defined by its emission probability. We define the inter-relations between neighboring nodes based on the transmission probability. We present both qualitative and quantitative analysis in comparison to the popular Viterbi algorithm.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)</journal><volume>9350</volume><paginationStart>28</paginationStart><paginationEnd>35</paginationEnd><publisher>Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015. MICCAI 2015. Lecture Notes in Computer Science, vol 9350. Navab N., Hornegger J., Wells W., Frangi A. (eds).</publisher><isbnPrint>978-3-319-24570-6</isbnPrint><isbnElectronic>978-3-319-24571-3</isbnElectronic><keywords>Graph cut, image segmentation, medical image analysis, HMM, multiple border segmentation</keywords><publishedDay>31</publishedDay><publishedMonth>10</publishedMonth><publishedYear>2015</publishedYear><publishedDate>2015-10-31</publishedDate><doi>10.1007/978-3-319-24571-3_4</doi><url>http://link.springer.com/chapter/10.1007%2F978-3-319-24571-3_4</url><notes></notes><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2019-07-22T10:25:56.2859004</lastEdited><Created>2015-07-01T10:57:21.5824939</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Ehab</firstname><surname>Essa</surname><order>1</order></author><author><firstname>Xianghua</firstname><surname>Xie</surname><orcid>0000-0002-2701-8660</orcid><order>2</order></author><author><firstname>Jonathan</firstname><surname>Jones</surname><order>3</order></author></authors><documents><document><filename>0022241-01072015131905.pdf</filename><originalFilename>Paper406.pdf</originalFilename><uploaded>2015-07-01T13:19:05.5530000</uploaded><type>Output</type><contentLength>2049760</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2016-11-20T00:00:00.0000000</embargoDate><documentNotes/><copyrightCorrect>true</copyrightCorrect></document></documents><OutputDurs/></rfc1807>
spelling 2019-07-22T10:25:56.2859004 v2 22241 2015-07-01 Minimum s-Excess Graph for Segmenting and Tracking Multiple Borders with HMM b334d40963c7a2f435f06d2c26c74e11 0000-0002-2701-8660 Xianghua Xie Xianghua Xie true false 2015-07-01 SCS We present a novel HMM based approach to simultaneous segmentation of vessel walls in Lymphatic confocal images. The vessel borders are parameterized using RBFs to minimize the number of tracking points. The proposed method tracks the hidden states that indicate border locations for both the inner and outer walls. The observation for both borders is obtained using edge-based features from steerable filters. Two separate Gaussian probability distributions for the vessel borders and background are used to infer the emission probability, and the transmission probability is learned using a Baum-Welch algorithm. We transform the segmentation problem into a minimization of an s-excess graph cost, with each node in the graph corresponding to a hidden state and the weight for each node being defined by its emission probability. We define the inter-relations between neighboring nodes based on the transmission probability. We present both qualitative and quantitative analysis in comparison to the popular Viterbi algorithm. Conference Paper/Proceeding/Abstract International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 9350 28 35 Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015. MICCAI 2015. Lecture Notes in Computer Science, vol 9350. Navab N., Hornegger J., Wells W., Frangi A. (eds). 978-3-319-24570-6 978-3-319-24571-3 Graph cut, image segmentation, medical image analysis, HMM, multiple border segmentation 31 10 2015 2015-10-31 10.1007/978-3-319-24571-3_4 http://link.springer.com/chapter/10.1007%2F978-3-319-24571-3_4 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University 2019-07-22T10:25:56.2859004 2015-07-01T10:57:21.5824939 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Ehab Essa 1 Xianghua Xie 0000-0002-2701-8660 2 Jonathan Jones 3 0022241-01072015131905.pdf Paper406.pdf 2015-07-01T13:19:05.5530000 Output 2049760 application/pdf Accepted Manuscript true 2016-11-20T00:00:00.0000000 true
title Minimum s-Excess Graph for Segmenting and Tracking Multiple Borders with HMM
spellingShingle Minimum s-Excess Graph for Segmenting and Tracking Multiple Borders with HMM
Xianghua Xie
title_short Minimum s-Excess Graph for Segmenting and Tracking Multiple Borders with HMM
title_full Minimum s-Excess Graph for Segmenting and Tracking Multiple Borders with HMM
title_fullStr Minimum s-Excess Graph for Segmenting and Tracking Multiple Borders with HMM
title_full_unstemmed Minimum s-Excess Graph for Segmenting and Tracking Multiple Borders with HMM
title_sort Minimum s-Excess Graph for Segmenting and Tracking Multiple Borders with HMM
author_id_str_mv b334d40963c7a2f435f06d2c26c74e11
author_id_fullname_str_mv b334d40963c7a2f435f06d2c26c74e11_***_Xianghua Xie
author Xianghua Xie
author2 Ehab Essa
Xianghua Xie
Jonathan Jones
format Conference Paper/Proceeding/Abstract
container_title International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)
container_volume 9350
container_start_page 28
publishDate 2015
institution Swansea University
isbn 978-3-319-24570-6
978-3-319-24571-3
doi_str_mv 10.1007/978-3-319-24571-3_4
publisher Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015. MICCAI 2015. Lecture Notes in Computer Science, vol 9350. Navab N., Hornegger J., Wells W., Frangi A. (eds).
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 Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url http://link.springer.com/chapter/10.1007%2F978-3-319-24571-3_4
document_store_str 1
active_str 0
description We present a novel HMM based approach to simultaneous segmentation of vessel walls in Lymphatic confocal images. The vessel borders are parameterized using RBFs to minimize the number of tracking points. The proposed method tracks the hidden states that indicate border locations for both the inner and outer walls. The observation for both borders is obtained using edge-based features from steerable filters. Two separate Gaussian probability distributions for the vessel borders and background are used to infer the emission probability, and the transmission probability is learned using a Baum-Welch algorithm. We transform the segmentation problem into a minimization of an s-excess graph cost, with each node in the graph corresponding to a hidden state and the weight for each node being defined by its emission probability. We define the inter-relations between neighboring nodes based on the transmission probability. We present both qualitative and quantitative analysis in comparison to the popular Viterbi algorithm.
published_date 2015-10-31T03:26:29Z
_version_ 1763750958249017344
score 11.016235

Similar Items