[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-355591-105":59,"doc-detail-355591-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","r3mv-a-novel-reliable-system-architecture-for-skin-cancer-classification-using-progressive-heterogeneous-multiblock-model-progressive-learning-three-tier-decision-fusion","R3MV - a novel reliable system architecture for skin cancer classification using progressive heterogeneous multiblock model - Progressive Learning Three-Tier Decision Fusion","","Reliable skin lesion prediction from deep learning often fails under dataset variations, limiting clinical use across diverse scenarios. This study proposes PHMBCNN with a progressive learning strategy and introduces the R3MV three-tier decision fusion system that aggregates outputs from (i) individual CNNs, (ii) a feature fusion classifier, and (iii) a meta-classifier trained on CNN outputs. Majority voting improves decision reliability. Using PAD_UFES_20 and HAM10000, accuracy rises to 81.78% and 99.3%, respectively, with PHMBCNN-GRU further improving performance.",{"@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/r3mv-a-novel-reliable-system-architecture-for-skin-cancer-classification-using-progressive-heterogeneous-multiblock-model-progressive-learning-three-tier-decision-fusion/355591/",{"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/r3mv-a-novel-reliable-system-architecture-for-skin-cancer-classification-using-progressive-heterogeneous-multiblock-model-progressive-learning-three-tier-decision-fusion/355591.png","ImageObject",300,407,{"name":92,"@type":93},"Sarah ","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-09-22",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},"Why are single-model predictions unreliable for skin cancer classification?","Question",{"text":113,"@type":114},"Single models can be sensitive to variations in datasets, causing inconsistent performance and limiting use in different clinical scenarios.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the R3MV three-tier decision fusion system improve reliability?",{"text":118,"@type":114},"R3MV combines predictions from individual CNNs, a feature fusion classification architecture, and a meta-classifier trained on CNN outputs, then applies majority voting to strengthen decision consistency.",{"name":120,"@type":111,"acceptedAnswer":121},"What datasets and performance gains are reported for the proposed approach?",{"text":122,"@type":114},"Experiments use PAD_UFES_20 and HAM10000. Accuracy improves from 75.70% to 80.69% (PAD_UFES_20) and from 92.07% to 96.01% (HAM10000), while the R3MV system reaches 81.78% and 99.3%, respectively.","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},355591,1790385291,{"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":26,"preview_page_count":19,"preview_urls":146},962085320529,"https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nR3MV: a novel reliable system architecture for skin cancer classification using progressive heterogeneous multiblock model  \nS. K. Reshma & S. R. Reeja􀀍  \nMedical picture categorization has been greatly enhanced by the use of deep learning, especially in the timely identification of skin lesions. Still, predictions from a single model remain unreliable due to their susceptibility to variations in the dataset, complicating their application to diverse clinical scenarios. This study introduces a unique CNN, PHMBCNN, designed to enhance classification accuracy using a progressive learning strategy. We propose the R3MV three-tier decision fusion system, which integrates predictions from (i) individual CNN model predictions,(ii) a feature fusion classification architecture, and (iii) a meta-classifier trained on the outputs ofthe CNN models. The final forecast is reached using a majority voting procedure, which enhances the reliability of the decision. The study utilizes two datasets for skin cancer: PAD_UFES_20 and HAM10000 . Incorporating a GRU into the PHMBCNN model results in the PHMBCNN-GRU. The classification accuracy enhanced from 75.70% for the PAD_UFES_ 20 dataset to 80.69%, and from 92.07% for the HAM10000 dataset to 96.01%. The R3MV system design achieves 81.78% for PAD_UFES_20 and 99.3% for HAM10000 .  \nKeywords Reliable three level majority vote system architecture, Skin malignancy, Progressive hybrid multi block CNN, Feature fusion classifier, Meta classifier, Gated recurrent unit  \nThe skin serves as a protective barrier for the human body1. Skin cancer is a disorder characterized by the abnormal proliferation of skin tissue, which can become malignant. If undetected and untreated, it may metastasize to adjacent organs, causing harm. Melanoma and non-melanoma represent two classifications of skin cancer2. Melanoma is a severe type of skin cancer. Melanoma accounts for a minority of occurrences, but non-melanoma comprises the majority.  \nA physician often uses the ABCDE method3 to assess the attributes of compromised skin for the diagnosis of tissue cancer. A biopsy4 may be recommended if necessary. The procedure is laborious, excruciating, and expensive. Non-invasive technologies are preferably superior to invasive techniques such as biopsy.  \nA progressive enhancement to the traditional diagnostic procedure has been implemented using a noninvasive technique for capturing images and their patterns. Microscopy and dermoscopy devices5 were utilized to obtain certain image patterns. Macroscopic pictures often exhibit poor resolution, while dermoscopic images are characterized by excellent resolution. Dermoscopic pictures may be employed by Deep Learning Neural Network models to accurately identify cancerous skin tissues, obviating the necessity for a domain expert or feature extractor through its automated feature engineering approach.  \nFernandes et al.6 performed a comprehensive analysis of the obstacles faced by AI models in dermatology, specifically emphasizing the absence of external validation necessary for evaluating clinical applicability and scientific rigor. Their examination of 41 papers revealed substantial deficiencies in current research, underscoring the pressing necessity to enhance validation frameworks and reporting standards. The authors assert that progressing towards resilient, context-sensitive, and equity-focused external validation is crucial for guaranteeing the secure and reliable incorporation of AI technologies into dermatology.  \nValliani et al.7 also note that machine-learning and deep-learning models often suffer a significant decline in performance when utilized on unknown datasets due to dataset shift. Their contention is that this deficiency in generalization is a significant obstacle to practical implementation, especially in medical imaging, where training datasets frequently reflect restricted populations","cbCaihPzhFJD1UDW","https://ap.wps.com/l/cbCaihPzhFJD1UDW","pdf",6765466,24,"English","# Introduction\n## Background on skin cancer and diagnostic challenges\n## Need for robust, generalizable AI models\n# Proposed Method\n## PHMBCNN progressive learning strategy\n## R3MV three-tier decision fusion system\n## PHMBCNN-GRU integration\n# Datasets and Results\n## PAD_UFES_20 and HAM10000 experimental evaluation\n## Accuracy improvements with R3MV","[{\"question\":\"Why are single-model predictions unreliable for skin cancer classification?\",\"answer\":\"Single models can be sensitive to variations in datasets, causing inconsistent performance and limiting use in different clinical scenarios.\"},{\"question\":\"How does the R3MV three-tier decision fusion system improve reliability?\",\"answer\":\"R3MV combines predictions from individual CNNs, a feature fusion classification architecture, and a meta-classifier trained on CNN outputs, then applies majority voting to strengthen decision consistency.\"},{\"question\":\"What datasets and performance gains are reported for the proposed approach?\",\"answer\":\"Experiments use PAD_UFES_20 and HAM10000. Accuracy improves from 75.70% to 80.69% (PAD_UFES_20) and from 92.07% to 96.01% (HAM10000), while the R3MV system reaches 81.78% and 99.3%, respectively.\"}]","R3MV - a novel reliable system architecture for skin cancer classification using progressive heterogeneous multiblock model - Progressive Learning Three-Tier Decision Fusion | PDF",1790120035,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/9662f19caf7ea1b08d0a6d5548828d90.webp",983,1291,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/5993c7a9c86c01b6b940c5feb34d9410.webp",982,1290,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/43dc2fef4332f982b0874fb8bca4496a.webp",981,1289,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/f8e5b0fb5736457f31252ecae3bb0d8f.webp",980,1287]