[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-363736-105":59,"doc-detail-363736-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","tridermcancernet-a-hybrid-deep-learning-framework-for-skin-cancer-classification","TriDermCancerNet - A hybrid deep learning framework for skin cancer classification","","Skin cancer diagnosis via automated image analysis remains challenging due to poor image contrast, visual similarity among lesion classes, and class imbalance. This study proposes TriDermCancerNet, a hybrid deep learning framework for classifying skin cancer from dermoscopic images. Two publicly available datasets (ISIC 2018 and 2019) are used. The pipeline applies contrast enhancement and data augmentation to improve image quality and balance classes, then parallel feature learning is performed using three modules (Inception, Inverted Bottleneck Residual, and Dense-177) with depth-concatenation fusion. Bayesian optimization selects key hyperparameters and the final model is evaluated on testing. Results show strong performance and statistical evidence that the fused model outperforms individual branches, supporting its use as a diagnostic aid for early detection.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/tridermcancernet-a-hybrid-deep-learning-framework-for-skin-cancer-classification/363736/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/tridermcancernet-a-hybrid-deep-learning-framework-for-skin-cancer-classification/363736.png","ImageObject",300,407,{"name":92,"@type":93},"Blitz","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-04","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",11,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does TriDermCancerNet address in skin cancer image classification?","Question",{"text":113,"@type":114},"It targets difficulties caused by poor image contrast, high visual similarity between lesion classes, and class imbalance in available datasets.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the proposed method prepare and balance dermoscopic image data?",{"text":118,"@type":114},"It uses a contrast enhancement technique and applies data augmentation to improve image quality and balance the datasets.",{"name":120,"@type":111,"acceptedAnswer":121},"What architecture components are integrated into TriDermCancerNet and how are they combined?",{"text":122,"@type":114},"The framework integrates three modules (Inception, Inverted Bottleneck Residual, and Dense-177) in parallel, then fuses extracted features using a depth concatenation approach.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},363736,1790203028,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":146,"preview_page_count":19,"preview_urls":147},24464137899374,"https://us-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","TriDermCancerNet: A hybrid deep learning framework for skin cancer classiﬁcation  \nJournal of International Medical Research Volume 54: 1–23 © The Author(s) 2026 Article reuse guidelines:  \n[sagepub.com/journals-permissions](sagepub.com/journals-permissions)[ ](sagepub.com/journals-permissions)[DOI: 10.1177/03000605261461235](DOI: 10.1177/03000605261461235)[ ](DOI: 10.1177/03000605261461235)[journals.sagepub.com/home/imr](journals.sagepub.com/home/imr)  \nBushra Fiaz 1, Muhammad Attique Khan2 , Aﬁa Zafar3, Shrooq Alsenan4, Yazan Alnsour5, Zepa Yang6 and Yunyoung Nam6  \nAbstract  \nObjective: Skin cancer diagnosis via automated image analysis remains a challenging task due to poor image contrast, visual similarity among lesion classes, and class imbalance in available datasets. To address these issues, this study proposes a novel Tri Model Dermatology Cancer Neural Network (TriDermCancerNet) for classifying skin cancer from dermoscopic images.  \nMethods: Two publicly available datasets are used in this work: the International Skin Imaging Collaboration 2018 and 2019 datasets, which contain multiple classes of cancer types. In the proposed model framework, a contrast enhancement technique was applied to improve image quality, followed by data augmentation to balance the datasets. The proposed TriDermCancerNet architecture is designed based on the key challenges of this work, including dataset variability, interclass similarity, and model explainability. The proposed architecture integrates three modules: a 105-layer Inception module, a 186-layer Inverted Bottleneck Residual module, and the Dense-177 module. Each module was integrated into the proposed network in parallel rather than in series. Thereafter, each module was trained, and features were extracted and fused using a depth concatenation approach. During training, several important hyperparameters were selected using Bayesian optimization, and the ﬁnal model was used for classiﬁcation in the testing phase.  \nResults: The fused TriDermCancerNet achieved 98.6% accuracy, 98.6% sensitivity, 98.6% F1-score, and an area under the curve of 1.0 on the International Skin Imaging Collaboration 2018 dataset and 99.7% accuracy, 99.6% sensitivity, 99.6% F1-score, and an area under the curve of 1.0 on the International Skin Imaging Collaboration 2019 dataset. Statistical signiﬁcance testing conﬁrmed that the fusion model outperforms each branch (p\u003C0.05).  \nConclusion: The proposed hybrid TriDermCancerNet approach enhances the precision and robustness of skin cancer classiﬁcation frameworks, providing clinicians with a valuable diagnostic aid for early detection.  \nKeywords  \nSkin cancer, dermoscopic images, deep learning, information fusion, bottleneck mechanism, classiﬁcation  \nReceived: 17 February 2026; revised: 22 April 2026; accepted: 2 June 2026  \n1 Department of Computer Engineering, HITEC University, Pakistan 2Center of AI, Prince Mohammad bin Fahd University, Saudi Arabia  \n3Department of Computer Science, National University of Computer and Emerging Sciences, Pakistan  \n4Information Systems Department, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Saudi Arabia 5Department of MIS, College of Business Administration, Prince Mohammad bin Fahd University, Saudi Arabia  \n6Department of ICT Convergence, Soonchunhyang University, South Korea  \nCorresponding authors:  \nZepa Yang, Department of ICT Convergence, Soonchunhyang University, Asan-si, South Korea.  \nEmail: [yangzepa@sch.ac.kr](yangzepa@sch.ac.kr)  \nMuhammad Attique Khan, Center of AI, Prince Mohammad bin Fahd University, Alkhobar, Saudi Arabia.  \nEmail: [attique.khan@ieee.org](attique.khan@ieee.org)  \nCreative Commons Non Commercial CC BY-NC: This article is distributed under the terms of the Creative Commons Attribution  \nNonCommercial 4.0 License ([https://creativecommons.org/licenses/by-nc/4.0/](https://creativecommons.org/licenses/by-nc/4.0/)) which permits non-commercial use, ","cbCaitXvDrTzRS3k","https://ap.wps.com/l/cbCaitXvDrTzRS3k","pdf",5046277,23,"English","# Abstract\n## Objective\n## Methods\n## Results\n## Conclusion\n# Introduction\n## Cancer overview\n## Skin lesions and melanoma background\n# Materials and Methods\n## Datasets and preprocessing\n## Model architecture and fusion strategy\n## Hyperparameter optimization\n# Results\n## Performance metrics on ISIC 2018 and 2019\n## Statistical significance\n# Conclusion","[{\"question\":\"What problem does TriDermCancerNet address in skin cancer image classification?\",\"answer\":\"It targets difficulties caused by poor image contrast, high visual similarity between lesion classes, and class imbalance in available datasets.\"},{\"question\":\"How does the proposed method prepare and balance dermoscopic image data?\",\"answer\":\"It uses a contrast enhancement technique and applies data augmentation to improve image quality and balance the datasets.\"},{\"question\":\"What architecture components are integrated into TriDermCancerNet and how are they combined?\",\"answer\":\"The framework integrates three modules (Inception, Inverted Bottleneck Residual, and Dense-177) in parallel, then fuses extracted features using a depth concatenation approach.\"}]","TriDermCancerNet - A hybrid deep learning framework for skin cancer classification | PDF",1790152896,58,[148,152,156,160],{"page_no":8,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/fb1ca7dbc5ae5c1d05c82930c59738c7.webp",983,1310,{"page_no":14,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/9e453e552edc18994f202d87cf911b87.webp",982,1309,{"page_no":81,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/a831a36fa516362eaa176eb8a0fb4306.webp",981,1308,{"page_no":19,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/f0da73a986d735ea222787c6249f0792.webp",980,1306]