Multi-Classifier-Based Automatic Polyp Detection in Endoscopic Images

Automatic polyp detection in endoscopy (or colonoscopy) images is challenging because the types of polyp and their appearances are diverse, and the colors and textures of polyps are quite similar to those of normal tissues in many cases. It is thus often very difficult to distinguish polyps from nor...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of medical and biological engineering 2016-12, Vol.36 (6), p.871-882
Hauptverfasser: Cho, Yeong-Jun, Bae, Seung-Hwan, Yoon, Kuk-Jin
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 882
container_issue 6
container_start_page 871
container_title Journal of medical and biological engineering
container_volume 36
creator Cho, Yeong-Jun
Bae, Seung-Hwan
Yoon, Kuk-Jin
description Automatic polyp detection in endoscopy (or colonoscopy) images is challenging because the types of polyp and their appearances are diverse, and the colors and textures of polyps are quite similar to those of normal tissues in many cases. It is thus often very difficult to distinguish polyps from normal tissues using conventional methodology. To effectively resolve these challenges, we propose a framework based on multi-classifier learning and a contour intensity difference (CID) measure. To detect polyps of diverse appearances, we first classify polyps into K types according to their shape via unsupervised learning. We then train K classifiers to detect the K types of polyp. This multi-classifier learning improves the polyp detection rate. However, false positives also increase because colon structures look similar to polyps. To reduce false positives while preserving the high detection rate, we propose a CID measure. Experimental results using public and our own datasets show that the proposed methods are promising for detecting polyps with diverse appearances.
doi_str_mv 10.1007/s40846-016-0190-4
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_1880803736</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1880803736</sourcerecordid><originalsourceid>FETCH-LOGICAL-c316t-fd73d790794554abb6fb35ca199269c4d9b1fb183fc335dd441db3e1397e4d573</originalsourceid><addsrcrecordid>eNp1kD9PwzAQxS0EElXpB2CLxGyw63_xWEqBSkUwwGw5tlO5SuNgO0O_Pa7CwMJJpxvuvXenHwC3GN1jhMRDoqimHCJ8bokgvQCzJZYSUsHEJZhhjiREsmbXYJHSAZUiknNcz8Dmbeyyh-tOp-Rb7yJ81MnZajXmcNTZm-ojdKehenLZmexDX_m-2vQ2JBOGst0e9d6lG3DV6i65xe-cg6_nzef6Fe7eX7br1Q4agnmGrRXEComEpIxR3TS8bQgzury65NJQKxvcNrgmrSGEWUsptg1xmEjhqGWCzMHdlDvE8D26lNUhjLEvJxWua1QjIggvKjypTAwpRdeqIfqjjieFkToDUxMwVYCpMzBFi2c5eVLR9nsX_yT_a_oB65lsqA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1880803736</pqid></control><display><type>article</type><title>Multi-Classifier-Based Automatic Polyp Detection in Endoscopic Images</title><source>SpringerLink Journals - AutoHoldings</source><creator>Cho, Yeong-Jun ; Bae, Seung-Hwan ; Yoon, Kuk-Jin</creator><creatorcontrib>Cho, Yeong-Jun ; Bae, Seung-Hwan ; Yoon, Kuk-Jin</creatorcontrib><description>Automatic polyp detection in endoscopy (or colonoscopy) images is challenging because the types of polyp and their appearances are diverse, and the colors and textures of polyps are quite similar to those of normal tissues in many cases. It is thus often very difficult to distinguish polyps from normal tissues using conventional methodology. To effectively resolve these challenges, we propose a framework based on multi-classifier learning and a contour intensity difference (CID) measure. To detect polyps of diverse appearances, we first classify polyps into K types according to their shape via unsupervised learning. We then train K classifiers to detect the K types of polyp. This multi-classifier learning improves the polyp detection rate. However, false positives also increase because colon structures look similar to polyps. To reduce false positives while preserving the high detection rate, we propose a CID measure. Experimental results using public and our own datasets show that the proposed methods are promising for detecting polyps with diverse appearances.</description><identifier>ISSN: 1609-0985</identifier><identifier>EISSN: 2199-4757</identifier><identifier>DOI: 10.1007/s40846-016-0190-4</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Biomedical Engineering and Bioengineering ; Cell Biology ; Classifiers ; Colon ; Endoscopy ; Engineering ; Image detection ; Imaging ; Learning ; Original Article ; Polyps ; Radiology ; Unsupervised learning</subject><ispartof>Journal of medical and biological engineering, 2016-12, Vol.36 (6), p.871-882</ispartof><rights>Taiwanese Society of Biomedical Engineering 2016</rights><rights>Copyright Springer Science &amp; Business Media 2016</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c316t-fd73d790794554abb6fb35ca199269c4d9b1fb183fc335dd441db3e1397e4d573</citedby><cites>FETCH-LOGICAL-c316t-fd73d790794554abb6fb35ca199269c4d9b1fb183fc335dd441db3e1397e4d573</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s40846-016-0190-4$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s40846-016-0190-4$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Cho, Yeong-Jun</creatorcontrib><creatorcontrib>Bae, Seung-Hwan</creatorcontrib><creatorcontrib>Yoon, Kuk-Jin</creatorcontrib><title>Multi-Classifier-Based Automatic Polyp Detection in Endoscopic Images</title><title>Journal of medical and biological engineering</title><addtitle>J. Med. Biol. Eng</addtitle><description>Automatic polyp detection in endoscopy (or colonoscopy) images is challenging because the types of polyp and their appearances are diverse, and the colors and textures of polyps are quite similar to those of normal tissues in many cases. It is thus often very difficult to distinguish polyps from normal tissues using conventional methodology. To effectively resolve these challenges, we propose a framework based on multi-classifier learning and a contour intensity difference (CID) measure. To detect polyps of diverse appearances, we first classify polyps into K types according to their shape via unsupervised learning. We then train K classifiers to detect the K types of polyp. This multi-classifier learning improves the polyp detection rate. However, false positives also increase because colon structures look similar to polyps. To reduce false positives while preserving the high detection rate, we propose a CID measure. Experimental results using public and our own datasets show that the proposed methods are promising for detecting polyps with diverse appearances.</description><subject>Biomedical Engineering and Bioengineering</subject><subject>Cell Biology</subject><subject>Classifiers</subject><subject>Colon</subject><subject>Endoscopy</subject><subject>Engineering</subject><subject>Image detection</subject><subject>Imaging</subject><subject>Learning</subject><subject>Original Article</subject><subject>Polyps</subject><subject>Radiology</subject><subject>Unsupervised learning</subject><issn>1609-0985</issn><issn>2199-4757</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2016</creationdate><recordtype>article</recordtype><recordid>eNp1kD9PwzAQxS0EElXpB2CLxGyw63_xWEqBSkUwwGw5tlO5SuNgO0O_Pa7CwMJJpxvuvXenHwC3GN1jhMRDoqimHCJ8bokgvQCzJZYSUsHEJZhhjiREsmbXYJHSAZUiknNcz8Dmbeyyh-tOp-Rb7yJ81MnZajXmcNTZm-ojdKehenLZmexDX_m-2vQ2JBOGst0e9d6lG3DV6i65xe-cg6_nzef6Fe7eX7br1Q4agnmGrRXEComEpIxR3TS8bQgzury65NJQKxvcNrgmrSGEWUsptg1xmEjhqGWCzMHdlDvE8D26lNUhjLEvJxWua1QjIggvKjypTAwpRdeqIfqjjieFkToDUxMwVYCpMzBFi2c5eVLR9nsX_yT_a_oB65lsqA</recordid><startdate>20161201</startdate><enddate>20161201</enddate><creator>Cho, Yeong-Jun</creator><creator>Bae, Seung-Hwan</creator><creator>Yoon, Kuk-Jin</creator><general>Springer Berlin Heidelberg</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>K9.</scope></search><sort><creationdate>20161201</creationdate><title>Multi-Classifier-Based Automatic Polyp Detection in Endoscopic Images</title><author>Cho, Yeong-Jun ; Bae, Seung-Hwan ; Yoon, Kuk-Jin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c316t-fd73d790794554abb6fb35ca199269c4d9b1fb183fc335dd441db3e1397e4d573</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2016</creationdate><topic>Biomedical Engineering and Bioengineering</topic><topic>Cell Biology</topic><topic>Classifiers</topic><topic>Colon</topic><topic>Endoscopy</topic><topic>Engineering</topic><topic>Image detection</topic><topic>Imaging</topic><topic>Learning</topic><topic>Original Article</topic><topic>Polyps</topic><topic>Radiology</topic><topic>Unsupervised learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Cho, Yeong-Jun</creatorcontrib><creatorcontrib>Bae, Seung-Hwan</creatorcontrib><creatorcontrib>Yoon, Kuk-Jin</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Health &amp; Medical Complete (Alumni)</collection><jtitle>Journal of medical and biological engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Cho, Yeong-Jun</au><au>Bae, Seung-Hwan</au><au>Yoon, Kuk-Jin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Multi-Classifier-Based Automatic Polyp Detection in Endoscopic Images</atitle><jtitle>Journal of medical and biological engineering</jtitle><stitle>J. Med. Biol. Eng</stitle><date>2016-12-01</date><risdate>2016</risdate><volume>36</volume><issue>6</issue><spage>871</spage><epage>882</epage><pages>871-882</pages><issn>1609-0985</issn><eissn>2199-4757</eissn><abstract>Automatic polyp detection in endoscopy (or colonoscopy) images is challenging because the types of polyp and their appearances are diverse, and the colors and textures of polyps are quite similar to those of normal tissues in many cases. It is thus often very difficult to distinguish polyps from normal tissues using conventional methodology. To effectively resolve these challenges, we propose a framework based on multi-classifier learning and a contour intensity difference (CID) measure. To detect polyps of diverse appearances, we first classify polyps into K types according to their shape via unsupervised learning. We then train K classifiers to detect the K types of polyp. This multi-classifier learning improves the polyp detection rate. However, false positives also increase because colon structures look similar to polyps. To reduce false positives while preserving the high detection rate, we propose a CID measure. Experimental results using public and our own datasets show that the proposed methods are promising for detecting polyps with diverse appearances.</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/s40846-016-0190-4</doi><tpages>12</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1609-0985
ispartof Journal of medical and biological engineering, 2016-12, Vol.36 (6), p.871-882
issn 1609-0985
2199-4757
language eng
recordid cdi_proquest_journals_1880803736
source SpringerLink Journals - AutoHoldings
subjects Biomedical Engineering and Bioengineering
Cell Biology
Classifiers
Colon
Endoscopy
Engineering
Image detection
Imaging
Learning
Original Article
Polyps
Radiology
Unsupervised learning
title Multi-Classifier-Based Automatic Polyp Detection in Endoscopic Images
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T15%3A39%3A40IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Multi-Classifier-Based%20Automatic%20Polyp%20Detection%20in%20Endoscopic%20Images&rft.jtitle=Journal%20of%20medical%20and%20biological%20engineering&rft.au=Cho,%20Yeong-Jun&rft.date=2016-12-01&rft.volume=36&rft.issue=6&rft.spage=871&rft.epage=882&rft.pages=871-882&rft.issn=1609-0985&rft.eissn=2199-4757&rft_id=info:doi/10.1007/s40846-016-0190-4&rft_dat=%3Cproquest_cross%3E1880803736%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1880803736&rft_id=info:pmid/&rfr_iscdi=true