[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-374129-105":59,"doc-detail-374129-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","a-robust-deep-learning-framework-for-multiclass-skin-cancer-classification","A robust deep learning framework for multiclass skin cancer classification","","A hybrid deep learning model is proposed for multiclass skin cancer classification, addressing the visual similarity between benign and malignant lesions that hinders accurate diagnosis. The architecture combines ConvNeXtV2 blocks in early stages for fine-grained local pattern capture with separable self-attention in later stages to focus on diagnostically relevant regions while reducing computational cost. Training and validation use the ISIC 2019 dataset across eight lesion categories, supported by data augmentation and transfer learning. The approach achieves 93.48% accuracy, 93.24% precision, 90.70% recall, and 91.82% F1-score with compact 21.92M parameters.",{"@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/a-robust-deep-learning-framework-for-multiclass-skin-cancer-classification/374129/",{"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/a-robust-deep-learning-framework-for-multiclass-skin-cancer-classification/374129.png","ImageObject",300,407,{"name":92,"@type":93},"Ivy","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 problem does the study target in skin cancer classification?","Question",{"text":113,"@type":114},"The study targets the difficulty of accurately classifying skin lesions because benign and malignant cases can look visually similar.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the proposed model combine ConvNeXtV2 and self-attention?",{"text":118,"@type":114},"ConvNeXtV2 blocks are used in the first two stages to capture fine local features, while separable self-attention is used later to prioritize diagnostically relevant regions with reduced computational complexity.",{"name":120,"@type":111,"acceptedAnswer":121},"What dataset and evaluation results are reported?",{"text":122,"@type":114},"The model is trained and validated on the ISIC 2019 dataset containing eight skin lesion categories, achieving 93.48% accuracy, 93.24% precision, 90.70% recall, and 91.82% F1-score.","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},374129,1790533940,{"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":56,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145},549758252649,"https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nA robust deep learning framework for multiclass skin cancer classification  \nBurhanettin Ozdemir1􀀍 & Ishak Pacal2,3  \nSkin cancer represents a significant global health concern, where early and precise diagnosis plays a pivotal role in improving treatment efficacy and patient survival rates. Nonetheless, the inherent visual similarities between benign and malignant lesions pose substantial challenges to accurate classification. To overcome these obstacles, this study proposes an innovative hybrid deep learning model that combines ConvNeXtV2 blocks and separable self-attention mechanisms, tailored to enhance feature extraction and optimize classification performance. The inclusion of ConvNeXtV2 blocks in the initial two stages is driven by their ability to effectively capture fine-grained local features and subtle patterns, which are critical for distinguishing between visually similar lesion types. Meanwhile, the adoption of separable self-attention in the later stages allows the model to selectively prioritize diagnostically relevant regions while minimizing computational complexity, addressing the inefficiencies often associated with traditional self-attention mechanisms. The model was comprehensively trained and validated on the ISIC 2019 dataset, which includes eight distinct skin lesion categories. Advanced methodologies such as data augmentation and transfer learning were employed to further enhance model robustness and reliability. The proposed architecture achieved exceptional performance metrics, with 93.48% accuracy, 93.24% precision, 90.70% recall, and a 91.82% F1-score, outperforming over ten Convolutional Neural Network (CNN) based and over ten Vision Transformer (ViT) based models tested under comparable conditions. Despite its robust performance, the model maintains a compact design with only 21.92 million parameters, making it highly efficient and suitable for model deployment. The Proposed Model demonstrates exceptional accuracy and generalizability across diverse skin lesion classes, establishing a reliable framework for early and accurate skin cancer diagnosis in clinical practice.  \nKeywords Medical image analysis, Health, Skin cancer detection, ConvNeXtv2, Vision Transformer  \nAs the body’s primary defense against external threats, the skin plays a vital role in maintaining overall health and well-being1. It is the largest organ of the human body, serving as a protective barrier against harmful microorganisms, physical trauma, and harsh environmental factors2. Composed of three main layers: the epidermis, dermis, and hypodermis, the skin not only shields internal systems but also regulates temperature, facilitates vitamin D synthesis, and sustains hydration and electrolyte balance3. However, continuous exposure to external elements increases the risk of various conditions, including cancer, a disease marked by the abnormal and uncontrolled growth of cells4. Cancer can affect virtually any organ or tissue in the body, leading to severe health consequences and requiring timely intervention for effective management5. Among these, skin cancer represents a particularly pressing public health issue, influenced by factors such as prolonged sun exposure, genetic predisposition, and environmental triggers. Alarmingly, projections for 2024 in the United States estimate 108,270 new cases of skin cancer, with 13,120 related deaths6.  \nSkin cancer is broadly categorized into two primary forms: melanoma and nonmelanoma7. Melanoma, known for its aggressive and life-threatening nature, accounts for the majority of fatalities associated with skin cancer7,8. Detecting melanoma at an early stage is essential for improving patient outcomes and expanding treatment options, as is the case with many other types of cancer7–10. Early detection not only allows for timely medical intervention but also significantly increases the likelihood of successful ","cbCaijuRywkE4rXp","https://ap.wps.com/l/cbCaijuRywkE4rXp","pdf",4402836,"English","# Introduction\n## Skin’s role and cancer risk\n## Skin cancer types and need for early diagnosis\n# Proposed Method\n## Hybrid architecture design (ConvNeXtV2 + separable self-attention)\n## Training and validation on ISIC 2019\n# Results and Performance","[{\"question\":\"What problem does the study target in skin cancer classification?\",\"answer\":\"The study targets the difficulty of accurately classifying skin lesions because benign and malignant cases can look visually similar.\"},{\"question\":\"How does the proposed model combine ConvNeXtV2 and self-attention?\",\"answer\":\"ConvNeXtV2 blocks are used in the first two stages to capture fine local features, while separable self-attention is used later to prioritize diagnostically relevant regions with reduced computational complexity.\"},{\"question\":\"What dataset and evaluation results are reported?\",\"answer\":\"The model is trained and validated on the ISIC 2019 dataset containing eight skin lesion categories, achieving 93.48% accuracy, 93.24% precision, 90.70% recall, and 91.82% F1-score.\"}]","A robust deep learning framework for multiclass skin cancer classification | PDF",1790201176,48]