[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-370323-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-370323-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","synergistic-transfer-learning-and-adversarial-networks-for-breast-cancer-diagnosis-benign-vs-invasive-classification","Synergistic transfer learning and adversarial networks for breast cancer diagnosis - benign vs. invasive classification","","Current breast cancer diagnosis faces cost, time, and inter-observer variability limitations. A deep learning framework is proposed to improve classification by combining generative adversarial networks for data augmentation with transfer learning and multi-scale CNN feature enrichment. A conditional Wasserstein GAN (cWGAN) generates synthetic images conditioned on clinical data, followed by conventional augmentations applied to both original and synthetic samples. Three pre-trained CNNs (DenseNet-201, NasNetMobile, ResNet-101) support multi-scale feature learning. Evaluation on the BreakHis dataset achieves 99.2% accuracy for binary classification and 98.5% for multi-class classification, outperforming existing approaches.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/synergistic-transfer-learning-and-adversarial-networks-for-breast-cancer-diagnosis-benign-vs-invasive-classification/370323/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/synergistic-transfer-learning-and-adversarial-networks-for-breast-cancer-diagnosis-benign-vs-invasive-classification/370323.png","ImageObject",300,407,{"name":42,"@type":43},"Theodore","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-30","2026-09-23",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",16,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the research address in breast cancer diagnosis?","Question",{"text":63,"@type":64},"Existing methods face limitations including high cost, long processing time, and inter-observer variability, which can reduce diagnostic consistency and speed.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does the framework use GANs in the proposed approach?",{"text":68,"@type":64},"It employs a conditional Wasserstein GAN (cWGAN) to generate synthetic breast cancer images conditioned on clinical data, improving training stability and enabling targeted feature incorporation.",{"name":70,"@type":61,"acceptedAnswer":71},"What transfer learning and CNN models are integrated, and what results were achieved?",{"text":72,"@type":64},"The approach uses a multi-scale transfer learning scheme integrating DenseNet-201, NasNetMobile, and ResNet-101 with multi-scale feature enrichment. On the BreakHis dataset, it reports 99.2% accuracy for binary classification and 98.5% for multi-class classification.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},370323,1790216252,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":145,"read_time":99,"preview_page_count":33,"preview_urls":146},7971461740886,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nSynergistic transfer learning and adversarial networks for breast cancer diagnosis: benign vs . invasive classification  \nWejdan Deebani1, Lubna Aziz2,3􀀍, Arshad Aziz2, Wael Sh. Basri4, Wedad M. Alawad5 &  \nSara A. Althubiti6  \nCurrent breast cancer diagnosis methods often face limitations such as high cost, time consumption, and inter-observer variability. To address these challenges, this research proposes a novel deep learning framework that leverages generative adversarial networks (GANs) for data augmentation and transfer learning to enhance breast cancer classification using convolutional neural networks (CNNs). The framework uses a two-stage augmentation approach. First, a conditional Wasserstein GAN (cWGAN) generates synthetic breast cancer images based on clinical data, enhancing training stability and enabling targeted feature incorporation. Second, traditional augmentation techniques (e.g., rotation, flipping, cropping) are applied to both original and synthetic images. A multi-scale transfer learning technique is also employed, integrating three pre-trained CNNs (DenseNet-201, NasNetMobile, ResNet-101) with a multi-scale feature enrichment scheme, allowing the model to capture features at various scales. The framework was evaluated on the BreakHis dataset, achieving an accuracy of 99.2% for binary classification and 98.5% for multi-class classification, significantly outperforming existing methods. This framework offers a more efficient, cost-effective, and accurate approach for breast cancer diagnosis. Future work will focus on generalizing the framework to clinical datasets and integrating it into diagnostic workflows.  \nKeywords Breast cancer diagnosis, Deep learning, Generative adversarial networks (GANs), Transfer learning, Accuracy  \nBreast cancer remains a leading global health concern, with an estimated 2.4 million new cases diagnosed in 2022 alone (World Health Organization [WHO], 2023) . Early detection is crucial for improving patient outcomes, with studies demonstrating significantly higher survival rates for cancers detected at earlier stages (American Cancer Society [ACS], 2024). Biopsy, the gold standard for definitive diagnosis1, involves microscopic examination of tissue samples by pathologists (Henry et al., 2018) . However, this visual analysis is inherently subjective and prone to errors due to inter-observer variability and limitations of human perception2. These limitations, compounded by the global shortage of pathologists3,4, pose a significant challenge to accurate and timely breast cancer diagnosis.  \nDigital pathology uses technology to convert tissue samples into digital images and applies computational algorithms for analysis2,5,6. These algorithms aim to detect information that is challenging for the human eye to detect. Despite advancements in the field, accurate diagnosis and treatment is still a challenge due to the need for skilled and experienced pathologists and the potential for misclassification due to human error. Automated classification of breast cancer from histopathological images is a crucial research area in medicine, driven by President Obama’s 2015 precision medicine initiatives7. The goal is to develop a reliable diagnostic system for breast cancer. Early detection of breast cancer is important as it can aid in disease treatment. Pathology  \n1Department of Mathematics, College of Science and Arts, King AbdulAziz University, 21911 Rabigh, Saudi Arabia.  \n2Department of Artificial Intelligence, FEST Iqra University Karachi, Karachi, Pakistan. 3Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, Johor, Malaysia. 4College of Business Administration, Management Information System, Northern Border University, Arar, Saudi Arabia. 5Department of Information Technology, College of Computer, Qassim University, Buraydah 51452, Saudi Arabia. 6Department of Computer Science, College of Co","cbCaig4qeNlTWP8S","https://ap.wps.com/l/cbCaig4qeNlTWP8S","pdf",4317674,24,"English","# Breast cancer diagnosis challenges\n## Proposed framework overview\n## Two-stage data augmentation with cWGAN\n## Multi-scale transfer learning with pre-trained CNNs\n## Experimental evaluation on BreakHis dataset\n## Motivation and background for automated pathology\n## Transfer learning and augmentation rationale","[{\"question\":\"What problem does the research address in breast cancer diagnosis?\",\"answer\":\"Existing methods face limitations including high cost, long processing time, and inter-observer variability, which can reduce diagnostic consistency and speed.\"},{\"question\":\"How does the framework use GANs in the proposed approach?\",\"answer\":\"It employs a conditional Wasserstein GAN (cWGAN) to generate synthetic breast cancer images conditioned on clinical data, improving training stability and enabling targeted feature incorporation.\"},{\"question\":\"What transfer learning and CNN models are integrated, and what results were achieved?\",\"answer\":\"The approach uses a multi-scale transfer learning scheme integrating DenseNet-201, NasNetMobile, and ResNet-101 with multi-scale feature enrichment. On the BreakHis dataset, it reports 99.2% accuracy for binary classification and 98.5% for multi-class classification.\"}]","Synergistic transfer learning and adversarial networks for breast cancer diagnosis - benign vs. invasive classification | PDF",1790188018,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/5c603ee23901fb9bc799ce9394af8e7b.webp",983,1291,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/67bd01d044ae24e3c3448240560ef8a8.webp",982,1290,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/df334797c6b274d62007a3280d3cb5ea.webp",981,1289,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/dc86e100c72683308c18ffaa9fd18e3e.webp",980,1287]