Generating Knowledge-Guided Discriminative Features Using Genetic Programming for Melanoma Detection

Melanoma is the deadliest form of skin cancer that causes around 75% of deaths worldwide. However, most of the skin cancers can be cured, especially if detected and treated early. Existing approaches have employed various feature extraction methods, where different types of features are used individ...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on emerging topics in computational intelligence 2021-08, Vol.5 (4), p.554-569
Hauptverfasser: Ain, Qurrat Ul, Al-Sahaf, Harith, Xue, Bing, Zhang, Mengjie
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 569
container_issue 4
container_start_page 554
container_title IEEE transactions on emerging topics in computational intelligence
container_volume 5
creator Ain, Qurrat Ul
Al-Sahaf, Harith
Xue, Bing
Zhang, Mengjie
description Melanoma is the deadliest form of skin cancer that causes around 75% of deaths worldwide. However, most of the skin cancers can be cured, especially if detected and treated early. Existing approaches have employed various feature extraction methods, where different types of features are used individually for skin image classification which may not provide sufficient information to the classification algorithm necessary to discriminate between classes, leading to sub-optimal performance. This study develops a novel skin image classification method using multi-tree genetic programming (GP). To capture local information from gray and color skin images, Local Binary Pattern is used in this work. In addition, for capturing global information, variation in color within the lesion and the skin regions, and domain-specific lesion border shape features are extracted. GP with a multi-tree representation is employed to use multiple types of features. Genetic operators such as crossover and mutation are designed accordingly in order to select a single type of features at terminals in one tree of the GP individual. The performance of the proposed method is assessed using two skin image datasets having images captured from multiple modalities, and compared with six most commonly used classification algorithms as well as the standard (single-tree) wrapper and embedded GP methods. The results show that the proposed method has significantly outperformed all these classification methods. Being interpretable and fast in terms of the computation time, this method can help dermatologist identify prominent skin image features, specific to a type of skin cancer in real-time situations.
doi_str_mv 10.1109/TETCI.2020.2983426
format Article
fullrecord <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_9072194</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9072194</ieee_id><sourcerecordid>2553593790</sourcerecordid><originalsourceid>FETCH-LOGICAL-c339t-ffdc4f33c9165855c31d0a8458e3223820c5556409432263a416c088a380b8813</originalsourceid><addsrcrecordid>eNpNUE1PAjEQbYwmEuQP6GUTz4v9XNqjAUEiRg-QeGtqd5aUsFtsdzX-e7tCjKf5em_mzUPomuAxIVjdrR_W0-WYYorHVEnGaXGGBpRPSE6leDv_l1-iUYw7jDFVgjDBB6hcQAPBtK7ZZk-N_9pDuYV80bkSymzmog2udk2af0I2B9N2AWK2iT28Z7bOZq_Bb4Op675X-ZA9w940vjbZDFqwrfPNFbqozD7C6BSHaDNPmh_z1ctiOb1f5ZYx1eZVVVpeMWYVKYQUwjJSYiO5kMAoZZJiK4QoOFY81QUznBQWS2mYxO9SEjZEt8e9h-A_Ooit3vkuNOmkpkIwodhE4YSiR5QNPsYAlT6kJ0341gTr3lD9a6juDdUnQxPp5khyAPBHUHhCSVLzA_DTcQc</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2553593790</pqid></control><display><type>article</type><title>Generating Knowledge-Guided Discriminative Features Using Genetic Programming for Melanoma Detection</title><source>IEEE Electronic Library (IEL)</source><creator>Ain, Qurrat Ul ; Al-Sahaf, Harith ; Xue, Bing ; Zhang, Mengjie</creator><creatorcontrib>Ain, Qurrat Ul ; Al-Sahaf, Harith ; Xue, Bing ; Zhang, Mengjie</creatorcontrib><description>Melanoma is the deadliest form of skin cancer that causes around 75% of deaths worldwide. However, most of the skin cancers can be cured, especially if detected and treated early. Existing approaches have employed various feature extraction methods, where different types of features are used individually for skin image classification which may not provide sufficient information to the classification algorithm necessary to discriminate between classes, leading to sub-optimal performance. This study develops a novel skin image classification method using multi-tree genetic programming (GP). To capture local information from gray and color skin images, Local Binary Pattern is used in this work. In addition, for capturing global information, variation in color within the lesion and the skin regions, and domain-specific lesion border shape features are extracted. GP with a multi-tree representation is employed to use multiple types of features. Genetic operators such as crossover and mutation are designed accordingly in order to select a single type of features at terminals in one tree of the GP individual. The performance of the proposed method is assessed using two skin image datasets having images captured from multiple modalities, and compared with six most commonly used classification algorithms as well as the standard (single-tree) wrapper and embedded GP methods. The results show that the proposed method has significantly outperformed all these classification methods. Being interpretable and fast in terms of the computation time, this method can help dermatologist identify prominent skin image features, specific to a type of skin cancer in real-time situations.</description><identifier>ISSN: 2471-285X</identifier><identifier>EISSN: 2471-285X</identifier><identifier>DOI: 10.1109/TETCI.2020.2983426</identifier><identifier>CODEN: ITETCU</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Cancer ; Classification ; Color ; feature construction ; Feature extraction ; feature selection ; Genetic algorithms ; Genetic programming ; Histograms ; Image classification ; Image color analysis ; Lesions ; Melanoma ; melanoma detection ; Skin ; Skin cancer</subject><ispartof>IEEE transactions on emerging topics in computational intelligence, 2021-08, Vol.5 (4), p.554-569</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c339t-ffdc4f33c9165855c31d0a8458e3223820c5556409432263a416c088a380b8813</citedby><cites>FETCH-LOGICAL-c339t-ffdc4f33c9165855c31d0a8458e3223820c5556409432263a416c088a380b8813</cites><orcidid>0000-0003-4463-9538 ; 0000-0003-4633-6135 ; 0000-0002-6891-9887 ; 0000-0002-4865-8026</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9072194$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27923,27924,54757</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9072194$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Ain, Qurrat Ul</creatorcontrib><creatorcontrib>Al-Sahaf, Harith</creatorcontrib><creatorcontrib>Xue, Bing</creatorcontrib><creatorcontrib>Zhang, Mengjie</creatorcontrib><title>Generating Knowledge-Guided Discriminative Features Using Genetic Programming for Melanoma Detection</title><title>IEEE transactions on emerging topics in computational intelligence</title><addtitle>TETCI</addtitle><description>Melanoma is the deadliest form of skin cancer that causes around 75% of deaths worldwide. However, most of the skin cancers can be cured, especially if detected and treated early. Existing approaches have employed various feature extraction methods, where different types of features are used individually for skin image classification which may not provide sufficient information to the classification algorithm necessary to discriminate between classes, leading to sub-optimal performance. This study develops a novel skin image classification method using multi-tree genetic programming (GP). To capture local information from gray and color skin images, Local Binary Pattern is used in this work. In addition, for capturing global information, variation in color within the lesion and the skin regions, and domain-specific lesion border shape features are extracted. GP with a multi-tree representation is employed to use multiple types of features. Genetic operators such as crossover and mutation are designed accordingly in order to select a single type of features at terminals in one tree of the GP individual. The performance of the proposed method is assessed using two skin image datasets having images captured from multiple modalities, and compared with six most commonly used classification algorithms as well as the standard (single-tree) wrapper and embedded GP methods. The results show that the proposed method has significantly outperformed all these classification methods. Being interpretable and fast in terms of the computation time, this method can help dermatologist identify prominent skin image features, specific to a type of skin cancer in real-time situations.</description><subject>Cancer</subject><subject>Classification</subject><subject>Color</subject><subject>feature construction</subject><subject>Feature extraction</subject><subject>feature selection</subject><subject>Genetic algorithms</subject><subject>Genetic programming</subject><subject>Histograms</subject><subject>Image classification</subject><subject>Image color analysis</subject><subject>Lesions</subject><subject>Melanoma</subject><subject>melanoma detection</subject><subject>Skin</subject><subject>Skin cancer</subject><issn>2471-285X</issn><issn>2471-285X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNUE1PAjEQbYwmEuQP6GUTz4v9XNqjAUEiRg-QeGtqd5aUsFtsdzX-e7tCjKf5em_mzUPomuAxIVjdrR_W0-WYYorHVEnGaXGGBpRPSE6leDv_l1-iUYw7jDFVgjDBB6hcQAPBtK7ZZk-N_9pDuYV80bkSymzmog2udk2af0I2B9N2AWK2iT28Z7bOZq_Bb4Op675X-ZA9w940vjbZDFqwrfPNFbqozD7C6BSHaDNPmh_z1ctiOb1f5ZYx1eZVVVpeMWYVKYQUwjJSYiO5kMAoZZJiK4QoOFY81QUznBQWS2mYxO9SEjZEt8e9h-A_Ooit3vkuNOmkpkIwodhE4YSiR5QNPsYAlT6kJ0341gTr3lD9a6juDdUnQxPp5khyAPBHUHhCSVLzA_DTcQc</recordid><startdate>20210801</startdate><enddate>20210801</enddate><creator>Ain, Qurrat Ul</creator><creator>Al-Sahaf, Harith</creator><creator>Xue, Bing</creator><creator>Zhang, Mengjie</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0003-4463-9538</orcidid><orcidid>https://orcid.org/0000-0003-4633-6135</orcidid><orcidid>https://orcid.org/0000-0002-6891-9887</orcidid><orcidid>https://orcid.org/0000-0002-4865-8026</orcidid></search><sort><creationdate>20210801</creationdate><title>Generating Knowledge-Guided Discriminative Features Using Genetic Programming for Melanoma Detection</title><author>Ain, Qurrat Ul ; Al-Sahaf, Harith ; Xue, Bing ; Zhang, Mengjie</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c339t-ffdc4f33c9165855c31d0a8458e3223820c5556409432263a416c088a380b8813</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Cancer</topic><topic>Classification</topic><topic>Color</topic><topic>feature construction</topic><topic>Feature extraction</topic><topic>feature selection</topic><topic>Genetic algorithms</topic><topic>Genetic programming</topic><topic>Histograms</topic><topic>Image classification</topic><topic>Image color analysis</topic><topic>Lesions</topic><topic>Melanoma</topic><topic>melanoma detection</topic><topic>Skin</topic><topic>Skin cancer</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ain, Qurrat Ul</creatorcontrib><creatorcontrib>Al-Sahaf, Harith</creatorcontrib><creatorcontrib>Xue, Bing</creatorcontrib><creatorcontrib>Zhang, Mengjie</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE transactions on emerging topics in computational intelligence</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ain, Qurrat Ul</au><au>Al-Sahaf, Harith</au><au>Xue, Bing</au><au>Zhang, Mengjie</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Generating Knowledge-Guided Discriminative Features Using Genetic Programming for Melanoma Detection</atitle><jtitle>IEEE transactions on emerging topics in computational intelligence</jtitle><stitle>TETCI</stitle><date>2021-08-01</date><risdate>2021</risdate><volume>5</volume><issue>4</issue><spage>554</spage><epage>569</epage><pages>554-569</pages><issn>2471-285X</issn><eissn>2471-285X</eissn><coden>ITETCU</coden><abstract>Melanoma is the deadliest form of skin cancer that causes around 75% of deaths worldwide. However, most of the skin cancers can be cured, especially if detected and treated early. Existing approaches have employed various feature extraction methods, where different types of features are used individually for skin image classification which may not provide sufficient information to the classification algorithm necessary to discriminate between classes, leading to sub-optimal performance. This study develops a novel skin image classification method using multi-tree genetic programming (GP). To capture local information from gray and color skin images, Local Binary Pattern is used in this work. In addition, for capturing global information, variation in color within the lesion and the skin regions, and domain-specific lesion border shape features are extracted. GP with a multi-tree representation is employed to use multiple types of features. Genetic operators such as crossover and mutation are designed accordingly in order to select a single type of features at terminals in one tree of the GP individual. The performance of the proposed method is assessed using two skin image datasets having images captured from multiple modalities, and compared with six most commonly used classification algorithms as well as the standard (single-tree) wrapper and embedded GP methods. The results show that the proposed method has significantly outperformed all these classification methods. Being interpretable and fast in terms of the computation time, this method can help dermatologist identify prominent skin image features, specific to a type of skin cancer in real-time situations.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/TETCI.2020.2983426</doi><tpages>16</tpages><orcidid>https://orcid.org/0000-0003-4463-9538</orcidid><orcidid>https://orcid.org/0000-0003-4633-6135</orcidid><orcidid>https://orcid.org/0000-0002-6891-9887</orcidid><orcidid>https://orcid.org/0000-0002-4865-8026</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 2471-285X
ispartof IEEE transactions on emerging topics in computational intelligence, 2021-08, Vol.5 (4), p.554-569
issn 2471-285X
2471-285X
language eng
recordid cdi_ieee_primary_9072194
source IEEE Electronic Library (IEL)
subjects Cancer
Classification
Color
feature construction
Feature extraction
feature selection
Genetic algorithms
Genetic programming
Histograms
Image classification
Image color analysis
Lesions
Melanoma
melanoma detection
Skin
Skin cancer
title Generating Knowledge-Guided Discriminative Features Using Genetic Programming for Melanoma Detection
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T08%3A14%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Generating%20Knowledge-Guided%20Discriminative%20Features%20Using%20Genetic%20Programming%20for%20Melanoma%20Detection&rft.jtitle=IEEE%20transactions%20on%20emerging%20topics%20in%20computational%20intelligence&rft.au=Ain,%20Qurrat%20Ul&rft.date=2021-08-01&rft.volume=5&rft.issue=4&rft.spage=554&rft.epage=569&rft.pages=554-569&rft.issn=2471-285X&rft.eissn=2471-285X&rft.coden=ITETCU&rft_id=info:doi/10.1109/TETCI.2020.2983426&rft_dat=%3Cproquest_RIE%3E2553593790%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2553593790&rft_id=info:pmid/&rft_ieee_id=9072194&rfr_iscdi=true