Loading…
Computer-aided classification of melanocytic lesions using dermoscopic images
Background Computer-assisted diagnosis of dermoscopic images of skin lesions has the potential to improve melanoma early detection. Objective We sought to evaluate the performance of a novel classifier that uses decision forest classification of dermoscopic images to generate a lesion severity score...
Saved in:
Published in: | Journal of the American Academy of Dermatology 2015-11, Vol.73 (5), p.769-776 |
---|---|
Main Authors: | , , , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c477t-19c1b35c31bb77735e38776dadf0925a32920d553ba4b808f9e6057d74969b6d3 |
---|---|
cites | cdi_FETCH-LOGICAL-c477t-19c1b35c31bb77735e38776dadf0925a32920d553ba4b808f9e6057d74969b6d3 |
container_end_page | 776 |
container_issue | 5 |
container_start_page | 769 |
container_title | Journal of the American Academy of Dermatology |
container_volume | 73 |
creator | Ferris, Laura K., MD, PhD Harkes, Jan A., MS Gilbert, Benjamin, MS Winger, Daniel G., MS Golubets, Kseniya, MD, MHS Akilov, Oleg, MD, PhD Satyanarayanan, Mahadev, PhD |
description | Background Computer-assisted diagnosis of dermoscopic images of skin lesions has the potential to improve melanoma early detection. Objective We sought to evaluate the performance of a novel classifier that uses decision forest classification of dermoscopic images to generate a lesion severity score. Methods Severity scores were calculated for 173 dermoscopic images of skin lesions with known histologic diagnosis (39 melanomas, 14 nonmelanoma skin cancers, and 120 benign lesions). A threshold score was used to measure classifier sensitivity and specificity. A reader study was conducted to compare the sensitivity and specificity of the classifier with those of 30 dermatology clinicians. Results The classifier sensitivity for melanoma was 97.4%; specificity was 44.2% in a test set of images. In the reader study, the classifier's sensitivity to melanoma was higher ( P |
doi_str_mv | 10.1016/j.jaad.2015.07.028 |
format | article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1722928883</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0190962215019738</els_id><sourcerecordid>1722928883</sourcerecordid><originalsourceid>FETCH-LOGICAL-c477t-19c1b35c31bb77735e38776dadf0925a32920d553ba4b808f9e6057d74969b6d3</originalsourceid><addsrcrecordid>eNp9kU9v1DAQxS0EapfSL8AB5cglYWxv_EdCSGjV0kpFHICz5diTyiGJFztB2m-Poy0cOHAaa_ze08xvCHlNoaFAxbuhGaz1DQPaNiAbYOoZ2VHQshZSyedkB1RDrQVjl-RlzgMA6D2XF-SSCa6E4HRHPh_idFwXTLUNHn3lRptz6IOzS4hzFftqwtHO0Z2W4KoRc-nmas1hfqw8pilmF4_lJ0z2EfMr8qK3Y8brp3pFvt_efDvc1Q9fPt0fPj7Ubi_lUlPtaMdbx2nXSSl5i1xJKbz1PWjWWs40A9-2vLP7ToHqNQpopZd7LXQnPL8ib8-5xxR_rpgXM4XscCyTYlyzoZKVCKUUL1J2lroUc07Ym2Mqw6aToWA2jGYwG0azYTQgTcFYTG-e8tduQv_X8odbEbw_C7Bs-StgMtkFnB36kNAtxsfw__wP_9jdGOYCffyBJ8xDXNNc-BlqMjNgvm6H3O5I2_KSXPHfdz6YVA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1722928883</pqid></control><display><type>article</type><title>Computer-aided classification of melanocytic lesions using dermoscopic images</title><source>ScienceDirect Journals</source><creator>Ferris, Laura K., MD, PhD ; Harkes, Jan A., MS ; Gilbert, Benjamin, MS ; Winger, Daniel G., MS ; Golubets, Kseniya, MD, MHS ; Akilov, Oleg, MD, PhD ; Satyanarayanan, Mahadev, PhD</creator><creatorcontrib>Ferris, Laura K., MD, PhD ; Harkes, Jan A., MS ; Gilbert, Benjamin, MS ; Winger, Daniel G., MS ; Golubets, Kseniya, MD, MHS ; Akilov, Oleg, MD, PhD ; Satyanarayanan, Mahadev, PhD</creatorcontrib><description>Background Computer-assisted diagnosis of dermoscopic images of skin lesions has the potential to improve melanoma early detection. Objective We sought to evaluate the performance of a novel classifier that uses decision forest classification of dermoscopic images to generate a lesion severity score. Methods Severity scores were calculated for 173 dermoscopic images of skin lesions with known histologic diagnosis (39 melanomas, 14 nonmelanoma skin cancers, and 120 benign lesions). A threshold score was used to measure classifier sensitivity and specificity. A reader study was conducted to compare the sensitivity and specificity of the classifier with those of 30 dermatology clinicians. Results The classifier sensitivity for melanoma was 97.4%; specificity was 44.2% in a test set of images. In the reader study, the classifier's sensitivity to melanoma was higher ( P < .001) and specificity was lower ( P < .001) than that of clinicians. Limitations This is a retrospective study using existing images primarily chosen for biopsy by a dermatologist. The size of the test set is small. Conclusions Our classifier may aid clinicians in deciding if a skin lesion should be biopsied and can easily be incorporated into a portable tool (that uses no proprietary equipment) that could aid clinicians in noninvasively evaluating cutaneous lesions.</description><identifier>ISSN: 0190-9622</identifier><identifier>EISSN: 1097-6787</identifier><identifier>DOI: 10.1016/j.jaad.2015.07.028</identifier><identifier>PMID: 26386631</identifier><language>eng</language><publisher>United States: Elsevier Inc</publisher><subject>basal cell carcinoma ; computer-assisted diagnosis ; Decision Trees ; Dermatology ; dermoscopy ; Dermoscopy - methods ; Female ; Humans ; Image Interpretation, Computer-Assisted - methods ; information technology ; machine learning ; Male ; melanoma ; Melanoma - classification ; Melanoma - pathology ; skin cancer ; Skin Neoplasms - classification ; Skin Neoplasms - pathology</subject><ispartof>Journal of the American Academy of Dermatology, 2015-11, Vol.73 (5), p.769-776</ispartof><rights>2015</rights><rights>Copyright © 2015. Published by Elsevier Inc.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c477t-19c1b35c31bb77735e38776dadf0925a32920d553ba4b808f9e6057d74969b6d3</citedby><cites>FETCH-LOGICAL-c477t-19c1b35c31bb77735e38776dadf0925a32920d553ba4b808f9e6057d74969b6d3</cites><orcidid>0000-0003-1339-5710</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/26386631$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Ferris, Laura K., MD, PhD</creatorcontrib><creatorcontrib>Harkes, Jan A., MS</creatorcontrib><creatorcontrib>Gilbert, Benjamin, MS</creatorcontrib><creatorcontrib>Winger, Daniel G., MS</creatorcontrib><creatorcontrib>Golubets, Kseniya, MD, MHS</creatorcontrib><creatorcontrib>Akilov, Oleg, MD, PhD</creatorcontrib><creatorcontrib>Satyanarayanan, Mahadev, PhD</creatorcontrib><title>Computer-aided classification of melanocytic lesions using dermoscopic images</title><title>Journal of the American Academy of Dermatology</title><addtitle>J Am Acad Dermatol</addtitle><description>Background Computer-assisted diagnosis of dermoscopic images of skin lesions has the potential to improve melanoma early detection. Objective We sought to evaluate the performance of a novel classifier that uses decision forest classification of dermoscopic images to generate a lesion severity score. Methods Severity scores were calculated for 173 dermoscopic images of skin lesions with known histologic diagnosis (39 melanomas, 14 nonmelanoma skin cancers, and 120 benign lesions). A threshold score was used to measure classifier sensitivity and specificity. A reader study was conducted to compare the sensitivity and specificity of the classifier with those of 30 dermatology clinicians. Results The classifier sensitivity for melanoma was 97.4%; specificity was 44.2% in a test set of images. In the reader study, the classifier's sensitivity to melanoma was higher ( P < .001) and specificity was lower ( P < .001) than that of clinicians. Limitations This is a retrospective study using existing images primarily chosen for biopsy by a dermatologist. The size of the test set is small. Conclusions Our classifier may aid clinicians in deciding if a skin lesion should be biopsied and can easily be incorporated into a portable tool (that uses no proprietary equipment) that could aid clinicians in noninvasively evaluating cutaneous lesions.</description><subject>basal cell carcinoma</subject><subject>computer-assisted diagnosis</subject><subject>Decision Trees</subject><subject>Dermatology</subject><subject>dermoscopy</subject><subject>Dermoscopy - methods</subject><subject>Female</subject><subject>Humans</subject><subject>Image Interpretation, Computer-Assisted - methods</subject><subject>information technology</subject><subject>machine learning</subject><subject>Male</subject><subject>melanoma</subject><subject>Melanoma - classification</subject><subject>Melanoma - pathology</subject><subject>skin cancer</subject><subject>Skin Neoplasms - classification</subject><subject>Skin Neoplasms - pathology</subject><issn>0190-9622</issn><issn>1097-6787</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2015</creationdate><recordtype>article</recordtype><recordid>eNp9kU9v1DAQxS0EapfSL8AB5cglYWxv_EdCSGjV0kpFHICz5diTyiGJFztB2m-Poy0cOHAaa_ze08xvCHlNoaFAxbuhGaz1DQPaNiAbYOoZ2VHQshZSyedkB1RDrQVjl-RlzgMA6D2XF-SSCa6E4HRHPh_idFwXTLUNHn3lRptz6IOzS4hzFftqwtHO0Z2W4KoRc-nmas1hfqw8pilmF4_lJ0z2EfMr8qK3Y8brp3pFvt_efDvc1Q9fPt0fPj7Ubi_lUlPtaMdbx2nXSSl5i1xJKbz1PWjWWs40A9-2vLP7ToHqNQpopZd7LXQnPL8ib8-5xxR_rpgXM4XscCyTYlyzoZKVCKUUL1J2lroUc07Ym2Mqw6aToWA2jGYwG0azYTQgTcFYTG-e8tduQv_X8odbEbw_C7Bs-StgMtkFnB36kNAtxsfw__wP_9jdGOYCffyBJ8xDXNNc-BlqMjNgvm6H3O5I2_KSXPHfdz6YVA</recordid><startdate>20151101</startdate><enddate>20151101</enddate><creator>Ferris, Laura K., MD, PhD</creator><creator>Harkes, Jan A., MS</creator><creator>Gilbert, Benjamin, MS</creator><creator>Winger, Daniel G., MS</creator><creator>Golubets, Kseniya, MD, MHS</creator><creator>Akilov, Oleg, MD, PhD</creator><creator>Satyanarayanan, Mahadev, PhD</creator><general>Elsevier Inc</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><orcidid>https://orcid.org/0000-0003-1339-5710</orcidid></search><sort><creationdate>20151101</creationdate><title>Computer-aided classification of melanocytic lesions using dermoscopic images</title><author>Ferris, Laura K., MD, PhD ; Harkes, Jan A., MS ; Gilbert, Benjamin, MS ; Winger, Daniel G., MS ; Golubets, Kseniya, MD, MHS ; Akilov, Oleg, MD, PhD ; Satyanarayanan, Mahadev, PhD</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c477t-19c1b35c31bb77735e38776dadf0925a32920d553ba4b808f9e6057d74969b6d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2015</creationdate><topic>basal cell carcinoma</topic><topic>computer-assisted diagnosis</topic><topic>Decision Trees</topic><topic>Dermatology</topic><topic>dermoscopy</topic><topic>Dermoscopy - methods</topic><topic>Female</topic><topic>Humans</topic><topic>Image Interpretation, Computer-Assisted - methods</topic><topic>information technology</topic><topic>machine learning</topic><topic>Male</topic><topic>melanoma</topic><topic>Melanoma - classification</topic><topic>Melanoma - pathology</topic><topic>skin cancer</topic><topic>Skin Neoplasms - classification</topic><topic>Skin Neoplasms - pathology</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ferris, Laura K., MD, PhD</creatorcontrib><creatorcontrib>Harkes, Jan A., MS</creatorcontrib><creatorcontrib>Gilbert, Benjamin, MS</creatorcontrib><creatorcontrib>Winger, Daniel G., MS</creatorcontrib><creatorcontrib>Golubets, Kseniya, MD, MHS</creatorcontrib><creatorcontrib>Akilov, Oleg, MD, PhD</creatorcontrib><creatorcontrib>Satyanarayanan, Mahadev, PhD</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><jtitle>Journal of the American Academy of Dermatology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ferris, Laura K., MD, PhD</au><au>Harkes, Jan A., MS</au><au>Gilbert, Benjamin, MS</au><au>Winger, Daniel G., MS</au><au>Golubets, Kseniya, MD, MHS</au><au>Akilov, Oleg, MD, PhD</au><au>Satyanarayanan, Mahadev, PhD</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Computer-aided classification of melanocytic lesions using dermoscopic images</atitle><jtitle>Journal of the American Academy of Dermatology</jtitle><addtitle>J Am Acad Dermatol</addtitle><date>2015-11-01</date><risdate>2015</risdate><volume>73</volume><issue>5</issue><spage>769</spage><epage>776</epage><pages>769-776</pages><issn>0190-9622</issn><eissn>1097-6787</eissn><abstract>Background Computer-assisted diagnosis of dermoscopic images of skin lesions has the potential to improve melanoma early detection. Objective We sought to evaluate the performance of a novel classifier that uses decision forest classification of dermoscopic images to generate a lesion severity score. Methods Severity scores were calculated for 173 dermoscopic images of skin lesions with known histologic diagnosis (39 melanomas, 14 nonmelanoma skin cancers, and 120 benign lesions). A threshold score was used to measure classifier sensitivity and specificity. A reader study was conducted to compare the sensitivity and specificity of the classifier with those of 30 dermatology clinicians. Results The classifier sensitivity for melanoma was 97.4%; specificity was 44.2% in a test set of images. In the reader study, the classifier's sensitivity to melanoma was higher ( P < .001) and specificity was lower ( P < .001) than that of clinicians. Limitations This is a retrospective study using existing images primarily chosen for biopsy by a dermatologist. The size of the test set is small. Conclusions Our classifier may aid clinicians in deciding if a skin lesion should be biopsied and can easily be incorporated into a portable tool (that uses no proprietary equipment) that could aid clinicians in noninvasively evaluating cutaneous lesions.</abstract><cop>United States</cop><pub>Elsevier Inc</pub><pmid>26386631</pmid><doi>10.1016/j.jaad.2015.07.028</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0003-1339-5710</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0190-9622 |
ispartof | Journal of the American Academy of Dermatology, 2015-11, Vol.73 (5), p.769-776 |
issn | 0190-9622 1097-6787 |
language | eng |
recordid | cdi_proquest_miscellaneous_1722928883 |
source | ScienceDirect Journals |
subjects | basal cell carcinoma computer-assisted diagnosis Decision Trees Dermatology dermoscopy Dermoscopy - methods Female Humans Image Interpretation, Computer-Assisted - methods information technology machine learning Male melanoma Melanoma - classification Melanoma - pathology skin cancer Skin Neoplasms - classification Skin Neoplasms - pathology |
title | Computer-aided classification of melanocytic lesions using dermoscopic images |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T18%3A28%3A02IST&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=Computer-aided%20classification%20of%20melanocytic%20lesions%20using%20dermoscopic%20images&rft.jtitle=Journal%20of%20the%20American%20Academy%20of%20Dermatology&rft.au=Ferris,%20Laura%20K.,%20MD,%20PhD&rft.date=2015-11-01&rft.volume=73&rft.issue=5&rft.spage=769&rft.epage=776&rft.pages=769-776&rft.issn=0190-9622&rft.eissn=1097-6787&rft_id=info:doi/10.1016/j.jaad.2015.07.028&rft_dat=%3Cproquest_cross%3E1722928883%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c477t-19c1b35c31bb77735e38776dadf0925a32920d553ba4b808f9e6057d74969b6d3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1722928883&rft_id=info:pmid/26386631&rfr_iscdi=true |