[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-376949-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-376949-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","transformer-based-approach-to-melanoma-detection-paper","Transformer-Based Approach to Melanoma Detection - Paper","","Melanoma is a malignant cancer driven largely by DNA damage, commonly linked to environmental ultraviolet exposure. Because early stages are critical for preventing aggressive growth and mortality, timely identification of suspicious lesions is essential. The work proposes a ViT-based architecture to classify melanoma versus non-cancerous skin lesions using public ISIC challenge data. Multiple classifier configurations are evaluated to identify the most discriminative model, achieving strong metrics including accuracy, sensitivity, specificity, and AUROC.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/healthcare/","Healthcare",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/transformer-based-approach-to-melanoma-detection-paper/376949/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/transformer-based-approach-to-melanoma-detection-paper/376949.png","ImageObject",300,407,{"name":42,"@type":43},"\tCallum ","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-30","2026-09-24",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",13,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the study address in melanoma detection?","Question",{"text":63,"@type":64},"It addresses early identification of melanoma from skin images to support diagnosis and reduce the risk of rapid cancer spread.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What model architecture is proposed for classifying lesions?",{"text":68,"@type":64},"The study presents a ViT-based architecture to classify melanoma versus non-cancerous lesions.",{"name":70,"@type":61,"acceptedAnswer":71},"How is the approach evaluated and what results are reported?",{"text":72,"@type":64},"The model is trained and tested on public skin cancer data from the ISIC challenge, and multiple classifier configurations are compared. The best configuration reports high accuracy, sensitivity, specificity, and AUROC.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},376949,1790758317,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,110,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":108,"slug":109},7,40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":112,"show_sort_weight":113,"slug":114},8,"Research & Report",30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":107,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":55,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145},137451211410,"https://ap-avatar.wpscdn.com/avatar/2000bb0a9246f588df?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786362646172706240","sensors   \nArticle  \nTransformer-Based Approach to Melanoma Detection  \nGiansalvo Cirrincione 1,†, Sergio Cannata 2, *,†, Giovanni Cicceri 3, Francesco Prinzi 3, Tiziana Currieri 3, Marta Lovino 4, Carmelo Militello 5, Eros Pasero 2 and Salvatore Vitabile 3  \nCitation: Cirrincione, G.; Cannata, S.; Cicceri, G.; Prinzi, F.; Currieri, T.; Lovino, M.; Militello, C.; Pasero, E.; Vitabile, S. Transformer-Based Approach to Melanoma Detection. Sensors 2023, 23, 5677. [https://](https://)[ ](https://)[doi.org/10.3390/s23125677](doi.org/10.3390/s23125677)  \nAcademic Editor: Alexander Wong  \nReceived: 18 May 2023  \nRevised: 9 June 2023  \nAccepted: 15 June 2023  \nPublished: 17 June 2023  \nCopyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \n1 Département Electronique-Electrotechnique-Automatique (EEA), University of Picardie Jules Verne, 80000 Amiens, France; [giansalvo.cirrincione@u-picardie.fr](giansalvo.cirrincione@u-picardie.fr)  \n2 Department of Electronics and Telecommunications, Politecnico di Torino, 10129 Turin, Italy;  \neros.pasero@polito.it  \n3 Department of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, 90127 Palermo, Italy; [giovanni.cicceri@unipa.it](giovanni.cicceri@unipa.it) (G.C.); [francesco.prinzi@unipa.it](francesco.prinzi@unipa.it) (F.P.); [tiziana.currieri@unipa.it](tiziana.currieri@unipa.it) (T.C.); salvatore.vitabile@unipa.it (S.V.)  \n4 Department of Engineering Enzo Ferrari, University of Modena and Reggio Emilia, 41125 Modena, Italy; [marta.lovino@unimore.it](marta.lovino@unimore.it)  \n5 Institute for High-Performance Computing and Networking (ICAR-CNR), Italian National Research Council, 90146 Palermo, Italy; carmelo.militello@cnr.it  \n* Correspondence: sergio.cannata@polito.it † These authors contributed equally to this work.  \nAbstract: Melanoma is a malignant cancer type which develops when DNA damage occurs (mainly due to environmental factors such as ultraviolet rays) . Often, melanoma results in intense and aggressive cell growth that, if not caught in time, can bring one toward death. Thus, early identification atthe initial stage is fundamental to stopping the spread of cancer. In this paper, a ViT-based architecture able to classify melanoma versus non-cancerous lesions is presented. The proposed predictive model is trained and tested on public skin cancer data from the ISIC challenge, and the obtained results are highly promising. Different classifier configurations are considered and analyzed in order to find the most discriminating one. The best one reached an accuracy of 0.948, sensitivity of 0.928, specificity of 0.967, and AUROC of 0 .948.  \nKeywords: skin cancer; melanoma detection; vision transformers; artificial intelligence; decision-making support  \n1. Introduction  \nAccording to the World Health Organization (WHO), skin cancer is considered oneof the most common types of cancer worldwide [1] . Over one million skin cancer cases are diagnosed each year, estimated to account for one third of all cancer diagnoses [2] . Exposure to sun ultraviolet (UV) radiation represents the primary cause of skin cancer. Hence, the WHO recommends avoiding prolonged sun exposure to individuals with fair skin and regular self-examinations for any suspicious lesions on the skin.  \nMelanoma is a skin cancer that develops from the pigment-producing cells known as melanocytes [3] . The incidence of melanoma has significantly increased in the past 30 years [4], making up only 5 percent of all cases but having a mortality rate of over 75 percent [5,6] .  \nMelanoma skin cancer requires early diagnosis and treatment, aspects vital to improving outcomes in affected individuals and preventin","cbCaiuqJARcn3pGX","https://ap.wps.com/l/cbCaiuqJARcn3pGX","pdf",803597,"English","# Introduction\n## Motivation and background (skin cancer and melanoma)\n## Computer-aided diagnosis and existing deep learning methods\n## Limitations of CNNs and motivation for transformer-based modeling","[{\"question\":\"What problem does the study address in melanoma detection?\",\"answer\":\"It addresses early identification of melanoma from skin images to support diagnosis and reduce the risk of rapid cancer spread.\"},{\"question\":\"What model architecture is proposed for classifying lesions?\",\"answer\":\"The study presents a ViT-based architecture to classify melanoma versus non-cancerous lesions.\"},{\"question\":\"How is the approach evaluated and what results are reported?\",\"answer\":\"The model is trained and tested on public skin cancer data from the ISIC challenge, and multiple classifier configurations are compared. The best configuration reports high accuracy, sensitivity, specificity, and AUROC.\"}]","Transformer-Based Approach to Melanoma Detection - Paper | PDF",1790222276,33]