Applications of Image Analysis to Anatomic Pathology: Realities and Promises
Image Analysis in Pathology is viewed as an ancillary method meant to provide objective support in the resolution of difficult problems. Its Achilles heel is the process of nuclear segmetation (delimitation of the nuclear membrane) which is extremely difficult in pathology materials. Although intera...
Gespeichert in:
Veröffentlicht in: | Cancer investigation 2003, Vol.21 (6), p.950-959 |
---|---|
Hauptverfasser: | , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 959 |
---|---|
container_issue | 6 |
container_start_page | 950 |
container_title | Cancer investigation |
container_volume | 21 |
creator | Gil, Joan Wu, Hai-Shan |
description | Image Analysis in Pathology is viewed as an ancillary method meant to provide objective support in the resolution of difficult problems. Its Achilles heel is the process of nuclear segmetation (delimitation of the nuclear membrane) which is extremely difficult in pathology materials. Although interactive segmentation procedures are available no reliable fully automatic method has been described. The only application of image analysis that has truly succeeded in Pathology is DNA ploidy measurement. A very desirable application is the quantitation of immunohistochemical markers, which is technically challenging, has been resolved only in certain cases and is unlikely to have a general solution. Nuclear quantitation has repeatedly proven to be helpful in reaching differential diagnoses, in particular when based on size distributions of nuclear profiles rather than its average, but is hampered by the segmentation problem discussed above. Texture analysis of chromatin is an exciting, mathematically complex application likely to succeed, for which many approaches have been described. Finally a diagnosis (classification) can be obtained based on algorithms applied to multiple descriptors of tumor cells (for instance nuclear sizes, chromatin texture, shape, etc). The best classificatory approaches are neural networks (a form of artificial intelligence), multivariate analysis, and logistic regression (statistical). |
doi_str_mv | 10.1081/CNV-120025097 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1081_CNV_120025097</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>71509743</sourcerecordid><originalsourceid>FETCH-LOGICAL-c482t-ea97b488ae7068d8562983fe1aa76a9a31bddfe481186cf43b66fa92ec91a6b53</originalsourceid><addsrcrecordid>eNp1kUtvEzEQgC0EomnhyBXtBW4Lfuz6wS2K6EOKaFUBV2vWazeuvOtgO0L59zhKoOLQ04w03zz0DULvCP5EsCSfV99-toRiTHusxAu0ID2jbUcUfYkWWLC-FQqLM3Se8yPGRFLRv0ZnpKsVruQCrZfbbfAGio9zbqJrbiZ4sM1yhrDPPjclHvISJ2-aOyibGOLD_ktzbyH44m1uYB6bu1Tr2eY36JWDkO3bU7xAPy6_fl9dt-vbq5vVct2aTtLSWlBi6KQEKzCXo-w5VZI5SwAEBwWMDOPobCcJkdy4jg2cO1DUGkWADz27QB-Pc7cp_trZXHRdb2wIMNu4y1qQg4yOVbA9gibFnJN1epv8BGmvCdYHfbrq0__0Vf79afBumOz4RJ98VeDDCYBsILgEs_H5ieuZpIzzyskj52cX0wS_YwqjLrAPMf1tYs_dIP5r3VTVZWMgWf0Yd6k-Jj9z_R-RBJwk</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>71509743</pqid></control><display><type>article</type><title>Applications of Image Analysis to Anatomic Pathology: Realities and Promises</title><source>MEDLINE</source><source>Taylor & Francis Medical Library - CRKN</source><source>Access via Taylor & Francis</source><creator>Gil, Joan ; Wu, Hai-Shan</creator><creatorcontrib>Gil, Joan ; Wu, Hai-Shan</creatorcontrib><description>Image Analysis in Pathology is viewed as an ancillary method meant to provide objective support in the resolution of difficult problems. Its Achilles heel is the process of nuclear segmetation (delimitation of the nuclear membrane) which is extremely difficult in pathology materials. Although interactive segmentation procedures are available no reliable fully automatic method has been described. The only application of image analysis that has truly succeeded in Pathology is DNA ploidy measurement. A very desirable application is the quantitation of immunohistochemical markers, which is technically challenging, has been resolved only in certain cases and is unlikely to have a general solution. Nuclear quantitation has repeatedly proven to be helpful in reaching differential diagnoses, in particular when based on size distributions of nuclear profiles rather than its average, but is hampered by the segmentation problem discussed above. Texture analysis of chromatin is an exciting, mathematically complex application likely to succeed, for which many approaches have been described. Finally a diagnosis (classification) can be obtained based on algorithms applied to multiple descriptors of tumor cells (for instance nuclear sizes, chromatin texture, shape, etc). The best classificatory approaches are neural networks (a form of artificial intelligence), multivariate analysis, and logistic regression (statistical).</description><identifier>ISSN: 0735-7907</identifier><identifier>EISSN: 1532-4192</identifier><identifier>DOI: 10.1081/CNV-120025097</identifier><identifier>PMID: 14735698</identifier><identifier>CODEN: CINVD7</identifier><language>eng</language><publisher>New York, NY: Informa UK Ltd</publisher><subject>Algorithms ; Biological and medical sciences ; Cell Nucleus - ultrastructure ; Chromatin ; Diagnostic classification algorithms ; Fractal analysis ; Humans ; Image analysis ; Image Processing, Computer-Assisted ; Immunohistochemistry ; Medical sciences ; Morphometry ; Multiple tumors. Solid tumors. Tumors in childhood (general aspects) ; Neoplasms - pathology ; Nuclear quantitation ; Pathology ; Pathology - trends ; Ploidy ; Texture analysis ; Tumors</subject><ispartof>Cancer investigation, 2003, Vol.21 (6), p.950-959</ispartof><rights>2003 Informa UK Ltd All rights reserved: reproduction in whole or part not permitted 2003</rights><rights>2004 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c482t-ea97b488ae7068d8562983fe1aa76a9a31bddfe481186cf43b66fa92ec91a6b53</citedby><cites>FETCH-LOGICAL-c482t-ea97b488ae7068d8562983fe1aa76a9a31bddfe481186cf43b66fa92ec91a6b53</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.tandfonline.com/doi/pdf/10.1081/CNV-120025097$$EPDF$$P50$$Ginformaworld$$H</linktopdf><linktohtml>$$Uhttps://www.tandfonline.com/doi/full/10.1081/CNV-120025097$$EHTML$$P50$$Ginformaworld$$H</linktohtml><link.rule.ids>314,780,784,4024,27923,27924,27925,59647,59753,60436,60542,61221,61256,61402,61437</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=15382366$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/14735698$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Gil, Joan</creatorcontrib><creatorcontrib>Wu, Hai-Shan</creatorcontrib><title>Applications of Image Analysis to Anatomic Pathology: Realities and Promises</title><title>Cancer investigation</title><addtitle>Cancer Invest</addtitle><description>Image Analysis in Pathology is viewed as an ancillary method meant to provide objective support in the resolution of difficult problems. Its Achilles heel is the process of nuclear segmetation (delimitation of the nuclear membrane) which is extremely difficult in pathology materials. Although interactive segmentation procedures are available no reliable fully automatic method has been described. The only application of image analysis that has truly succeeded in Pathology is DNA ploidy measurement. A very desirable application is the quantitation of immunohistochemical markers, which is technically challenging, has been resolved only in certain cases and is unlikely to have a general solution. Nuclear quantitation has repeatedly proven to be helpful in reaching differential diagnoses, in particular when based on size distributions of nuclear profiles rather than its average, but is hampered by the segmentation problem discussed above. Texture analysis of chromatin is an exciting, mathematically complex application likely to succeed, for which many approaches have been described. Finally a diagnosis (classification) can be obtained based on algorithms applied to multiple descriptors of tumor cells (for instance nuclear sizes, chromatin texture, shape, etc). The best classificatory approaches are neural networks (a form of artificial intelligence), multivariate analysis, and logistic regression (statistical).</description><subject>Algorithms</subject><subject>Biological and medical sciences</subject><subject>Cell Nucleus - ultrastructure</subject><subject>Chromatin</subject><subject>Diagnostic classification algorithms</subject><subject>Fractal analysis</subject><subject>Humans</subject><subject>Image analysis</subject><subject>Image Processing, Computer-Assisted</subject><subject>Immunohistochemistry</subject><subject>Medical sciences</subject><subject>Morphometry</subject><subject>Multiple tumors. Solid tumors. Tumors in childhood (general aspects)</subject><subject>Neoplasms - pathology</subject><subject>Nuclear quantitation</subject><subject>Pathology</subject><subject>Pathology - trends</subject><subject>Ploidy</subject><subject>Texture analysis</subject><subject>Tumors</subject><issn>0735-7907</issn><issn>1532-4192</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2003</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNp1kUtvEzEQgC0EomnhyBXtBW4Lfuz6wS2K6EOKaFUBV2vWazeuvOtgO0L59zhKoOLQ04w03zz0DULvCP5EsCSfV99-toRiTHusxAu0ID2jbUcUfYkWWLC-FQqLM3Se8yPGRFLRv0ZnpKsVruQCrZfbbfAGio9zbqJrbiZ4sM1yhrDPPjclHvISJ2-aOyibGOLD_ktzbyH44m1uYB6bu1Tr2eY36JWDkO3bU7xAPy6_fl9dt-vbq5vVct2aTtLSWlBi6KQEKzCXo-w5VZI5SwAEBwWMDOPobCcJkdy4jg2cO1DUGkWADz27QB-Pc7cp_trZXHRdb2wIMNu4y1qQg4yOVbA9gibFnJN1epv8BGmvCdYHfbrq0__0Vf79afBumOz4RJ98VeDDCYBsILgEs_H5ieuZpIzzyskj52cX0wS_YwqjLrAPMf1tYs_dIP5r3VTVZWMgWf0Yd6k-Jj9z_R-RBJwk</recordid><startdate>2003</startdate><enddate>2003</enddate><creator>Gil, Joan</creator><creator>Wu, Hai-Shan</creator><general>Informa UK Ltd</general><general>Taylor & Francis</general><general>Informa Healthcare</general><scope>IQODW</scope><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></search><sort><creationdate>2003</creationdate><title>Applications of Image Analysis to Anatomic Pathology: Realities and Promises</title><author>Gil, Joan ; Wu, Hai-Shan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c482t-ea97b488ae7068d8562983fe1aa76a9a31bddfe481186cf43b66fa92ec91a6b53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2003</creationdate><topic>Algorithms</topic><topic>Biological and medical sciences</topic><topic>Cell Nucleus - ultrastructure</topic><topic>Chromatin</topic><topic>Diagnostic classification algorithms</topic><topic>Fractal analysis</topic><topic>Humans</topic><topic>Image analysis</topic><topic>Image Processing, Computer-Assisted</topic><topic>Immunohistochemistry</topic><topic>Medical sciences</topic><topic>Morphometry</topic><topic>Multiple tumors. Solid tumors. Tumors in childhood (general aspects)</topic><topic>Neoplasms - pathology</topic><topic>Nuclear quantitation</topic><topic>Pathology</topic><topic>Pathology - trends</topic><topic>Ploidy</topic><topic>Texture analysis</topic><topic>Tumors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Gil, Joan</creatorcontrib><creatorcontrib>Wu, Hai-Shan</creatorcontrib><collection>Pascal-Francis</collection><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><jtitle>Cancer investigation</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Gil, Joan</au><au>Wu, Hai-Shan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Applications of Image Analysis to Anatomic Pathology: Realities and Promises</atitle><jtitle>Cancer investigation</jtitle><addtitle>Cancer Invest</addtitle><date>2003</date><risdate>2003</risdate><volume>21</volume><issue>6</issue><spage>950</spage><epage>959</epage><pages>950-959</pages><issn>0735-7907</issn><eissn>1532-4192</eissn><coden>CINVD7</coden><abstract>Image Analysis in Pathology is viewed as an ancillary method meant to provide objective support in the resolution of difficult problems. Its Achilles heel is the process of nuclear segmetation (delimitation of the nuclear membrane) which is extremely difficult in pathology materials. Although interactive segmentation procedures are available no reliable fully automatic method has been described. The only application of image analysis that has truly succeeded in Pathology is DNA ploidy measurement. A very desirable application is the quantitation of immunohistochemical markers, which is technically challenging, has been resolved only in certain cases and is unlikely to have a general solution. Nuclear quantitation has repeatedly proven to be helpful in reaching differential diagnoses, in particular when based on size distributions of nuclear profiles rather than its average, but is hampered by the segmentation problem discussed above. Texture analysis of chromatin is an exciting, mathematically complex application likely to succeed, for which many approaches have been described. Finally a diagnosis (classification) can be obtained based on algorithms applied to multiple descriptors of tumor cells (for instance nuclear sizes, chromatin texture, shape, etc). The best classificatory approaches are neural networks (a form of artificial intelligence), multivariate analysis, and logistic regression (statistical).</abstract><cop>New York, NY</cop><pub>Informa UK Ltd</pub><pmid>14735698</pmid><doi>10.1081/CNV-120025097</doi><tpages>10</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0735-7907 |
ispartof | Cancer investigation, 2003, Vol.21 (6), p.950-959 |
issn | 0735-7907 1532-4192 |
language | eng |
recordid | cdi_crossref_primary_10_1081_CNV_120025097 |
source | MEDLINE; Taylor & Francis Medical Library - CRKN; Access via Taylor & Francis |
subjects | Algorithms Biological and medical sciences Cell Nucleus - ultrastructure Chromatin Diagnostic classification algorithms Fractal analysis Humans Image analysis Image Processing, Computer-Assisted Immunohistochemistry Medical sciences Morphometry Multiple tumors. Solid tumors. Tumors in childhood (general aspects) Neoplasms - pathology Nuclear quantitation Pathology Pathology - trends Ploidy Texture analysis Tumors |
title | Applications of Image Analysis to Anatomic Pathology: Realities and Promises |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T17%3A43%3A20IST&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=Applications%20of%20Image%20Analysis%20to%20Anatomic%20Pathology:%20Realities%20and%20Promises&rft.jtitle=Cancer%20investigation&rft.au=Gil,%20Joan&rft.date=2003&rft.volume=21&rft.issue=6&rft.spage=950&rft.epage=959&rft.pages=950-959&rft.issn=0735-7907&rft.eissn=1532-4192&rft.coden=CINVD7&rft_id=info:doi/10.1081/CNV-120025097&rft_dat=%3Cproquest_cross%3E71509743%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=71509743&rft_id=info:pmid/14735698&rfr_iscdi=true |