Automatic detection of blue-white veil and related structures in dermoscopy images
Abstract Dermoscopy is a non-invasive skin imaging technique, which permits visualization of features of pigmented melanocytic neoplasms that are not discernable by examination with the naked eye. One of the most important features for the diagnosis of melanoma in dermoscopy images is the blue-white...
Gespeichert in:
| Veröffentlicht in: | Computerized medical imaging and graphics 2008-12, Vol.32 (8), p.670-677 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 677 |
|---|---|
| container_issue | 8 |
| container_start_page | 670 |
| container_title | Computerized medical imaging and graphics |
| container_volume | 32 |
| creator | Celebi, M. Emre Iyatomi, Hitoshi Stoecker, William V Moss, Randy H Rabinovitz, Harold S Argenziano, Giuseppe Soyer, H. Peter |
| description | Abstract Dermoscopy is a non-invasive skin imaging technique, which permits visualization of features of pigmented melanocytic neoplasms that are not discernable by examination with the naked eye. One of the most important features for the diagnosis of melanoma in dermoscopy images is the blue-white veil (irregular, structureless areas of confluent blue pigmentation with an overlying white “ground-glass” film). In this article, we present a machine learning approach to the detection of blue-white veil and related structures in dermoscopy images. The method involves contextual pixel classification using a decision tree classifier. The percentage of blue-white areas detected in a lesion combined with a simple shape descriptor yielded a sensitivity of 69.35% and a specificity of 89.97% on a set of 545 dermoscopy images. The sensitivity rises to 78.20% for detection of blue veil in those cases where it is a primary feature for melanoma recognition. |
| doi_str_mv | 10.1016/j.compmedimag.2008.08.003 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_3160648</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0895611108000815</els_id><sourcerecordid>69792514</sourcerecordid><originalsourceid>FETCH-LOGICAL-c551t-d141a30b1c2ef640a440da61a577ac7499663d935e05b366c8d899fd52162ed83</originalsourceid><addsrcrecordid>eNqNUsuK3DAQNCEhO9nkF4Jzyc2TbtuSpcvCMuSxsBDI4yw0UntXE9uaSPKE-fvIzJDd5BRo0EFV1UVXFcUbhDUC8ne7tfHjfiTrRn23rgHEehlonhQrFJ2soOvwabECIVnFEfGieBHjDgBq6PB5cYFCQCsZWxVfrufkR52cKS0lMsn5qfR9uR1mqn7du0TlgdxQ6smWgQadyJYxhdmkOVAs3ZRpYfTR-P2xXOxQfFk86_UQ6dX5vSy-f3j_bfOpuv388WZzfVsZxjBVFlvUDWzR1NTzFnTbgtUcNes6bbpWSs4bKxtGwLYN50ZYIWVvWY28Jiuay-LqpLuft_kWhqYU9KD2IdsIR-W1U3__TO5e3fmDapADbxeBt2eB4H_OFJMaXTQ0DHoiP0fFZSdrhm0GyhPQBB9joP7PEgS1JKJ26lEiaklELQNN5r5-7PKBeY4gAzYnAOVbHRwFFY2jyWStkPNQ1rv_WnP1j4oZ3OSMHn7QkeLOz2HKYShUsVagvi7VWJoBIrdCIGt-A5w6uZc</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>69792514</pqid></control><display><type>article</type><title>Automatic detection of blue-white veil and related structures in dermoscopy images</title><source>MEDLINE</source><source>Elsevier ScienceDirect Journals</source><creator>Celebi, M. Emre ; Iyatomi, Hitoshi ; Stoecker, William V ; Moss, Randy H ; Rabinovitz, Harold S ; Argenziano, Giuseppe ; Soyer, H. Peter</creator><creatorcontrib>Celebi, M. Emre ; Iyatomi, Hitoshi ; Stoecker, William V ; Moss, Randy H ; Rabinovitz, Harold S ; Argenziano, Giuseppe ; Soyer, H. Peter</creatorcontrib><description>Abstract Dermoscopy is a non-invasive skin imaging technique, which permits visualization of features of pigmented melanocytic neoplasms that are not discernable by examination with the naked eye. One of the most important features for the diagnosis of melanoma in dermoscopy images is the blue-white veil (irregular, structureless areas of confluent blue pigmentation with an overlying white “ground-glass” film). In this article, we present a machine learning approach to the detection of blue-white veil and related structures in dermoscopy images. The method involves contextual pixel classification using a decision tree classifier. The percentage of blue-white areas detected in a lesion combined with a simple shape descriptor yielded a sensitivity of 69.35% and a specificity of 89.97% on a set of 545 dermoscopy images. The sensitivity rises to 78.20% for detection of blue veil in those cases where it is a primary feature for melanoma recognition.</description><identifier>ISSN: 0895-6111</identifier><identifier>EISSN: 1879-0771</identifier><identifier>DOI: 10.1016/j.compmedimag.2008.08.003</identifier><identifier>PMID: 18804955</identifier><language>eng</language><publisher>United States: Elsevier Ltd</publisher><subject>Artificial Intelligence ; Blue-white veil ; Contextual pixel classification ; Decision tree classifier ; Decision Trees ; Dermatology - methods ; Dermoscopy ; Dermoscopy - methods ; Humans ; Image Interpretation, Computer-Assisted - methods ; Internal Medicine ; Melanoma ; Melanoma - diagnosis ; Melanoma - pathology ; Nevus, Blue - diagnosis ; Nevus, Blue - pathology ; Other ; Pattern Recognition, Automated - methods ; Sensitivity and Specificity ; Skin Neoplasms - diagnosis ; Skin Neoplasms - pathology ; Skin Pigmentation</subject><ispartof>Computerized medical imaging and graphics, 2008-12, Vol.32 (8), p.670-677</ispartof><rights>Elsevier Ltd</rights><rights>2008 Elsevier Ltd</rights><rights>2008 Elsevier Ltd. All rights reserved. 2008</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c551t-d141a30b1c2ef640a440da61a577ac7499663d935e05b366c8d899fd52162ed83</citedby><cites>FETCH-LOGICAL-c551t-d141a30b1c2ef640a440da61a577ac7499663d935e05b366c8d899fd52162ed83</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.compmedimag.2008.08.003$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>230,314,777,781,882,3537,27905,27906,45976</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/18804955$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Celebi, M. Emre</creatorcontrib><creatorcontrib>Iyatomi, Hitoshi</creatorcontrib><creatorcontrib>Stoecker, William V</creatorcontrib><creatorcontrib>Moss, Randy H</creatorcontrib><creatorcontrib>Rabinovitz, Harold S</creatorcontrib><creatorcontrib>Argenziano, Giuseppe</creatorcontrib><creatorcontrib>Soyer, H. Peter</creatorcontrib><title>Automatic detection of blue-white veil and related structures in dermoscopy images</title><title>Computerized medical imaging and graphics</title><addtitle>Comput Med Imaging Graph</addtitle><description>Abstract Dermoscopy is a non-invasive skin imaging technique, which permits visualization of features of pigmented melanocytic neoplasms that are not discernable by examination with the naked eye. One of the most important features for the diagnosis of melanoma in dermoscopy images is the blue-white veil (irregular, structureless areas of confluent blue pigmentation with an overlying white “ground-glass” film). In this article, we present a machine learning approach to the detection of blue-white veil and related structures in dermoscopy images. The method involves contextual pixel classification using a decision tree classifier. The percentage of blue-white areas detected in a lesion combined with a simple shape descriptor yielded a sensitivity of 69.35% and a specificity of 89.97% on a set of 545 dermoscopy images. The sensitivity rises to 78.20% for detection of blue veil in those cases where it is a primary feature for melanoma recognition.</description><subject>Artificial Intelligence</subject><subject>Blue-white veil</subject><subject>Contextual pixel classification</subject><subject>Decision tree classifier</subject><subject>Decision Trees</subject><subject>Dermatology - methods</subject><subject>Dermoscopy</subject><subject>Dermoscopy - methods</subject><subject>Humans</subject><subject>Image Interpretation, Computer-Assisted - methods</subject><subject>Internal Medicine</subject><subject>Melanoma</subject><subject>Melanoma - diagnosis</subject><subject>Melanoma - pathology</subject><subject>Nevus, Blue - diagnosis</subject><subject>Nevus, Blue - pathology</subject><subject>Other</subject><subject>Pattern Recognition, Automated - methods</subject><subject>Sensitivity and Specificity</subject><subject>Skin Neoplasms - diagnosis</subject><subject>Skin Neoplasms - pathology</subject><subject>Skin Pigmentation</subject><issn>0895-6111</issn><issn>1879-0771</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2008</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNqNUsuK3DAQNCEhO9nkF4Jzyc2TbtuSpcvCMuSxsBDI4yw0UntXE9uaSPKE-fvIzJDd5BRo0EFV1UVXFcUbhDUC8ne7tfHjfiTrRn23rgHEehlonhQrFJ2soOvwabECIVnFEfGieBHjDgBq6PB5cYFCQCsZWxVfrufkR52cKS0lMsn5qfR9uR1mqn7du0TlgdxQ6smWgQadyJYxhdmkOVAs3ZRpYfTR-P2xXOxQfFk86_UQ6dX5vSy-f3j_bfOpuv388WZzfVsZxjBVFlvUDWzR1NTzFnTbgtUcNes6bbpWSs4bKxtGwLYN50ZYIWVvWY28Jiuay-LqpLuft_kWhqYU9KD2IdsIR-W1U3__TO5e3fmDapADbxeBt2eB4H_OFJMaXTQ0DHoiP0fFZSdrhm0GyhPQBB9joP7PEgS1JKJ26lEiaklELQNN5r5-7PKBeY4gAzYnAOVbHRwFFY2jyWStkPNQ1rv_WnP1j4oZ3OSMHn7QkeLOz2HKYShUsVagvi7VWJoBIrdCIGt-A5w6uZc</recordid><startdate>20081201</startdate><enddate>20081201</enddate><creator>Celebi, M. Emre</creator><creator>Iyatomi, Hitoshi</creator><creator>Stoecker, William V</creator><creator>Moss, Randy H</creator><creator>Rabinovitz, Harold S</creator><creator>Argenziano, Giuseppe</creator><creator>Soyer, H. Peter</creator><general>Elsevier Ltd</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>20081201</creationdate><title>Automatic detection of blue-white veil and related structures in dermoscopy images</title><author>Celebi, M. Emre ; Iyatomi, Hitoshi ; Stoecker, William V ; Moss, Randy H ; Rabinovitz, Harold S ; Argenziano, Giuseppe ; Soyer, H. Peter</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c551t-d141a30b1c2ef640a440da61a577ac7499663d935e05b366c8d899fd52162ed83</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Artificial Intelligence</topic><topic>Blue-white veil</topic><topic>Contextual pixel classification</topic><topic>Decision tree classifier</topic><topic>Decision Trees</topic><topic>Dermatology - methods</topic><topic>Dermoscopy</topic><topic>Dermoscopy - methods</topic><topic>Humans</topic><topic>Image Interpretation, Computer-Assisted - methods</topic><topic>Internal Medicine</topic><topic>Melanoma</topic><topic>Melanoma - diagnosis</topic><topic>Melanoma - pathology</topic><topic>Nevus, Blue - diagnosis</topic><topic>Nevus, Blue - pathology</topic><topic>Other</topic><topic>Pattern Recognition, Automated - methods</topic><topic>Sensitivity and Specificity</topic><topic>Skin Neoplasms - diagnosis</topic><topic>Skin Neoplasms - pathology</topic><topic>Skin Pigmentation</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Celebi, M. Emre</creatorcontrib><creatorcontrib>Iyatomi, Hitoshi</creatorcontrib><creatorcontrib>Stoecker, William V</creatorcontrib><creatorcontrib>Moss, Randy H</creatorcontrib><creatorcontrib>Rabinovitz, Harold S</creatorcontrib><creatorcontrib>Argenziano, Giuseppe</creatorcontrib><creatorcontrib>Soyer, H. Peter</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>Computerized medical imaging and graphics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Celebi, M. Emre</au><au>Iyatomi, Hitoshi</au><au>Stoecker, William V</au><au>Moss, Randy H</au><au>Rabinovitz, Harold S</au><au>Argenziano, Giuseppe</au><au>Soyer, H. Peter</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Automatic detection of blue-white veil and related structures in dermoscopy images</atitle><jtitle>Computerized medical imaging and graphics</jtitle><addtitle>Comput Med Imaging Graph</addtitle><date>2008-12-01</date><risdate>2008</risdate><volume>32</volume><issue>8</issue><spage>670</spage><epage>677</epage><pages>670-677</pages><issn>0895-6111</issn><eissn>1879-0771</eissn><abstract>Abstract Dermoscopy is a non-invasive skin imaging technique, which permits visualization of features of pigmented melanocytic neoplasms that are not discernable by examination with the naked eye. One of the most important features for the diagnosis of melanoma in dermoscopy images is the blue-white veil (irregular, structureless areas of confluent blue pigmentation with an overlying white “ground-glass” film). In this article, we present a machine learning approach to the detection of blue-white veil and related structures in dermoscopy images. The method involves contextual pixel classification using a decision tree classifier. The percentage of blue-white areas detected in a lesion combined with a simple shape descriptor yielded a sensitivity of 69.35% and a specificity of 89.97% on a set of 545 dermoscopy images. The sensitivity rises to 78.20% for detection of blue veil in those cases where it is a primary feature for melanoma recognition.</abstract><cop>United States</cop><pub>Elsevier Ltd</pub><pmid>18804955</pmid><doi>10.1016/j.compmedimag.2008.08.003</doi><tpages>8</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0895-6111 |
| ispartof | Computerized medical imaging and graphics, 2008-12, Vol.32 (8), p.670-677 |
| issn | 0895-6111 1879-0771 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_3160648 |
| source | MEDLINE; Elsevier ScienceDirect Journals |
| subjects | Artificial Intelligence Blue-white veil Contextual pixel classification Decision tree classifier Decision Trees Dermatology - methods Dermoscopy Dermoscopy - methods Humans Image Interpretation, Computer-Assisted - methods Internal Medicine Melanoma Melanoma - diagnosis Melanoma - pathology Nevus, Blue - diagnosis Nevus, Blue - pathology Other Pattern Recognition, Automated - methods Sensitivity and Specificity Skin Neoplasms - diagnosis Skin Neoplasms - pathology Skin Pigmentation |
| title | Automatic detection of blue-white veil and related structures in dermoscopy images |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-18T01%3A09%3A08IST&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=Automatic%20detection%20of%20blue-white%20veil%20and%20related%20structures%20in%20dermoscopy%20images&rft.jtitle=Computerized%20medical%20imaging%20and%20graphics&rft.au=Celebi,%20M.%20Emre&rft.date=2008-12-01&rft.volume=32&rft.issue=8&rft.spage=670&rft.epage=677&rft.pages=670-677&rft.issn=0895-6111&rft.eissn=1879-0771&rft_id=info:doi/10.1016/j.compmedimag.2008.08.003&rft_dat=%3Cproquest_pubme%3E69792514%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=69792514&rft_id=info:pmid/18804955&rft_els_id=S0895611108000815&rfr_iscdi=true |