[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-344078-105":59,"doc-detail-344078-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","a-deep-fusion-based-vision-transformer-for-breast-cancer-classification","A deep fusion-based vision transformer for breast cancer classification","","Breast cancer remains a major cause of death, and early detection is difficult because histopathological signals are subtle and highly dependent on tissue structure and staining properties. Conventional CNNs and prior vision-transformer approaches often fail to capture both cell-layer patterns and whole-image processing effectively. A deep fusion-based vision Transformer model (DFViT) is proposed to fuse RGB and stain-normalized images, extracting local and global features. Experiments on BreakHis, BACH, and UCSC datasets show superior accuracy, F1 score, precision, and recall for diagnosis.",{"@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/a-deep-fusion-based-vision-transformer-for-breast-cancer-classification/344078/",{"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-deep-fusion-based-vision-transformer-for-breast-cancer-classification/344078.png","ImageObject",300,407,{"name":92,"@type":93},"Evangeline","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-01","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why are conventional CNN models insufficient for breast cancer histopathological classification?","Question",{"text":112,"@type":113},"They struggle to capture patterns of cell layers and staining properties, and they may not process whole-image information effectively, leading to reduced accuracy and diagnostic reliability.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What is the core idea of DFViT in this research?",{"text":117,"@type":113},"DFViT fuses RGB images with stain-normalized images and integrates CNN and transformer architectures to better extract complementary local and global features.",{"name":119,"@type":110,"acceptedAnswer":120},"Which datasets and performance metrics are used to evaluate DFViT?",{"text":121,"@type":113},"The model is trained and tested on BreakHis, BACH, and UCSC cancer genomics datasets, and evaluation reports accuracy, F1 score, precision, and recall.","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},344078,1790801157,{"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":44,"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},13056703019662,"https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188","DOI: 10.1049/htl2.12093  \nLETTER  \nA deep fusion-based vision transformer for breast cancer classiﬁcation  \nAhsan Fiaz1  Basit Raza1  Muhammad Faheem2   Aadil Raza3  \n1Department of Computer Science, COMSATS University Islamabad (CUI), Islamabad, Pakistan  \n2 School of Technology and Innovations, University of Vaasa, Vaasa, Finland  \n3Department of Physics, COMSATS University Islamabad (CUI), Islamabad, Pakistan  \nCorrespondence  \nMuhammad Faheem, School of Technology and Innovations, University of Vaasa, Vaasa, 65200, Finland.  \nEmail: muhammad.faheem@uwasa.ﬁ  \nAbstract  \nBreast cancer is one of the most common causes of death in women in the modern world. Cancerous tissue detection in histopathological images relies on complex features related to tissue structure and staining properties. Convolutional neural network (CNN) models like ResNet50, Inception-V1, and VGG-16, while useful in many applications, cannot capture the patterns of cell layers and staining properties. Most previous approaches, such as stain normalization and instance-based vision transformers, either miss important features or do not process the whole image effectively. Therefore, a deep fusion-based vision Transformer model (DFViT) that combines CNNs and transformers for better feature extraction is proposed. DFViT captures local and global patterns more effectively by fusing RGB and stain-normalized images. Trained and tested on several datasets, such as BreakHis, breast cancer histology (BACH), and UCSC cancer genomics (UC), the results demonstrate outstanding accuracy, F1 score, precision, and recall, setting a new milestone in histopathological image analysis for diagnosing breast cancer.  \n1  INTRODUCTION  \nCancer, particularly breast cancer, poses a signiﬁcant global health threat, with 19.3 million new cases reported in 2020 and 680,000 women succumbing to the disease [1] . Early detection is challenging due to subtle symptoms and the small size of lumps, emphasizing the need for a robust screening system [2] . Breast cancer can be either malignant or benign, with malignant cases being life-threatening and benign ones non-cancerous. Doctors typically rely on X-rays and microscope images for analysis, but manual interpretation is highly challenging [3] . Various diagnostic methods, such as mammography and staining techniques like haematoxylin-eosin, aid in analysing tissue conditions [4] .  \nComputer-aided diagnostic (CAD) systems play a crucial role in disease diagnosis by reducing workload and minimizing errors [5] . Despite advancements in CAD systems, diagnosing breast cancer remains difﬁcult due to the disease’s high prevalence, time-consuming procedures, and the variability of expert opinions [6] . Deep learning, particularly convolutional neural networks (CNNs), has emerged as a powerful tool for histological image classiﬁcation, helping to speed up diagnosis,  \nenhance the effectiveness of screening, and improve diagnostic consistency among pathologists [7–10] .  \nCNNs use convolution kernels to extract features, but class imbalance remains a challenge. Generative adversarial networks (GANs) have been applied to augment data samples, though GAN-generated data may not always accurately represent realworld scenarios [11, 12] . To address these issues, researchers have introduced attention-based high-order deep networks, which combine attention mechanisms with high-order statistical representations to capture more discriminating features in breast cancer images [13] .  \nThe Transformer architecture, based on attention mechanisms, has also proven effective in extracting global features from images, making it useful for image classiﬁcation [14] . CNN and Vision Transformer models, originally designed for natural image classiﬁcation, have shown reasonable performance on histopathology images. Still, CNN-based models struggle to detect the relative position patterns between cells and layers composed of clustering cells. Additionally, cell-layer lev","cbCaii7OQiTUENos","https://ap.wps.com/l/cbCaii7OQiTUENos","pdf",2822070,14,"English","# Introduction\n## Motivation for computer-aided diagnosis\n## Limitations of existing deep learning approaches\n## Role of CNNs and Transformers in histopathology","[{\"question\":\"Why are conventional CNN models insufficient for breast cancer histopathological classification?\",\"answer\":\"They struggle to capture patterns of cell layers and staining properties, and they may not process whole-image information effectively, leading to reduced accuracy and diagnostic reliability.\"},{\"question\":\"What is the core idea of DFViT in this research?\",\"answer\":\"DFViT fuses RGB images with stain-normalized images and integrates CNN and transformer architectures to better extract complementary local and global features.\"},{\"question\":\"Which datasets and performance metrics are used to evaluate DFViT?\",\"answer\":\"The model is trained and tested on BreakHis, BACH, and UCSC cancer genomics datasets, and evaluation reports accuracy, F1 score, precision, and recall.\"}]","A deep fusion-based vision transformer for breast cancer classification | PDF",1790052955,35,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/64245b5964e97da6704d4e55811ca8f3.webp",983,1291,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/4aaf0e88d38799022ff3fe0509460269.webp",982,1290,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/b0fe3fc551495e766eeebd458d08ac1c.webp",981,1289,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/41cfa95a1e9a330780e5dd05c147d95c.webp",980,1287]