Loading…

Skin lesion classification using modified deep and multi-directional invariant handcrafted features

Skin lesions encompass various skin conditions, including cancerous growths resulting from uncontrolled proliferation of skin cells. Globally, this disease affects a significant portion of the population, with millions of fatalities recorded. Over the past three decades, there has been a concerning...

Full description

Saved in:
Bibliographic Details
Published in:Journal of network and computer applications 2024-11, Vol.231, p.103949, Article 103949
Main Authors: Pradhan, Jitesh, Singh, Ashish, Kumar, Abhinav, Khan, Muhammad Khurram
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c181t-5f8161340fcd70266648ac998ccb26d25b358b473e6306f98582e267bf1ababb3
container_end_page
container_issue
container_start_page 103949
container_title Journal of network and computer applications
container_volume 231
creator Pradhan, Jitesh
Singh, Ashish
Kumar, Abhinav
Khan, Muhammad Khurram
description Skin lesions encompass various skin conditions, including cancerous growths resulting from uncontrolled proliferation of skin cells. Globally, this disease affects a significant portion of the population, with millions of fatalities recorded. Over the past three decades, there has been a concerning escalation in diagnosed cases of skin cancer. Early detection is crucial for effective treatment, as late diagnosis significantly heightens mortality risk. Existing research often focuses on either handcrafted or deep features, neglecting the diverse textural and structural properties inherent in skin lesion images. Additionally, reliance on a single optimizer in CNN-based schemes poses efficiency challenges. To tackle these issues, this paper presents two novel approaches for classifying skin lesions in dermoscopic images to assess cancer severity. The first approach enhances classification accuracy by leveraging a modified VGG-16 network and employing both RMSProp and Adam optimizers. The second approach introduces a Hybrid CNN Model, integrating deep features from the modified VGG-16 network with handcrafted color and multi-directional texture features. Color features are extracted using a non-uniform cumulative probability-based histogram method, while texture features are derived from a 45∘ rotated complex wavelet filter-based dual-tree complex wavelet transform. The amalgamated features facilitate accurate prediction of skin lesion classes. Evaluation on ISIC 2017 skin cancer classification challenge images demonstrates significant performance enhancements over existing techniques.
doi_str_mv 10.1016/j.jnca.2024.103949
format article
fullrecord <record><control><sourceid>elsevier_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1016_j_jnca_2024_103949</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S1084804524001267</els_id><sourcerecordid>S1084804524001267</sourcerecordid><originalsourceid>FETCH-LOGICAL-c181t-5f8161340fcd70266648ac998ccb26d25b358b473e6306f98582e267bf1ababb3</originalsourceid><addsrcrecordid>eNp9kMtOwzAQRb0AiVL4AVb-gRS_4joSG1TxkiqxANaWH2NwSJ3KTirx9yQKa1ajGd0zmjkI3VCyoYTK23bTJmc2jDAxDXgjmjO0okSJShFRX6DLUlpCiBQNXyH39h0T7qDEPmHXmVJiiM4MczuWmD7xoffTCDz2AEdskseHsRti5WMGN-dMh2M6mRxNGvDXFHDZhGECAphhzFCu0HkwXYHrv7pGH48P77vnav_69LK731eOKjpUdVBUUi5IcH5LmJRSKOOaRjlnmfSstrxWVmw5SE5kaFStGDC5tYEaa6zla8SWvS73pWQI-pjjweQfTYme1ehWz2r0rEYvaiboboFguuwUIeviIiQHy3_a9_E__BdxFHDm</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Skin lesion classification using modified deep and multi-directional invariant handcrafted features</title><source>Elsevier</source><creator>Pradhan, Jitesh ; Singh, Ashish ; Kumar, Abhinav ; Khan, Muhammad Khurram</creator><creatorcontrib>Pradhan, Jitesh ; Singh, Ashish ; Kumar, Abhinav ; Khan, Muhammad Khurram</creatorcontrib><description>Skin lesions encompass various skin conditions, including cancerous growths resulting from uncontrolled proliferation of skin cells. Globally, this disease affects a significant portion of the population, with millions of fatalities recorded. Over the past three decades, there has been a concerning escalation in diagnosed cases of skin cancer. Early detection is crucial for effective treatment, as late diagnosis significantly heightens mortality risk. Existing research often focuses on either handcrafted or deep features, neglecting the diverse textural and structural properties inherent in skin lesion images. Additionally, reliance on a single optimizer in CNN-based schemes poses efficiency challenges. To tackle these issues, this paper presents two novel approaches for classifying skin lesions in dermoscopic images to assess cancer severity. The first approach enhances classification accuracy by leveraging a modified VGG-16 network and employing both RMSProp and Adam optimizers. The second approach introduces a Hybrid CNN Model, integrating deep features from the modified VGG-16 network with handcrafted color and multi-directional texture features. Color features are extracted using a non-uniform cumulative probability-based histogram method, while texture features are derived from a 45∘ rotated complex wavelet filter-based dual-tree complex wavelet transform. The amalgamated features facilitate accurate prediction of skin lesion classes. Evaluation on ISIC 2017 skin cancer classification challenge images demonstrates significant performance enhancements over existing techniques.</description><identifier>ISSN: 1084-8045</identifier><identifier>DOI: 10.1016/j.jnca.2024.103949</identifier><language>eng</language><publisher>Elsevier Ltd</publisher><subject>Complex wavelet transform ; Convolutional neural network ; Deep features ; Invariant features ; Probability-histogram ; Skin lesion</subject><ispartof>Journal of network and computer applications, 2024-11, Vol.231, p.103949, Article 103949</ispartof><rights>2024 Elsevier Ltd</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c181t-5f8161340fcd70266648ac998ccb26d25b358b473e6306f98582e267bf1ababb3</cites><orcidid>0000-0001-9367-7069</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>Pradhan, Jitesh</creatorcontrib><creatorcontrib>Singh, Ashish</creatorcontrib><creatorcontrib>Kumar, Abhinav</creatorcontrib><creatorcontrib>Khan, Muhammad Khurram</creatorcontrib><title>Skin lesion classification using modified deep and multi-directional invariant handcrafted features</title><title>Journal of network and computer applications</title><description>Skin lesions encompass various skin conditions, including cancerous growths resulting from uncontrolled proliferation of skin cells. Globally, this disease affects a significant portion of the population, with millions of fatalities recorded. Over the past three decades, there has been a concerning escalation in diagnosed cases of skin cancer. Early detection is crucial for effective treatment, as late diagnosis significantly heightens mortality risk. Existing research often focuses on either handcrafted or deep features, neglecting the diverse textural and structural properties inherent in skin lesion images. Additionally, reliance on a single optimizer in CNN-based schemes poses efficiency challenges. To tackle these issues, this paper presents two novel approaches for classifying skin lesions in dermoscopic images to assess cancer severity. The first approach enhances classification accuracy by leveraging a modified VGG-16 network and employing both RMSProp and Adam optimizers. The second approach introduces a Hybrid CNN Model, integrating deep features from the modified VGG-16 network with handcrafted color and multi-directional texture features. Color features are extracted using a non-uniform cumulative probability-based histogram method, while texture features are derived from a 45∘ rotated complex wavelet filter-based dual-tree complex wavelet transform. The amalgamated features facilitate accurate prediction of skin lesion classes. Evaluation on ISIC 2017 skin cancer classification challenge images demonstrates significant performance enhancements over existing techniques.</description><subject>Complex wavelet transform</subject><subject>Convolutional neural network</subject><subject>Deep features</subject><subject>Invariant features</subject><subject>Probability-histogram</subject><subject>Skin lesion</subject><issn>1084-8045</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kMtOwzAQRb0AiVL4AVb-gRS_4joSG1TxkiqxANaWH2NwSJ3KTirx9yQKa1ajGd0zmjkI3VCyoYTK23bTJmc2jDAxDXgjmjO0okSJShFRX6DLUlpCiBQNXyH39h0T7qDEPmHXmVJiiM4MczuWmD7xoffTCDz2AEdskseHsRti5WMGN-dMh2M6mRxNGvDXFHDZhGECAphhzFCu0HkwXYHrv7pGH48P77vnav_69LK731eOKjpUdVBUUi5IcH5LmJRSKOOaRjlnmfSstrxWVmw5SE5kaFStGDC5tYEaa6zla8SWvS73pWQI-pjjweQfTYme1ehWz2r0rEYvaiboboFguuwUIeviIiQHy3_a9_E__BdxFHDm</recordid><startdate>202411</startdate><enddate>202411</enddate><creator>Pradhan, Jitesh</creator><creator>Singh, Ashish</creator><creator>Kumar, Abhinav</creator><creator>Khan, Muhammad Khurram</creator><general>Elsevier Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0001-9367-7069</orcidid></search><sort><creationdate>202411</creationdate><title>Skin lesion classification using modified deep and multi-directional invariant handcrafted features</title><author>Pradhan, Jitesh ; Singh, Ashish ; Kumar, Abhinav ; Khan, Muhammad Khurram</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c181t-5f8161340fcd70266648ac998ccb26d25b358b473e6306f98582e267bf1ababb3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Complex wavelet transform</topic><topic>Convolutional neural network</topic><topic>Deep features</topic><topic>Invariant features</topic><topic>Probability-histogram</topic><topic>Skin lesion</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Pradhan, Jitesh</creatorcontrib><creatorcontrib>Singh, Ashish</creatorcontrib><creatorcontrib>Kumar, Abhinav</creatorcontrib><creatorcontrib>Khan, Muhammad Khurram</creatorcontrib><collection>CrossRef</collection><jtitle>Journal of network and computer applications</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Pradhan, Jitesh</au><au>Singh, Ashish</au><au>Kumar, Abhinav</au><au>Khan, Muhammad Khurram</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Skin lesion classification using modified deep and multi-directional invariant handcrafted features</atitle><jtitle>Journal of network and computer applications</jtitle><date>2024-11</date><risdate>2024</risdate><volume>231</volume><spage>103949</spage><pages>103949-</pages><artnum>103949</artnum><issn>1084-8045</issn><abstract>Skin lesions encompass various skin conditions, including cancerous growths resulting from uncontrolled proliferation of skin cells. Globally, this disease affects a significant portion of the population, with millions of fatalities recorded. Over the past three decades, there has been a concerning escalation in diagnosed cases of skin cancer. Early detection is crucial for effective treatment, as late diagnosis significantly heightens mortality risk. Existing research often focuses on either handcrafted or deep features, neglecting the diverse textural and structural properties inherent in skin lesion images. Additionally, reliance on a single optimizer in CNN-based schemes poses efficiency challenges. To tackle these issues, this paper presents two novel approaches for classifying skin lesions in dermoscopic images to assess cancer severity. The first approach enhances classification accuracy by leveraging a modified VGG-16 network and employing both RMSProp and Adam optimizers. The second approach introduces a Hybrid CNN Model, integrating deep features from the modified VGG-16 network with handcrafted color and multi-directional texture features. Color features are extracted using a non-uniform cumulative probability-based histogram method, while texture features are derived from a 45∘ rotated complex wavelet filter-based dual-tree complex wavelet transform. The amalgamated features facilitate accurate prediction of skin lesion classes. Evaluation on ISIC 2017 skin cancer classification challenge images demonstrates significant performance enhancements over existing techniques.</abstract><pub>Elsevier Ltd</pub><doi>10.1016/j.jnca.2024.103949</doi><orcidid>https://orcid.org/0000-0001-9367-7069</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 1084-8045
ispartof Journal of network and computer applications, 2024-11, Vol.231, p.103949, Article 103949
issn 1084-8045
language eng
recordid cdi_crossref_primary_10_1016_j_jnca_2024_103949
source Elsevier
subjects Complex wavelet transform
Convolutional neural network
Deep features
Invariant features
Probability-histogram
Skin lesion
title Skin lesion classification using modified deep and multi-directional invariant handcrafted features
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T06%3A51%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-elsevier_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Skin%20lesion%20classification%20using%20modified%20deep%20and%20multi-directional%20invariant%20handcrafted%20features&rft.jtitle=Journal%20of%20network%20and%20computer%20applications&rft.au=Pradhan,%20Jitesh&rft.date=2024-11&rft.volume=231&rft.spage=103949&rft.pages=103949-&rft.artnum=103949&rft.issn=1084-8045&rft_id=info:doi/10.1016/j.jnca.2024.103949&rft_dat=%3Celsevier_cross%3ES1084804524001267%3C/elsevier_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c181t-5f8161340fcd70266648ac998ccb26d25b358b473e6306f98582e267bf1ababb3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true