[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-369434-105":59,"doc-detail-369434-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","skinehdlf-a-hybrid-deep-learning-approach-for-accurate-skin-cancer-classification-in-complex-systems","SkinEHDLF - A Hybrid Deep Learning Approach for Accurate Skin Cancer Classification in Complex Systems","","SkinEHDLF proposes a hybrid deep-learning framework for precise skin cancer classification, combining ConvNeXt, EfficientNetV2, and Swin Transformer with an adaptive attention-based feature fusion mechanism. The model dynamically emphasizes the most relevant fused features to improve predictive reliability while reducing false positives. Experiments use the ISIC 2024 dataset containing 401,059 lesion images across melanoma, benign, and noncancerous categories. Results show strong performance, outperforming baseline and leading methods and demonstrating scalability for automated dermatological diagnostics.",{"@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":35,"@type":76,"position":81},"https://docshare.wps.com/document/healthcare/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/skinehdlf-a-hybrid-deep-learning-approach-for-accurate-skin-cancer-classification-in-complex-systems/369434/",{"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/skinehdlf-a-hybrid-deep-learning-approach-for-accurate-skin-cancer-classification-in-complex-systems/369434.png","ImageObject",300,407,{"name":92,"@type":93},"Connor ","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What is SkinEHDLF and what problem does it address?","Question",{"text":113,"@type":114},"SkinEHDLF is a hybrid deep-learning model designed to improve the accuracy and reliability of skin cancer classification. It targets common obstacles such as limited labeled data and the need to reduce false positives and negatives.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does SkinEHDLF combine different deep learning architectures?",{"text":118,"@type":114},"SkinEHDLF integrates ConvNeXt, EfficientNetV2, and Swin Transformer. It adds an adaptive attention-based feature fusion mechanism to optimize how features are synthesized and to focus on the most relevant information.",{"name":120,"@type":111,"acceptedAnswer":121},"How was SkinEHDLF evaluated and what performance results were reported?",{"text":122,"@type":114},"SkinEHDLF was trained and evaluated using the ISIC 2024 dataset with melanoma, benign, and noncancerous lesion categories. Reported results include AUROC up to 99.8% and accuracy up to 98.76% for binary classification, and strong multi-class metrics with reduced false positives compared with leading baselines.","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},369434,1790194742,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":34,"category_name":35,"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},687207022233,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nSkinEHDLF a hybrid deep learning approach for accurate skin cancer classification in complex systems  \nUmesh Kumar Lilhore1,2, Yogesh Kumar Sharma3, Sarita Simaiya1,6􀀍, Roobaea Alroobaea4, Abdullah M. Baqasah5, Majed Alsafyani4 & AfnanAlhazmi5  \nSkin cancer represents a significant global public health issue, and prompt and precise detection is essential for effective treatment. This study introduces SkinEHDLF, an innovative deep-learning model that enhances skin cancer classification. SkinEHDLF utilizes the advantages of several advanced models, i.e., ConvNeXt, EfficientNetV2, and Swin Transformer, while integrating an adaptive attention-based feature fusion mechanism to enhance the synthesis of acquired features. This hybrid methodology combines ConvNeXt’s proficient feature extraction capabilities, EfficientNetV2’sscalability, and Swin Transformer’s long-range attention mechanisms, resulting in a highly accurate and dependable model. The adaptive attention mechanism dynamically optimizes feature fusion, enabling the model to focus on the most relevant information, enhancing accuracy and reducing false positives. We trained and evaluated SkinEHDLF using the ISIC 2024 dataset, which comprises 401,059 skin lesion images extracted from 3D total-body photography. The dataset is divided into three categories: melanoma, benign lesions, and noncancerous skin anomalies. The findings indicate the superiority of SkinEHDLF compared to current models. In binary skin cancer classification, SkinEHDLF surpassed baseline models, achieving anAUROC of 99.8% and an accuracy of 98.76% . The model attained 98.6% accuracy, 97.9% precision, 97.3% recall, and 99.7% AUROC across all lesion categories in multi-class classification. SkinEHDLF demonstrates a 7.9% enhancement inaccuracy and a 28% decrease in false positives, outperforming leading models including ResNet-50, EfficientNet-B3, ViT-B16, and hybrid methodologies such as ResNet-50 + EfficientNet and ViT + CNN, thereby positioning itself as a more precise and reliable solution for automated skin cancer detection. These findings underscore SkinEHDLF’s capacity to transform dermatological diagnostics by providing a scalable and accurate method for classifying skin cancer.  \nKeywords Deep learning, Skin Cancer detection, Hybrid model, ConvNeXt, EfficientNetV2, Swin transformer  \nSkin cancer ranks among the most prevalent cancers globally, with millions of new cases documented annually. When atypical skin cells proliferate uncontrollably, they produce malignant tumors1,2. The three predominant forms of skin cancer are melanoma, basal cell carcinoma (BCC), and squamous cell carcinoma (SCC) . Although BCC and SCC are typically less aggressive, melanoma is the most perilous due to its rapid dissemination to other organs if not promptly identified and addressed. The incidence of skin cancer is progressively rising due to heightened exposure to ultraviolet (UV) radiation from both natural and artificial sources, rendering it a significant global health issue3,4. Early skin cancer detection increases the chances of survival and effective treatment, improving patient outcomes. Patients who receive timely diagnosis typically have a better prognosis, and many cases can be treated by surgically removing the tumor. Significant management challenges associated with advanced skin cancer result in higher death rates. Conventional detection techniques, such as dermatologists’  \n1Department of Computer Science and Engineering, School of Computing Science and Engineering, Galgotias University, Greater Noida 203201, Uttar Pradesh, India. 2Galgotias Multidisciplinary Research & Development Cell (G-MRDC), Galgotias University, Greater Noida 203201, Uttar Pradesh, India. 3Department of Computer Science, Koneru Lakshmaiah University Deemed to be University, Vijayawada 520 002, Andhra Pradesh, India. 4Department of Computer Science, College ","cbCaihS15fc3u4CG","https://ap.wps.com/l/cbCaihS15fc3u4CG","pdf",6220199,32,"English","# Skin cancer detection background\n## Machine learning and deep learning approaches\n## Key challenges in skin cancer diagnosis\n## Visual similarity and limited expertise\n## SkinEHDLF model and evaluation","[{\"question\":\"What is SkinEHDLF and what problem does it address?\",\"answer\":\"SkinEHDLF is a hybrid deep-learning model designed to improve the accuracy and reliability of skin cancer classification. It targets common obstacles such as limited labeled data and the need to reduce false positives and negatives.\"},{\"question\":\"How does SkinEHDLF combine different deep learning architectures?\",\"answer\":\"SkinEHDLF integrates ConvNeXt, EfficientNetV2, and Swin Transformer. It adds an adaptive attention-based feature fusion mechanism to optimize how features are synthesized and to focus on the most relevant information.\"},{\"question\":\"How was SkinEHDLF evaluated and what performance results were reported?\",\"answer\":\"SkinEHDLF was trained and evaluated using the ISIC 2024 dataset with melanoma, benign, and noncancerous lesion categories. Reported results include AUROC up to 99.8% and accuracy up to 98.76% for binary classification, and strong multi-class metrics with reduced false positives compared with leading baselines.\"}]","SkinEHDLF - A Hybrid Deep Learning Approach for Accurate Skin Cancer Classification in Complex Systems | PDF",1790182638,81]