Frequency-constrained robust principal component analysis: a sparse representation approach to segmentation of dynamic features in optical coherence tomography imaging
Sparse representation theory is an exciting area of research with recent applications in medical imaging and detection, segmentation, and quantitative analysis of biological processes. We present a variant on the robust-principal component analysis (RPCA) algorithm, called frequency constrained RPCA...
Gespeichert in:
| Veröffentlicht in: | Optics express 2017-10, Vol.25 (21), p.25819-25830 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 25830 |
|---|---|
| container_issue | 21 |
| container_start_page | 25819 |
| container_title | Optics express |
| container_volume | 25 |
| creator | McLean, James P Ling, Yuye Hendon, Christine P |
| description | Sparse representation theory is an exciting area of research with recent applications in medical imaging and detection, segmentation, and quantitative analysis of biological processes. We present a variant on the robust-principal component analysis (RPCA) algorithm, called frequency constrained RPCA (FC-RPCA), for selectively segmenting dynamic phenomena that exhibit spectra within a user-defined range of frequencies. The algorithm lacks subjective parameter tuning and demonstrates robust segmentation in datasets containing multiple motion sources and high amplitude noise. When tested on 17 ex-vivo, time lapse optical coherence tomography (OCT) B-scans of human ciliated epithelium, segmentation accuracies ranged between 91-99% and consistently out-performed traditional RPCA. |
| doi_str_mv | 10.1364/OE.25.025819 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_5644470</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1952529388</sourcerecordid><originalsourceid>FETCH-LOGICAL-c2299-4cea617b36f6fe3b717d5e2ab3f02f7696c673dcf20bbe70252bc3a08c2d2b273</originalsourceid><addsrcrecordid>eNpVUcuO1DAQjBCIfcCNM_KRAxn8SpxwQEKrWUBaaS5wtjpOJ2OU2MZOVsoX8ZuYnWW0nNxyVVe1qoriDaM7Jmr54bDf8WpHedWw9llxyWgrS0kb9fzJfFFcpfSTUiZVq14WF7ylknFZXRa_byP-WtGZrTTepSWCddiT6Ls1LSRE64wNMBHj5-AduoWAg2lLNn0kQFKAmJBEDBFTBmGx3hEIIXowR7J4knCcz4AfSL85mK0hA8Ky5iVi83dYrHnwOGLMp2BenP0YIRw3YmcYrRtfFS8GmBK-fnyvix-3--83X8u7w5dvN5_vSsN525bSINRMdaIe6gFFp5jqK-TQiYHyQdVtbWolejNw2nWocmq8MwJoY3jPO67EdfHppBvWbsbe5NsjTDoHMUPctAer_0ecPerR3-uqllIqmgXePQpEn4NNi55tMjhN4NCvSbO2yqataJpMfX-imuhTijicbRjVf7vVh73mlT51m-lvn552Jv8rU_wBhJymRg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1952529388</pqid></control><display><type>article</type><title>Frequency-constrained robust principal component analysis: a sparse representation approach to segmentation of dynamic features in optical coherence tomography imaging</title><source>MEDLINE</source><source>DOAJ Directory of Open Access Journals</source><source>EZB-FREE-00999 freely available EZB journals</source><source>Alma/SFX Local Collection</source><creator>McLean, James P ; Ling, Yuye ; Hendon, Christine P</creator><creatorcontrib>McLean, James P ; Ling, Yuye ; Hendon, Christine P</creatorcontrib><description>Sparse representation theory is an exciting area of research with recent applications in medical imaging and detection, segmentation, and quantitative analysis of biological processes. We present a variant on the robust-principal component analysis (RPCA) algorithm, called frequency constrained RPCA (FC-RPCA), for selectively segmenting dynamic phenomena that exhibit spectra within a user-defined range of frequencies. The algorithm lacks subjective parameter tuning and demonstrates robust segmentation in datasets containing multiple motion sources and high amplitude noise. When tested on 17 ex-vivo, time lapse optical coherence tomography (OCT) B-scans of human ciliated epithelium, segmentation accuracies ranged between 91-99% and consistently out-performed traditional RPCA.</description><identifier>ISSN: 1094-4087</identifier><identifier>EISSN: 1094-4087</identifier><identifier>DOI: 10.1364/OE.25.025819</identifier><identifier>PMID: 29041245</identifier><language>eng</language><publisher>United States: Optical Society of America</publisher><subject>Algorithms ; Cilia - physiology ; Epithelium - diagnostic imaging ; Humans ; Movement ; Principal Component Analysis ; Time Factors ; Tomography, Optical Coherence - methods ; Tomography, Optical Coherence - statistics & numerical data ; Trachea - cytology ; Trachea - diagnostic imaging</subject><ispartof>Optics express, 2017-10, Vol.25 (21), p.25819-25830</ispartof><rights>2017 Optical Society of America 2017 Optical Society of America</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c2299-4cea617b36f6fe3b717d5e2ab3f02f7696c673dcf20bbe70252bc3a08c2d2b273</citedby><cites>FETCH-LOGICAL-c2299-4cea617b36f6fe3b717d5e2ab3f02f7696c673dcf20bbe70252bc3a08c2d2b273</cites><orcidid>0000-0002-4628-7604</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,315,781,785,865,886,27929,27930</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/29041245$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>McLean, James P</creatorcontrib><creatorcontrib>Ling, Yuye</creatorcontrib><creatorcontrib>Hendon, Christine P</creatorcontrib><title>Frequency-constrained robust principal component analysis: a sparse representation approach to segmentation of dynamic features in optical coherence tomography imaging</title><title>Optics express</title><addtitle>Opt Express</addtitle><description>Sparse representation theory is an exciting area of research with recent applications in medical imaging and detection, segmentation, and quantitative analysis of biological processes. We present a variant on the robust-principal component analysis (RPCA) algorithm, called frequency constrained RPCA (FC-RPCA), for selectively segmenting dynamic phenomena that exhibit spectra within a user-defined range of frequencies. The algorithm lacks subjective parameter tuning and demonstrates robust segmentation in datasets containing multiple motion sources and high amplitude noise. When tested on 17 ex-vivo, time lapse optical coherence tomography (OCT) B-scans of human ciliated epithelium, segmentation accuracies ranged between 91-99% and consistently out-performed traditional RPCA.</description><subject>Algorithms</subject><subject>Cilia - physiology</subject><subject>Epithelium - diagnostic imaging</subject><subject>Humans</subject><subject>Movement</subject><subject>Principal Component Analysis</subject><subject>Time Factors</subject><subject>Tomography, Optical Coherence - methods</subject><subject>Tomography, Optical Coherence - statistics & numerical data</subject><subject>Trachea - cytology</subject><subject>Trachea - diagnostic imaging</subject><issn>1094-4087</issn><issn>1094-4087</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNpVUcuO1DAQjBCIfcCNM_KRAxn8SpxwQEKrWUBaaS5wtjpOJ2OU2MZOVsoX8ZuYnWW0nNxyVVe1qoriDaM7Jmr54bDf8WpHedWw9llxyWgrS0kb9fzJfFFcpfSTUiZVq14WF7ylknFZXRa_byP-WtGZrTTepSWCddiT6Ls1LSRE64wNMBHj5-AduoWAg2lLNn0kQFKAmJBEDBFTBmGx3hEIIXowR7J4knCcz4AfSL85mK0hA8Ky5iVi83dYrHnwOGLMp2BenP0YIRw3YmcYrRtfFS8GmBK-fnyvix-3--83X8u7w5dvN5_vSsN525bSINRMdaIe6gFFp5jqK-TQiYHyQdVtbWolejNw2nWocmq8MwJoY3jPO67EdfHppBvWbsbe5NsjTDoHMUPctAer_0ecPerR3-uqllIqmgXePQpEn4NNi55tMjhN4NCvSbO2yqataJpMfX-imuhTijicbRjVf7vVh73mlT51m-lvn552Jv8rU_wBhJymRg</recordid><startdate>20171016</startdate><enddate>20171016</enddate><creator>McLean, James P</creator><creator>Ling, Yuye</creator><creator>Hendon, Christine P</creator><general>Optical Society of America</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0002-4628-7604</orcidid></search><sort><creationdate>20171016</creationdate><title>Frequency-constrained robust principal component analysis: a sparse representation approach to segmentation of dynamic features in optical coherence tomography imaging</title><author>McLean, James P ; Ling, Yuye ; Hendon, Christine P</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c2299-4cea617b36f6fe3b717d5e2ab3f02f7696c673dcf20bbe70252bc3a08c2d2b273</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Algorithms</topic><topic>Cilia - physiology</topic><topic>Epithelium - diagnostic imaging</topic><topic>Humans</topic><topic>Movement</topic><topic>Principal Component Analysis</topic><topic>Time Factors</topic><topic>Tomography, Optical Coherence - methods</topic><topic>Tomography, Optical Coherence - statistics & numerical data</topic><topic>Trachea - cytology</topic><topic>Trachea - diagnostic imaging</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>McLean, James P</creatorcontrib><creatorcontrib>Ling, Yuye</creatorcontrib><creatorcontrib>Hendon, Christine P</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Optics express</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>McLean, James P</au><au>Ling, Yuye</au><au>Hendon, Christine P</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Frequency-constrained robust principal component analysis: a sparse representation approach to segmentation of dynamic features in optical coherence tomography imaging</atitle><jtitle>Optics express</jtitle><addtitle>Opt Express</addtitle><date>2017-10-16</date><risdate>2017</risdate><volume>25</volume><issue>21</issue><spage>25819</spage><epage>25830</epage><pages>25819-25830</pages><issn>1094-4087</issn><eissn>1094-4087</eissn><abstract>Sparse representation theory is an exciting area of research with recent applications in medical imaging and detection, segmentation, and quantitative analysis of biological processes. We present a variant on the robust-principal component analysis (RPCA) algorithm, called frequency constrained RPCA (FC-RPCA), for selectively segmenting dynamic phenomena that exhibit spectra within a user-defined range of frequencies. The algorithm lacks subjective parameter tuning and demonstrates robust segmentation in datasets containing multiple motion sources and high amplitude noise. When tested on 17 ex-vivo, time lapse optical coherence tomography (OCT) B-scans of human ciliated epithelium, segmentation accuracies ranged between 91-99% and consistently out-performed traditional RPCA.</abstract><cop>United States</cop><pub>Optical Society of America</pub><pmid>29041245</pmid><doi>10.1364/OE.25.025819</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0002-4628-7604</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1094-4087 |
| ispartof | Optics express, 2017-10, Vol.25 (21), p.25819-25830 |
| issn | 1094-4087 1094-4087 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_5644470 |
| source | MEDLINE; DOAJ Directory of Open Access Journals; EZB-FREE-00999 freely available EZB journals; Alma/SFX Local Collection |
| subjects | Algorithms Cilia - physiology Epithelium - diagnostic imaging Humans Movement Principal Component Analysis Time Factors Tomography, Optical Coherence - methods Tomography, Optical Coherence - statistics & numerical data Trachea - cytology Trachea - diagnostic imaging |
| title | Frequency-constrained robust principal component analysis: a sparse representation approach to segmentation of dynamic features in optical coherence tomography imaging |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-16T02%3A58%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Frequency-constrained%20robust%20principal%20component%20analysis:%20a%20sparse%20representation%20approach%20to%20segmentation%20of%20dynamic%20features%20in%20optical%20coherence%20tomography%20imaging&rft.jtitle=Optics%20express&rft.au=McLean,%20James%20P&rft.date=2017-10-16&rft.volume=25&rft.issue=21&rft.spage=25819&rft.epage=25830&rft.pages=25819-25830&rft.issn=1094-4087&rft.eissn=1094-4087&rft_id=info:doi/10.1364/OE.25.025819&rft_dat=%3Cproquest_pubme%3E1952529388%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1952529388&rft_id=info:pmid/29041245&rfr_iscdi=true |