EFAM-Net: A Multi-Class Skin Lesion Classification Model Utilizing Enhanced Feature Fusion and Attention Mechanisms

Skin cancer caused by common malignant tumors is a major threat to the health of patients. Automated classification of skin lesions using computer algorithms is crucial for enhancing diagnostic efficiency and reducing mortality rates associated with skin cancer. Enhancing the capabilities of image c...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE access 2024, Vol.12, p.143029-143041
Hauptverfasser: Ji, Zhanlin, Wang, Xuan, Liu, Chunling, Wang, Zhiwu, Yuan, Na, Ganchev, Ivan
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 143041
container_issue
container_start_page 143029
container_title IEEE access
container_volume 12
creator Ji, Zhanlin
Wang, Xuan
Liu, Chunling
Wang, Zhiwu
Yuan, Na
Ganchev, Ivan
description Skin cancer caused by common malignant tumors is a major threat to the health of patients. Automated classification of skin lesions using computer algorithms is crucial for enhancing diagnostic efficiency and reducing mortality rates associated with skin cancer. Enhancing the capabilities of image classification models for skin lesions is essential to assist in accurately classifying skin diseases of patients. Aiming at this goal, a novel EFAM-Net model is proposed in this paper for the skin lesion classification task. Firstly, a newly designed Attention Residual Learning ConvNeXt (ARLC) block is used to extract low-level features such as colors and textures in images. Then, the deep-layer blocks of the network are replaced with a newly designed Parallel ConvNeXt (PCNXt) block, allowing to capture richer and more complex features. Additionally, another newly designed Multi-scale Efficient Attention Feature Fusion (MEAFF) block enhances feature extraction at various scales, allowing the model to effectively capture more comprehensive features in specific layers, fuse feature maps of different scales and enhance feature reuse at the end. EFAM-Net is experimentally evaluated on the ISIC 2019 and HAM10000 public datasets, as well as on a private dataset. The obtained results show that EFAM-Net achieves top classification performance among all compared models, by achieving overall accuracy of 92.30%, 93.95%, and 94.31% on the ISIC 2019, HAM10000, and private dataset, respectively.
doi_str_mv 10.1109/ACCESS.2024.3468612
format Article
fullrecord <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_proquest_journals_3114560686</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10695064</ieee_id><doaj_id>oai_doaj_org_article_58be92bcb7de46f097b5d1ff5c3a52ec</doaj_id><sourcerecordid>3114560686</sourcerecordid><originalsourceid>FETCH-LOGICAL-c289t-848150dbd8fca5478af75beb569b564e9c9b67a72ffd2795114cfce70726f4c13</originalsourceid><addsrcrecordid>eNpNUU1v1DAUjBBIVG1_ARwscc5iO_6IuUXRLlTahcPSs-XYz8VLmhTbOcCvx7upqlqy_N5oZt6Tp6o-ELwhBKvPXd9vj8cNxZRtGiZaQeib6ooSoeqGN-Ltq_p9dZvSCZfTFojLqyptd92h_g75C-rQYRlzqPvRpISOv8OE9pDCPKELEnywJp_bw-xgRPc5jOFfmB7QdvplJgsO7cDkJQLaLReZmRzqcoZpVYEttJAe0031zpsxwe3ze13d77Y_-2_1_sfXu77b15a2KtctawnHbnCtt4Yz2Rov-QADF6pcBsqqQUgjqfeOSsUJYdZbkFhS4ZklzXV1t_q62Zz0UwyPJv7Vswn6AszxQZuYgx1B83YARQc7SAdMeKzkwB3xntvGcAq2eH1avZ7i_GeBlPVpXuJU1tdNGcwFLh9fWM3KsnFOKYJ_mUqwPoel17D0OSz9HFZRfVxVAQBeKUpCWLDmP51ykMQ</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3114560686</pqid></control><display><type>article</type><title>EFAM-Net: A Multi-Class Skin Lesion Classification Model Utilizing Enhanced Feature Fusion and Attention Mechanisms</title><source>IEEE Open Access Journals</source><source>DOAJ Directory of Open Access Journals</source><source>EZB-FREE-00999 freely available EZB journals</source><creator>Ji, Zhanlin ; Wang, Xuan ; Liu, Chunling ; Wang, Zhiwu ; Yuan, Na ; Ganchev, Ivan</creator><creatorcontrib>Ji, Zhanlin ; Wang, Xuan ; Liu, Chunling ; Wang, Zhiwu ; Yuan, Na ; Ganchev, Ivan</creatorcontrib><description>Skin cancer caused by common malignant tumors is a major threat to the health of patients. Automated classification of skin lesions using computer algorithms is crucial for enhancing diagnostic efficiency and reducing mortality rates associated with skin cancer. Enhancing the capabilities of image classification models for skin lesions is essential to assist in accurately classifying skin diseases of patients. Aiming at this goal, a novel EFAM-Net model is proposed in this paper for the skin lesion classification task. Firstly, a newly designed Attention Residual Learning ConvNeXt (ARLC) block is used to extract low-level features such as colors and textures in images. Then, the deep-layer blocks of the network are replaced with a newly designed Parallel ConvNeXt (PCNXt) block, allowing to capture richer and more complex features. Additionally, another newly designed Multi-scale Efficient Attention Feature Fusion (MEAFF) block enhances feature extraction at various scales, allowing the model to effectively capture more comprehensive features in specific layers, fuse feature maps of different scales and enhance feature reuse at the end. EFAM-Net is experimentally evaluated on the ISIC 2019 and HAM10000 public datasets, as well as on a private dataset. The obtained results show that EFAM-Net achieves top classification performance among all compared models, by achieving overall accuracy of 92.30%, 93.95%, and 94.31% on the ISIC 2019, HAM10000, and private dataset, respectively.</description><identifier>ISSN: 2169-3536</identifier><identifier>EISSN: 2169-3536</identifier><identifier>DOI: 10.1109/ACCESS.2024.3468612</identifier><identifier>CODEN: IAECCG</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Accuracy ; Algorithms ; Cancer ; Cancer detection ; Classification ; Computational modeling ; ConvNeXt ; Datasets ; Deep learning ; EFAM-Net ; Feature extraction ; Feature maps ; HAM10000 ; Image classification ; Image enhancement ; ISIC 2019 ; lesion classification ; Lesions ; Medical imaging ; Skin ; Skin cancer</subject><ispartof>IEEE access, 2024, Vol.12, p.143029-143041</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c289t-848150dbd8fca5478af75beb569b564e9c9b67a72ffd2795114cfce70726f4c13</cites><orcidid>0000-0003-3527-3773 ; 0000-0003-0535-7087 ; 0000-0003-3904-4513</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10695064$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,864,2102,4024,27633,27923,27924,27925,54933</link.rule.ids></links><search><creatorcontrib>Ji, Zhanlin</creatorcontrib><creatorcontrib>Wang, Xuan</creatorcontrib><creatorcontrib>Liu, Chunling</creatorcontrib><creatorcontrib>Wang, Zhiwu</creatorcontrib><creatorcontrib>Yuan, Na</creatorcontrib><creatorcontrib>Ganchev, Ivan</creatorcontrib><title>EFAM-Net: A Multi-Class Skin Lesion Classification Model Utilizing Enhanced Feature Fusion and Attention Mechanisms</title><title>IEEE access</title><addtitle>Access</addtitle><description>Skin cancer caused by common malignant tumors is a major threat to the health of patients. Automated classification of skin lesions using computer algorithms is crucial for enhancing diagnostic efficiency and reducing mortality rates associated with skin cancer. Enhancing the capabilities of image classification models for skin lesions is essential to assist in accurately classifying skin diseases of patients. Aiming at this goal, a novel EFAM-Net model is proposed in this paper for the skin lesion classification task. Firstly, a newly designed Attention Residual Learning ConvNeXt (ARLC) block is used to extract low-level features such as colors and textures in images. Then, the deep-layer blocks of the network are replaced with a newly designed Parallel ConvNeXt (PCNXt) block, allowing to capture richer and more complex features. Additionally, another newly designed Multi-scale Efficient Attention Feature Fusion (MEAFF) block enhances feature extraction at various scales, allowing the model to effectively capture more comprehensive features in specific layers, fuse feature maps of different scales and enhance feature reuse at the end. EFAM-Net is experimentally evaluated on the ISIC 2019 and HAM10000 public datasets, as well as on a private dataset. The obtained results show that EFAM-Net achieves top classification performance among all compared models, by achieving overall accuracy of 92.30%, 93.95%, and 94.31% on the ISIC 2019, HAM10000, and private dataset, respectively.</description><subject>Accuracy</subject><subject>Algorithms</subject><subject>Cancer</subject><subject>Cancer detection</subject><subject>Classification</subject><subject>Computational modeling</subject><subject>ConvNeXt</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>EFAM-Net</subject><subject>Feature extraction</subject><subject>Feature maps</subject><subject>HAM10000</subject><subject>Image classification</subject><subject>Image enhancement</subject><subject>ISIC 2019</subject><subject>lesion classification</subject><subject>Lesions</subject><subject>Medical imaging</subject><subject>Skin</subject><subject>Skin cancer</subject><issn>2169-3536</issn><issn>2169-3536</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><sourceid>DOA</sourceid><recordid>eNpNUU1v1DAUjBBIVG1_ARwscc5iO_6IuUXRLlTahcPSs-XYz8VLmhTbOcCvx7upqlqy_N5oZt6Tp6o-ELwhBKvPXd9vj8cNxZRtGiZaQeib6ooSoeqGN-Ltq_p9dZvSCZfTFojLqyptd92h_g75C-rQYRlzqPvRpISOv8OE9pDCPKELEnywJp_bw-xgRPc5jOFfmB7QdvplJgsO7cDkJQLaLReZmRzqcoZpVYEttJAe0031zpsxwe3ze13d77Y_-2_1_sfXu77b15a2KtctawnHbnCtt4Yz2Rov-QADF6pcBsqqQUgjqfeOSsUJYdZbkFhS4ZklzXV1t_q62Zz0UwyPJv7Vswn6AszxQZuYgx1B83YARQc7SAdMeKzkwB3xntvGcAq2eH1avZ7i_GeBlPVpXuJU1tdNGcwFLh9fWM3KsnFOKYJ_mUqwPoel17D0OSz9HFZRfVxVAQBeKUpCWLDmP51ykMQ</recordid><startdate>2024</startdate><enddate>2024</enddate><creator>Ji, Zhanlin</creator><creator>Wang, Xuan</creator><creator>Liu, Chunling</creator><creator>Wang, Zhiwu</creator><creator>Yuan, Na</creator><creator>Ganchev, Ivan</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7SR</scope><scope>8BQ</scope><scope>8FD</scope><scope>JG9</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0003-3527-3773</orcidid><orcidid>https://orcid.org/0000-0003-0535-7087</orcidid><orcidid>https://orcid.org/0000-0003-3904-4513</orcidid></search><sort><creationdate>2024</creationdate><title>EFAM-Net: A Multi-Class Skin Lesion Classification Model Utilizing Enhanced Feature Fusion and Attention Mechanisms</title><author>Ji, Zhanlin ; Wang, Xuan ; Liu, Chunling ; Wang, Zhiwu ; Yuan, Na ; Ganchev, Ivan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c289t-848150dbd8fca5478af75beb569b564e9c9b67a72ffd2795114cfce70726f4c13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Algorithms</topic><topic>Cancer</topic><topic>Cancer detection</topic><topic>Classification</topic><topic>Computational modeling</topic><topic>ConvNeXt</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>EFAM-Net</topic><topic>Feature extraction</topic><topic>Feature maps</topic><topic>HAM10000</topic><topic>Image classification</topic><topic>Image enhancement</topic><topic>ISIC 2019</topic><topic>lesion classification</topic><topic>Lesions</topic><topic>Medical imaging</topic><topic>Skin</topic><topic>Skin cancer</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ji, Zhanlin</creatorcontrib><creatorcontrib>Wang, Xuan</creatorcontrib><creatorcontrib>Liu, Chunling</creatorcontrib><creatorcontrib>Wang, Zhiwu</creatorcontrib><creatorcontrib>Yuan, Na</creatorcontrib><creatorcontrib>Ganchev, Ivan</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>Materials 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><collection>DOAJ Directory of Open Access Journals</collection><jtitle>IEEE access</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ji, Zhanlin</au><au>Wang, Xuan</au><au>Liu, Chunling</au><au>Wang, Zhiwu</au><au>Yuan, Na</au><au>Ganchev, Ivan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>EFAM-Net: A Multi-Class Skin Lesion Classification Model Utilizing Enhanced Feature Fusion and Attention Mechanisms</atitle><jtitle>IEEE access</jtitle><stitle>Access</stitle><date>2024</date><risdate>2024</risdate><volume>12</volume><spage>143029</spage><epage>143041</epage><pages>143029-143041</pages><issn>2169-3536</issn><eissn>2169-3536</eissn><coden>IAECCG</coden><abstract>Skin cancer caused by common malignant tumors is a major threat to the health of patients. Automated classification of skin lesions using computer algorithms is crucial for enhancing diagnostic efficiency and reducing mortality rates associated with skin cancer. Enhancing the capabilities of image classification models for skin lesions is essential to assist in accurately classifying skin diseases of patients. Aiming at this goal, a novel EFAM-Net model is proposed in this paper for the skin lesion classification task. Firstly, a newly designed Attention Residual Learning ConvNeXt (ARLC) block is used to extract low-level features such as colors and textures in images. Then, the deep-layer blocks of the network are replaced with a newly designed Parallel ConvNeXt (PCNXt) block, allowing to capture richer and more complex features. Additionally, another newly designed Multi-scale Efficient Attention Feature Fusion (MEAFF) block enhances feature extraction at various scales, allowing the model to effectively capture more comprehensive features in specific layers, fuse feature maps of different scales and enhance feature reuse at the end. EFAM-Net is experimentally evaluated on the ISIC 2019 and HAM10000 public datasets, as well as on a private dataset. The obtained results show that EFAM-Net achieves top classification performance among all compared models, by achieving overall accuracy of 92.30%, 93.95%, and 94.31% on the ISIC 2019, HAM10000, and private dataset, respectively.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/ACCESS.2024.3468612</doi><tpages>13</tpages><orcidid>https://orcid.org/0000-0003-3527-3773</orcidid><orcidid>https://orcid.org/0000-0003-0535-7087</orcidid><orcidid>https://orcid.org/0000-0003-3904-4513</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2169-3536
ispartof IEEE access, 2024, Vol.12, p.143029-143041
issn 2169-3536
2169-3536
language eng
recordid cdi_proquest_journals_3114560686
source IEEE Open Access Journals; DOAJ Directory of Open Access Journals; EZB-FREE-00999 freely available EZB journals
subjects Accuracy
Algorithms
Cancer
Cancer detection
Classification
Computational modeling
ConvNeXt
Datasets
Deep learning
EFAM-Net
Feature extraction
Feature maps
HAM10000
Image classification
Image enhancement
ISIC 2019
lesion classification
Lesions
Medical imaging
Skin
Skin cancer
title EFAM-Net: A Multi-Class Skin Lesion Classification Model Utilizing Enhanced Feature Fusion and Attention Mechanisms
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T20%3A54%3A56IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=EFAM-Net:%20A%20Multi-Class%20Skin%20Lesion%20Classification%20Model%20Utilizing%20Enhanced%20Feature%20Fusion%20and%20Attention%20Mechanisms&rft.jtitle=IEEE%20access&rft.au=Ji,%20Zhanlin&rft.date=2024&rft.volume=12&rft.spage=143029&rft.epage=143041&rft.pages=143029-143041&rft.issn=2169-3536&rft.eissn=2169-3536&rft.coden=IAECCG&rft_id=info:doi/10.1109/ACCESS.2024.3468612&rft_dat=%3Cproquest_ieee_%3E3114560686%3C/proquest_ieee_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3114560686&rft_id=info:pmid/&rft_ieee_id=10695064&rft_doaj_id=oai_doaj_org_article_58be92bcb7de46f097b5d1ff5c3a52ec&rfr_iscdi=true