Toward Digital Staining using Imaging Mass Spectrometry and Random Forests
We show on imaging mass spectrometry (IMS) data that the Random Forest classifier can be used for automated tissue classification and that it results in predictions with high sensitivities and positive predictive values, even when intersample variability is present in the data. We further demonstrat...
Gespeichert in:
| Veröffentlicht in: | Journal of proteome research 2009-07, Vol.8 (7), p.3558-3567 |
|---|---|
| Hauptverfasser: | , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 3567 |
|---|---|
| container_issue | 7 |
| container_start_page | 3558 |
| container_title | Journal of proteome research |
| container_volume | 8 |
| creator | Hanselmann, Michael Köthe, Ullrich Kirchner, Marc Renard, Bernhard Y Amstalden, Erika R Glunde, Kristine Heeren, Ron M. A Hamprecht, Fred A |
| description | We show on imaging mass spectrometry (IMS) data that the Random Forest classifier can be used for automated tissue classification and that it results in predictions with high sensitivities and positive predictive values, even when intersample variability is present in the data. We further demonstrate how Markov Random Fields and vector-valued median filtering can be applied to reduce noise effects to further improve the classification results in a posthoc smoothing step. Our study gives clear evidence that digital staining by means of IMS constitutes a promising complement to chemical staining techniques. |
| doi_str_mv | 10.1021/pr900253y |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_2763415</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>67455733</sourcerecordid><originalsourceid>FETCH-LOGICAL-a403t-f5a575b9d567a5001626d7d6e53586215d21abb6fbb1309c0c1a847409d0cb503</originalsourceid><addsrcrecordid>eNptkNFKwzAUhoMoTqcXvoD0RsGLatI0yXIjyHQ6mQhuXofTNq0dbTOTVtnbm7E5Fbw5J3A-_vx8CJ0QfElwRK4WVmIcMbrcQQeEURZSicXu93sgaQ8dOjfHmDCB6T7qERlzyRg7QI8z8wk2C27LomyhCqYtlE3ZFEHnVnNcQ7HaT-BcMF3otLWm1q1dBtBkwYsfpg5GxmrXuiO0l0Pl9PFm99Hr6G42fAgnz_fj4c0khBjTNswZMMESmTEugPlOPOKZyLj2ZQc8IiyLCCQJz5OEUCxTnBIYxCLGMsNpwjDto-t17qJLap2lumktVGphyxrsUhko1d9LU76pwnyoSHAaeyd9dL4JsOa989VVXbpUVxU02nROcREzJij14MUaTK1xzup8-wnBamVebc179vR3qx9yo9oDZ2sAUqfmprONl_RP0BedHosj</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>67455733</pqid></control><display><type>article</type><title>Toward Digital Staining using Imaging Mass Spectrometry and Random Forests</title><source>MEDLINE</source><source>American Chemical Society Journals</source><creator>Hanselmann, Michael ; Köthe, Ullrich ; Kirchner, Marc ; Renard, Bernhard Y ; Amstalden, Erika R ; Glunde, Kristine ; Heeren, Ron M. A ; Hamprecht, Fred A</creator><creatorcontrib>Hanselmann, Michael ; Köthe, Ullrich ; Kirchner, Marc ; Renard, Bernhard Y ; Amstalden, Erika R ; Glunde, Kristine ; Heeren, Ron M. A ; Hamprecht, Fred A</creatorcontrib><description>We show on imaging mass spectrometry (IMS) data that the Random Forest classifier can be used for automated tissue classification and that it results in predictions with high sensitivities and positive predictive values, even when intersample variability is present in the data. We further demonstrate how Markov Random Fields and vector-valued median filtering can be applied to reduce noise effects to further improve the classification results in a posthoc smoothing step. Our study gives clear evidence that digital staining by means of IMS constitutes a promising complement to chemical staining techniques.</description><identifier>ISSN: 1535-3893</identifier><identifier>EISSN: 1535-3907</identifier><identifier>DOI: 10.1021/pr900253y</identifier><identifier>PMID: 19469555</identifier><language>eng</language><publisher>United States: American Chemical Society</publisher><subject>Algorithms ; Computational Biology - methods ; Data Interpretation, Statistical ; Gene Expression Profiling - methods ; Humans ; Image Processing, Computer-Assisted ; Markov Chains ; Mass Spectrometry - methods ; Models, Statistical ; Neoplasms - pathology ; Oligonucleotide Array Sequence Analysis - methods ; Pattern Recognition, Automated ; Proteomics - methods ; Software</subject><ispartof>Journal of proteome research, 2009-07, Vol.8 (7), p.3558-3567</ispartof><rights>Copyright © 2009 American Chemical Society</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-a403t-f5a575b9d567a5001626d7d6e53586215d21abb6fbb1309c0c1a847409d0cb503</citedby><cites>FETCH-LOGICAL-a403t-f5a575b9d567a5001626d7d6e53586215d21abb6fbb1309c0c1a847409d0cb503</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://pubs.acs.org/doi/pdf/10.1021/pr900253y$$EPDF$$P50$$Gacs$$H</linktopdf><linktohtml>$$Uhttps://pubs.acs.org/doi/10.1021/pr900253y$$EHTML$$P50$$Gacs$$H</linktohtml><link.rule.ids>230,314,780,784,885,2765,27076,27924,27925,56738,56788</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/19469555$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Hanselmann, Michael</creatorcontrib><creatorcontrib>Köthe, Ullrich</creatorcontrib><creatorcontrib>Kirchner, Marc</creatorcontrib><creatorcontrib>Renard, Bernhard Y</creatorcontrib><creatorcontrib>Amstalden, Erika R</creatorcontrib><creatorcontrib>Glunde, Kristine</creatorcontrib><creatorcontrib>Heeren, Ron M. A</creatorcontrib><creatorcontrib>Hamprecht, Fred A</creatorcontrib><title>Toward Digital Staining using Imaging Mass Spectrometry and Random Forests</title><title>Journal of proteome research</title><addtitle>J. Proteome Res</addtitle><description>We show on imaging mass spectrometry (IMS) data that the Random Forest classifier can be used for automated tissue classification and that it results in predictions with high sensitivities and positive predictive values, even when intersample variability is present in the data. We further demonstrate how Markov Random Fields and vector-valued median filtering can be applied to reduce noise effects to further improve the classification results in a posthoc smoothing step. Our study gives clear evidence that digital staining by means of IMS constitutes a promising complement to chemical staining techniques.</description><subject>Algorithms</subject><subject>Computational Biology - methods</subject><subject>Data Interpretation, Statistical</subject><subject>Gene Expression Profiling - methods</subject><subject>Humans</subject><subject>Image Processing, Computer-Assisted</subject><subject>Markov Chains</subject><subject>Mass Spectrometry - methods</subject><subject>Models, Statistical</subject><subject>Neoplasms - pathology</subject><subject>Oligonucleotide Array Sequence Analysis - methods</subject><subject>Pattern Recognition, Automated</subject><subject>Proteomics - methods</subject><subject>Software</subject><issn>1535-3893</issn><issn>1535-3907</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2009</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNptkNFKwzAUhoMoTqcXvoD0RsGLatI0yXIjyHQ6mQhuXofTNq0dbTOTVtnbm7E5Fbw5J3A-_vx8CJ0QfElwRK4WVmIcMbrcQQeEURZSicXu93sgaQ8dOjfHmDCB6T7qERlzyRg7QI8z8wk2C27LomyhCqYtlE3ZFEHnVnNcQ7HaT-BcMF3otLWm1q1dBtBkwYsfpg5GxmrXuiO0l0Pl9PFm99Hr6G42fAgnz_fj4c0khBjTNswZMMESmTEugPlOPOKZyLj2ZQc8IiyLCCQJz5OEUCxTnBIYxCLGMsNpwjDto-t17qJLap2lumktVGphyxrsUhko1d9LU76pwnyoSHAaeyd9dL4JsOa989VVXbpUVxU02nROcREzJij14MUaTK1xzup8-wnBamVebc179vR3qx9yo9oDZ2sAUqfmprONl_RP0BedHosj</recordid><startdate>20090701</startdate><enddate>20090701</enddate><creator>Hanselmann, Michael</creator><creator>Köthe, Ullrich</creator><creator>Kirchner, Marc</creator><creator>Renard, Bernhard Y</creator><creator>Amstalden, Erika R</creator><creator>Glunde, Kristine</creator><creator>Heeren, Ron M. A</creator><creator>Hamprecht, Fred A</creator><general>American Chemical Society</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></search><sort><creationdate>20090701</creationdate><title>Toward Digital Staining using Imaging Mass Spectrometry and Random Forests</title><author>Hanselmann, Michael ; Köthe, Ullrich ; Kirchner, Marc ; Renard, Bernhard Y ; Amstalden, Erika R ; Glunde, Kristine ; Heeren, Ron M. A ; Hamprecht, Fred A</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a403t-f5a575b9d567a5001626d7d6e53586215d21abb6fbb1309c0c1a847409d0cb503</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2009</creationdate><topic>Algorithms</topic><topic>Computational Biology - methods</topic><topic>Data Interpretation, Statistical</topic><topic>Gene Expression Profiling - methods</topic><topic>Humans</topic><topic>Image Processing, Computer-Assisted</topic><topic>Markov Chains</topic><topic>Mass Spectrometry - methods</topic><topic>Models, Statistical</topic><topic>Neoplasms - pathology</topic><topic>Oligonucleotide Array Sequence Analysis - methods</topic><topic>Pattern Recognition, Automated</topic><topic>Proteomics - methods</topic><topic>Software</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Hanselmann, Michael</creatorcontrib><creatorcontrib>Köthe, Ullrich</creatorcontrib><creatorcontrib>Kirchner, Marc</creatorcontrib><creatorcontrib>Renard, Bernhard Y</creatorcontrib><creatorcontrib>Amstalden, Erika R</creatorcontrib><creatorcontrib>Glunde, Kristine</creatorcontrib><creatorcontrib>Heeren, Ron M. A</creatorcontrib><creatorcontrib>Hamprecht, Fred A</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>Journal of proteome research</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Hanselmann, Michael</au><au>Köthe, Ullrich</au><au>Kirchner, Marc</au><au>Renard, Bernhard Y</au><au>Amstalden, Erika R</au><au>Glunde, Kristine</au><au>Heeren, Ron M. A</au><au>Hamprecht, Fred A</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Toward Digital Staining using Imaging Mass Spectrometry and Random Forests</atitle><jtitle>Journal of proteome research</jtitle><addtitle>J. Proteome Res</addtitle><date>2009-07-01</date><risdate>2009</risdate><volume>8</volume><issue>7</issue><spage>3558</spage><epage>3567</epage><pages>3558-3567</pages><issn>1535-3893</issn><eissn>1535-3907</eissn><abstract>We show on imaging mass spectrometry (IMS) data that the Random Forest classifier can be used for automated tissue classification and that it results in predictions with high sensitivities and positive predictive values, even when intersample variability is present in the data. We further demonstrate how Markov Random Fields and vector-valued median filtering can be applied to reduce noise effects to further improve the classification results in a posthoc smoothing step. Our study gives clear evidence that digital staining by means of IMS constitutes a promising complement to chemical staining techniques.</abstract><cop>United States</cop><pub>American Chemical Society</pub><pmid>19469555</pmid><doi>10.1021/pr900253y</doi><tpages>10</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1535-3893 |
| ispartof | Journal of proteome research, 2009-07, Vol.8 (7), p.3558-3567 |
| issn | 1535-3893 1535-3907 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_2763415 |
| source | MEDLINE; American Chemical Society Journals |
| subjects | Algorithms Computational Biology - methods Data Interpretation, Statistical Gene Expression Profiling - methods Humans Image Processing, Computer-Assisted Markov Chains Mass Spectrometry - methods Models, Statistical Neoplasms - pathology Oligonucleotide Array Sequence Analysis - methods Pattern Recognition, Automated Proteomics - methods Software |
| title | Toward Digital Staining using Imaging Mass Spectrometry and Random Forests |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T13%3A42%3A33IST&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=Toward%20Digital%20Staining%20using%20Imaging%20Mass%20Spectrometry%20and%20Random%20Forests&rft.jtitle=Journal%20of%20proteome%20research&rft.au=Hanselmann,%20Michael&rft.date=2009-07-01&rft.volume=8&rft.issue=7&rft.spage=3558&rft.epage=3567&rft.pages=3558-3567&rft.issn=1535-3893&rft.eissn=1535-3907&rft_id=info:doi/10.1021/pr900253y&rft_dat=%3Cproquest_pubme%3E67455733%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=67455733&rft_id=info:pmid/19469555&rfr_iscdi=true |