Loading…
Lungs cancer classification from CT images: An integrated design of contrast based classical features fusion and selection
•Contrast is enhance through gamma correction max intensity weights (GCmIW) approach.•Multiple features are fused through a serially canonical correlation-based approach.•Zero features are removed through entropy value.•Weighted neighborhood component analysis based features selected. Lung cancer is...
Saved in:
Published in: | Pattern recognition letters 2020-01, Vol.129, p.77-85 |
---|---|
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-c400t-8221ef7fb74a93278299f540326951afe9c2af4a58cb7bbaaf50f74e746e685f3 |
---|---|
cites | cdi_FETCH-LOGICAL-c400t-8221ef7fb74a93278299f540326951afe9c2af4a58cb7bbaaf50f74e746e685f3 |
container_end_page | 85 |
container_issue | |
container_start_page | 77 |
container_title | Pattern recognition letters |
container_volume | 129 |
creator | Khan, M. Attique Rubab, S. Kashif, Asifa Sharif, Muhammad Imran Muhammad, Nazeer Shah, Jamal Hussain Zhang, Yu-Dong Satapathy, Suresh Chandra |
description | •Contrast is enhance through gamma correction max intensity weights (GCmIW) approach.•Multiple features are fused through a serially canonical correlation-based approach.•Zero features are removed through entropy value.•Weighted neighborhood component analysis based features selected.
Lung cancer is a fatal type of cancer and it causes of severe deaths of approximately 422 people every day, worldwide. However, an early diagnosis is an expedient requirement for increasing the chances of human survival. In this regard the existing techniques of tumor detection, CT scans are mostly utilized to recognize the infected regions, nevertheless, the major challenges of CT images are low visibility of tumor regions, negative rates, to name but a few. In this work, we propose a novel design of contrast stretching based classical features fusion process for localizing the of lungs cancer classification. The proposed method encompasses three significant steps: firstly, contrast of original CT images is improved by gamma correction max intensity weights approach. Secondly, multiple texture, point, and geometric features are extracted from contrast images, which are later subjected to a serial canonical correlation-based fusion. Thirdly, zero values and negative features are replaced by an entropy-based approach, followed by weighted NCA for selection. Most discriminate features are fed into ensemble classifier for final classification. The validation of the proposed method is conducted on publicly available dataset: Lungs Data Science Bowl 2017 to achieving maximum accuracy of 99.4%. The numerical results clearly show that the performance of our proposed method outperforms in comparison with several existing methods with greater accuracy. |
doi_str_mv | 10.1016/j.patrec.2019.11.014 |
format | article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2352358457</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0167865519303289</els_id><sourcerecordid>2352358457</sourcerecordid><originalsourceid>FETCH-LOGICAL-c400t-8221ef7fb74a93278299f540326951afe9c2af4a58cb7bbaaf50f74e746e685f3</originalsourceid><addsrcrecordid>eNp9kE1r3DAQhkVoIdu0_6AHQc92JVmy7BwKYekXLOSSnMVYHi1aNvJGIxfaX18t7rkwMId55xnmYeyjFK0Usv98ai9QMvpWCTm2UrZC6hu2k4NVje20fsN2NWaboTfmlr0jOgkh-m4cduzPYU1H4h6Sx8z9GYhiiB5KXBIPeXnh-yceX-CIdM8fEo-p4DFDwZnPSPGY-BK4X1LJQIVPQHWwUTyceUAoa0biYaUrENLMCc_or_j37G2AM-GHf_2OPX_7-rT_0Rwev__cPxwar4UozaCUxGDDZDWMnbKDGsdgtOhUPxoJAUevIGgwg5_sNAEEI4LVaHWP_WBCd8c-bdxLXl5XpOJOy5pTPelUZ2oN2tia0lvK54UoY3CXXP_Ov50U7mrZndxm2V0tOyldtVzXvmxrWD_4FTE78hGrzDnWaHHzEv8P-AuSrYlj</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2352358457</pqid></control><display><type>article</type><title>Lungs cancer classification from CT images: An integrated design of contrast based classical features fusion and selection</title><source>ScienceDirect Freedom Collection</source><creator>Khan, M. Attique ; Rubab, S. ; Kashif, Asifa ; Sharif, Muhammad Imran ; Muhammad, Nazeer ; Shah, Jamal Hussain ; Zhang, Yu-Dong ; Satapathy, Suresh Chandra</creator><creatorcontrib>Khan, M. Attique ; Rubab, S. ; Kashif, Asifa ; Sharif, Muhammad Imran ; Muhammad, Nazeer ; Shah, Jamal Hussain ; Zhang, Yu-Dong ; Satapathy, Suresh Chandra</creatorcontrib><description>•Contrast is enhance through gamma correction max intensity weights (GCmIW) approach.•Multiple features are fused through a serially canonical correlation-based approach.•Zero features are removed through entropy value.•Weighted neighborhood component analysis based features selected.
Lung cancer is a fatal type of cancer and it causes of severe deaths of approximately 422 people every day, worldwide. However, an early diagnosis is an expedient requirement for increasing the chances of human survival. In this regard the existing techniques of tumor detection, CT scans are mostly utilized to recognize the infected regions, nevertheless, the major challenges of CT images are low visibility of tumor regions, negative rates, to name but a few. In this work, we propose a novel design of contrast stretching based classical features fusion process for localizing the of lungs cancer classification. The proposed method encompasses three significant steps: firstly, contrast of original CT images is improved by gamma correction max intensity weights approach. Secondly, multiple texture, point, and geometric features are extracted from contrast images, which are later subjected to a serial canonical correlation-based fusion. Thirdly, zero values and negative features are replaced by an entropy-based approach, followed by weighted NCA for selection. Most discriminate features are fed into ensemble classifier for final classification. The validation of the proposed method is conducted on publicly available dataset: Lungs Data Science Bowl 2017 to achieving maximum accuracy of 99.4%. The numerical results clearly show that the performance of our proposed method outperforms in comparison with several existing methods with greater accuracy.</description><identifier>ISSN: 0167-8655</identifier><identifier>EISSN: 1872-7344</identifier><identifier>DOI: 10.1016/j.patrec.2019.11.014</identifier><language>eng</language><publisher>Amsterdam: Elsevier B.V</publisher><subject>Cancer ; Classification ; Computed tomography ; Contrast normalization ; Entropy ; Feature extraction ; Fusion ; Image classification ; Image contrast ; Low visibility ; Lung cancer ; Lungs ; Lungs cancer ; Medical imaging ; Multiple features ; Selection ; Tumors</subject><ispartof>Pattern recognition letters, 2020-01, Vol.129, p.77-85</ispartof><rights>2019 Elsevier B.V.</rights><rights>Copyright Elsevier Science Ltd. Jan 2020</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c400t-8221ef7fb74a93278299f540326951afe9c2af4a58cb7bbaaf50f74e746e685f3</citedby><cites>FETCH-LOGICAL-c400t-8221ef7fb74a93278299f540326951afe9c2af4a58cb7bbaaf50f74e746e685f3</cites><orcidid>0000-0002-4870-1493 ; 0000-0002-7903-9391</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></links><search><creatorcontrib>Khan, M. Attique</creatorcontrib><creatorcontrib>Rubab, S.</creatorcontrib><creatorcontrib>Kashif, Asifa</creatorcontrib><creatorcontrib>Sharif, Muhammad Imran</creatorcontrib><creatorcontrib>Muhammad, Nazeer</creatorcontrib><creatorcontrib>Shah, Jamal Hussain</creatorcontrib><creatorcontrib>Zhang, Yu-Dong</creatorcontrib><creatorcontrib>Satapathy, Suresh Chandra</creatorcontrib><title>Lungs cancer classification from CT images: An integrated design of contrast based classical features fusion and selection</title><title>Pattern recognition letters</title><description>•Contrast is enhance through gamma correction max intensity weights (GCmIW) approach.•Multiple features are fused through a serially canonical correlation-based approach.•Zero features are removed through entropy value.•Weighted neighborhood component analysis based features selected.
Lung cancer is a fatal type of cancer and it causes of severe deaths of approximately 422 people every day, worldwide. However, an early diagnosis is an expedient requirement for increasing the chances of human survival. In this regard the existing techniques of tumor detection, CT scans are mostly utilized to recognize the infected regions, nevertheless, the major challenges of CT images are low visibility of tumor regions, negative rates, to name but a few. In this work, we propose a novel design of contrast stretching based classical features fusion process for localizing the of lungs cancer classification. The proposed method encompasses three significant steps: firstly, contrast of original CT images is improved by gamma correction max intensity weights approach. Secondly, multiple texture, point, and geometric features are extracted from contrast images, which are later subjected to a serial canonical correlation-based fusion. Thirdly, zero values and negative features are replaced by an entropy-based approach, followed by weighted NCA for selection. Most discriminate features are fed into ensemble classifier for final classification. The validation of the proposed method is conducted on publicly available dataset: Lungs Data Science Bowl 2017 to achieving maximum accuracy of 99.4%. The numerical results clearly show that the performance of our proposed method outperforms in comparison with several existing methods with greater accuracy.</description><subject>Cancer</subject><subject>Classification</subject><subject>Computed tomography</subject><subject>Contrast normalization</subject><subject>Entropy</subject><subject>Feature extraction</subject><subject>Fusion</subject><subject>Image classification</subject><subject>Image contrast</subject><subject>Low visibility</subject><subject>Lung cancer</subject><subject>Lungs</subject><subject>Lungs cancer</subject><subject>Medical imaging</subject><subject>Multiple features</subject><subject>Selection</subject><subject>Tumors</subject><issn>0167-8655</issn><issn>1872-7344</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNp9kE1r3DAQhkVoIdu0_6AHQc92JVmy7BwKYekXLOSSnMVYHi1aNvJGIxfaX18t7rkwMId55xnmYeyjFK0Usv98ai9QMvpWCTm2UrZC6hu2k4NVje20fsN2NWaboTfmlr0jOgkh-m4cduzPYU1H4h6Sx8z9GYhiiB5KXBIPeXnh-yceX-CIdM8fEo-p4DFDwZnPSPGY-BK4X1LJQIVPQHWwUTyceUAoa0biYaUrENLMCc_or_j37G2AM-GHf_2OPX_7-rT_0Rwev__cPxwar4UozaCUxGDDZDWMnbKDGsdgtOhUPxoJAUevIGgwg5_sNAEEI4LVaHWP_WBCd8c-bdxLXl5XpOJOy5pTPelUZ2oN2tia0lvK54UoY3CXXP_Ov50U7mrZndxm2V0tOyldtVzXvmxrWD_4FTE78hGrzDnWaHHzEv8P-AuSrYlj</recordid><startdate>202001</startdate><enddate>202001</enddate><creator>Khan, M. Attique</creator><creator>Rubab, S.</creator><creator>Kashif, Asifa</creator><creator>Sharif, Muhammad Imran</creator><creator>Muhammad, Nazeer</creator><creator>Shah, Jamal Hussain</creator><creator>Zhang, Yu-Dong</creator><creator>Satapathy, Suresh Chandra</creator><general>Elsevier B.V</general><general>Elsevier Science Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7TK</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-4870-1493</orcidid><orcidid>https://orcid.org/0000-0002-7903-9391</orcidid></search><sort><creationdate>202001</creationdate><title>Lungs cancer classification from CT images: An integrated design of contrast based classical features fusion and selection</title><author>Khan, M. Attique ; Rubab, S. ; Kashif, Asifa ; Sharif, Muhammad Imran ; Muhammad, Nazeer ; Shah, Jamal Hussain ; Zhang, Yu-Dong ; Satapathy, Suresh Chandra</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c400t-8221ef7fb74a93278299f540326951afe9c2af4a58cb7bbaaf50f74e746e685f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Cancer</topic><topic>Classification</topic><topic>Computed tomography</topic><topic>Contrast normalization</topic><topic>Entropy</topic><topic>Feature extraction</topic><topic>Fusion</topic><topic>Image classification</topic><topic>Image contrast</topic><topic>Low visibility</topic><topic>Lung cancer</topic><topic>Lungs</topic><topic>Lungs cancer</topic><topic>Medical imaging</topic><topic>Multiple features</topic><topic>Selection</topic><topic>Tumors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Khan, M. Attique</creatorcontrib><creatorcontrib>Rubab, S.</creatorcontrib><creatorcontrib>Kashif, Asifa</creatorcontrib><creatorcontrib>Sharif, Muhammad Imran</creatorcontrib><creatorcontrib>Muhammad, Nazeer</creatorcontrib><creatorcontrib>Shah, Jamal Hussain</creatorcontrib><creatorcontrib>Zhang, Yu-Dong</creatorcontrib><creatorcontrib>Satapathy, Suresh Chandra</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Neurosciences Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Pattern recognition letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Khan, M. Attique</au><au>Rubab, S.</au><au>Kashif, Asifa</au><au>Sharif, Muhammad Imran</au><au>Muhammad, Nazeer</au><au>Shah, Jamal Hussain</au><au>Zhang, Yu-Dong</au><au>Satapathy, Suresh Chandra</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Lungs cancer classification from CT images: An integrated design of contrast based classical features fusion and selection</atitle><jtitle>Pattern recognition letters</jtitle><date>2020-01</date><risdate>2020</risdate><volume>129</volume><spage>77</spage><epage>85</epage><pages>77-85</pages><issn>0167-8655</issn><eissn>1872-7344</eissn><abstract>•Contrast is enhance through gamma correction max intensity weights (GCmIW) approach.•Multiple features are fused through a serially canonical correlation-based approach.•Zero features are removed through entropy value.•Weighted neighborhood component analysis based features selected.
Lung cancer is a fatal type of cancer and it causes of severe deaths of approximately 422 people every day, worldwide. However, an early diagnosis is an expedient requirement for increasing the chances of human survival. In this regard the existing techniques of tumor detection, CT scans are mostly utilized to recognize the infected regions, nevertheless, the major challenges of CT images are low visibility of tumor regions, negative rates, to name but a few. In this work, we propose a novel design of contrast stretching based classical features fusion process for localizing the of lungs cancer classification. The proposed method encompasses three significant steps: firstly, contrast of original CT images is improved by gamma correction max intensity weights approach. Secondly, multiple texture, point, and geometric features are extracted from contrast images, which are later subjected to a serial canonical correlation-based fusion. Thirdly, zero values and negative features are replaced by an entropy-based approach, followed by weighted NCA for selection. Most discriminate features are fed into ensemble classifier for final classification. The validation of the proposed method is conducted on publicly available dataset: Lungs Data Science Bowl 2017 to achieving maximum accuracy of 99.4%. The numerical results clearly show that the performance of our proposed method outperforms in comparison with several existing methods with greater accuracy.</abstract><cop>Amsterdam</cop><pub>Elsevier B.V</pub><doi>10.1016/j.patrec.2019.11.014</doi><tpages>9</tpages><orcidid>https://orcid.org/0000-0002-4870-1493</orcidid><orcidid>https://orcid.org/0000-0002-7903-9391</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0167-8655 |
ispartof | Pattern recognition letters, 2020-01, Vol.129, p.77-85 |
issn | 0167-8655 1872-7344 |
language | eng |
recordid | cdi_proquest_journals_2352358457 |
source | ScienceDirect Freedom Collection |
subjects | Cancer Classification Computed tomography Contrast normalization Entropy Feature extraction Fusion Image classification Image contrast Low visibility Lung cancer Lungs Lungs cancer Medical imaging Multiple features Selection Tumors |
title | Lungs cancer classification from CT images: An integrated design of contrast based classical features fusion and selection |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T06%3A12%3A01IST&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=Lungs%20cancer%20classification%20from%20CT%20images:%20An%20integrated%20design%20of%20contrast%20based%20classical%20features%20fusion%20and%20selection&rft.jtitle=Pattern%20recognition%20letters&rft.au=Khan,%20M.%20Attique&rft.date=2020-01&rft.volume=129&rft.spage=77&rft.epage=85&rft.pages=77-85&rft.issn=0167-8655&rft.eissn=1872-7344&rft_id=info:doi/10.1016/j.patrec.2019.11.014&rft_dat=%3Cproquest_cross%3E2352358457%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c400t-8221ef7fb74a93278299f540326951afe9c2af4a58cb7bbaaf50f74e746e685f3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2352358457&rft_id=info:pmid/&rfr_iscdi=true |