[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-369630-105":59,"doc-detail-369630-en":130},{"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":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","deep-learning-model-for-grading-carcinoma-with-gini-based-feature-selection-and-linear-production-inspired-feature-fusion","Deep learning model for grading carcinoma with Gini-based feature selection and linear production inspired feature fusion","","Accurate grading of renal cell carcinoma (RCC) and hepatic cell carcinoma (HCC) is crucial for selecting appropriate treatments, yet conventional deep learning often underperforms on complex histopathology patterns. This research proposes a feature selection and fusion framework inspired by economic theories, combining attention-enhanced MobileNetV2, DenseNet121, and InceptionV3 as backbone CNNs. A Gini-based selector prioritizes discriminative features, while a linear-production-inspired fusion optimally integrates multi-network representations. Experiments validate improved state-of-the-art performance with 93.04% accuracy for RCC and 98.24% for LCC, demonstrating robustness and effectiveness.",{"@graph":69,"@context":122},[70,84,105],{"@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/deep-learning-model-for-grading-carcinoma-with-gini-based-feature-selection-and-linear-production-inspired-feature-fusion/369630/",{"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/deep-learning-model-for-grading-carcinoma-with-gini-based-feature-selection-and-linear-production-inspired-feature-fusion/369630.png","ImageObject",300,407,{"name":92,"@type":93},"Putri","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why is accurate carcinoma grading important in this research?","Question",{"text":112,"@type":113},"Accurate grading of carcinomas is needed to determine appropriate treatment strategies and to support clinicians in predicting tumor behavior such as growth and likelihood of spread.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What backbone models are used for the proposed feature fusion framework?",{"text":117,"@type":113},"The framework uses attention-enhanced MobileNetV2, DenseNet121, and InceptionV3 as foundational CNN architectures.",{"name":119,"@type":110,"acceptedAnswer":120},"How does the method select and combine features for prediction?",{"text":121,"@type":113},"A Gini-based feature selection method prioritizes the most discriminative features, and extracted features from each network are fused using a technique modeled after a linear production function to maximize each model’s contribution.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},369630,1790367966,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"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,"preview_page_count":19,"preview_urls":146},962085571259,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nDeep learning model for grading carcinoma with Gini-based featureselection and linear productioninspired feature fusion  \nShreyan Kundu1,6, Souradeep Mukhopadhyay2,6, Rahul Talukdar1, Dmitrii Kaplun3,4􀀍, Alexander Voznesensky4 & Ram Sarkar5  \nThe most common types of kidneys and liver cancer are renal cell carcinoma (RCC) and hepatic cell carcinoma (HCC), respectively. Accurate grading of these carcinomas is essential for determining the most appropriate treatment strategies, including surgery or pharmacological interventions. Traditional deep learning methods often struggle with the intricate and complex patterns seen in histopathology images of RCC and HCC, leading to inaccuracies in classification. To enhance the grading accuracy for liver and renal cell carcinoma, this research introduces a novel feature selection and fusion framework inspired by economic theories, incorporating attention mechanisms into three Convolutional Neural Network (CNN) architectures-MobileNetV2, DenseNet121, and InceptionV3-as foundational models. The attention mechanisms dynamically identify crucial image regions, leveraging each CNN’s unique strengths. Additionally, a Gini-based feature selection method is implemented to prioritize the most discriminative features, and the extracted features from each network are optimally combined using a fusion technique modeled after a linear production function, maximizing each model’s contribution to the final prediction. Experimental evaluations demonstrate that this proposed approach outperforms existing state-of-the-art models, achieving high accuracies of 93.04% for RCC and 98.24% for LCC. This underscores the method’s robustness and effectiveness in accurately grading these types of cancers. The code of our method is publicly available in [https://github.com/GHOSTCALL983/GRADE-CLASSIFIC](https://github.com/GHOSTCALL983/GRADE-CLASSIFIC)[ATION](ATION.)[.](ATION.)  \nKeywords Cell carcinoma, Deep learning, Histopathology image analysis, Automated grading system, Machine learning, Medical imaging, Cancer diagnosis, Image classification, Feature extraction  \nAbbreviations  \nAdamWAUC CAD CC CNN FLOPs GANGAP  \nGradCAM H[NONSPACE&E] HCC  \nISUPKMC  \nAdam optimizer with weight decay Area under the (ROC) curve Computer-aided diagnostics Cell carcinoma  \nConvolutional neural network Floating-point operations Generative adversarial network Global average pooling  \nGradient-weighted class activation mapping Hematoxylin and eosin  \nHepatic cell carcinoma  \nInternational Society of Urologic Pathology Kasturba Medical College  \n1Department of Computer Science & Engineering, Institute of Engineering & Management, Kolkata, India 700091.  \n2Department of Computer Science & Automation, Indian Institute of Science, Bangalore, India 560012. 3Artificial Intelligence Research Institute, China University of Mining and Technology, Xuzhou, China 221116. 4Radio Systems Department, Saint Petersburg Electrotechnical University “LETI”, Saint Petersburg, Russian Federation 197022.  \n5Department of Computer Science & Engineering, Jadavpur University, Kolkata, India 700032. 6Shreyan Kundu and Souradeep Mukhopadhyay contributed equally to this work. 􀀍 email: [dikaplun@etu.ru](dikaplun@etu.ru)  \n[www. nature.com/scientificreports/](www. nature.com/scientificreports/)  \nLSTM Long short-term memory  \nmAP Mean average precision  \nML Machine learning  \nRCC Renal cell carcinoma  \nRNN Recurrent neural network  \nSCR Shared channel residual  \nSE Squeeze-and-excitation  \nSOTA State-of-the-art  \nSVM Support vector machine  \nViT Vision transformer  \nList of symbols  \nX Input tensor or feature map  \nW1 , W2 Weights ofthe 1 × 1 convolution layers in Attention Block 1  \nσ (·) Sigmoid activation function  \nReLU (·) Rectified Linear Unit activation function  \n⊗ Element-wise multiplication  \n⊙ Element-wise multiplication (used interchangeably in some  \ncontexts)  \nGAP (·) Globa","cbCaikHjZJCNIguw","https://ap.wps.com/l/cbCaikHjZJCNIguw","pdf",4912529,26,"English","# Introduction\n## Motivation and clinical importance of carcinoma grading\n## Limitations of standalone deep learning and need for fusion","[{\"question\":\"Why is accurate carcinoma grading important in this research?\",\"answer\":\"Accurate grading of carcinomas is needed to determine appropriate treatment strategies and to support clinicians in predicting tumor behavior such as growth and likelihood of spread.\"},{\"question\":\"What backbone models are used for the proposed feature fusion framework?\",\"answer\":\"The framework uses attention-enhanced MobileNetV2, DenseNet121, and InceptionV3 as foundational CNN architectures.\"},{\"question\":\"How does the method select and combine features for prediction?\",\"answer\":\"A Gini-based feature selection method prioritizes the most discriminative features, and extracted features from each network are fused using a technique modeled after a linear production function to maximize each model’s contribution.\"}]","Deep learning model for grading carcinoma with Gini-based feature selection and linear production inspired feature fusion | PDF",1790183752,66,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/8d05a89fd4f4a2e56129a82b9b2015f0.webp",983,1291,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/b3e31de48aeb01bf2b5bbae2d43334fc.webp",982,1290,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/5e0c90cc76a4a92e452b318b93982132.webp",981,1289,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/1af5a0540accbfe092261cb964e42583.webp",980,1287]