[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-355454-105":59,"doc-detail-355454-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","magnification-independent-breast-cancer-diagnosis-using-a-gwo-enhanced-vision-transformer-with-multi-stage-stain-normalization","Magnification-independent breast cancer diagnosis using a GWO-enhanced vision transformer with multi-stage stain normalization","","Breast cancer diagnosis from histopathological images remains challenging due to staining variability, magnification differences, and complex tissue morphology. A preprocessing, balancing, and classification framework is developed for the BreakHis dataset using a four-stage stain normalization pipeline (CLAHE, histogram matching, Shades-of-Gray correction, and Macenko). A magnification-specific augmentation strategy mitigates severe class imbalance and standardizes benign/malignant representation. Separate ViT models for 40X/100X/200X/400X are optimized with Grey Wolf Optimizer hyperparameter tuning, achieving robust cross-validation performance and high accuracies across magnifications, supporting clinical integration.",{"@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/magnification-independent-breast-cancer-diagnosis-using-a-gwo-enhanced-vision-transformer-with-multi-stage-stain-normalization/355454/",{"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/magnification-independent-breast-cancer-diagnosis-using-a-gwo-enhanced-vision-transformer-with-multi-stage-stain-normalization/355454.png","ImageObject",300,407,{"name":92,"@type":93},"Maya Linwood","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-06","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",13,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why is magnification-independent breast cancer diagnosis difficult in histopathology images?","Question",{"text":113,"@type":114},"Staining variability, differences in magnification, and complex tissue morphology make manual and automated diagnosis inconsistent across samples.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What stain normalization pipeline is used in the proposed framework?",{"text":118,"@type":114},"The method applies a four-stage normalization sequence: CLAHE, histogram matching, Shades-of-Gray correction, and Macenko stain normalization to standardize color distribution and structure clarity.",{"name":120,"@type":111,"acceptedAnswer":121},"How does the approach address class imbalance and improve model performance?",{"text":122,"@type":114},"A targeted magnification-specific augmentation expands the dataset to equalize benign and malignant representation, and separate ViT models are tuned with Grey Wolf Optimizer for robust performance across magnifications.","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},355454,1790471503,{"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},962084928432,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nMagnification-independent breast cancer diagnosis using a GWOenhanced vision transformer with multi-stage stain normalization  \nTaiyaba Fatma1, Prabhat Kumar Sahu2􀀍, Sasanka Choudhury3 & Aneesh Wunnava4  \nBreast cancer diagnosis from histopathological images remains a critical yet challenging task due to staining variability, magnification differences, and complex tissue morphology. This study presentsa comprehensive preprocessing, balancing, and classification framework for the BreakHis dataset, integrating advanced stain normalization, magnification-wise augmentation, and an optimized Vision Transformer architecture. A four-stage normalization pipeline comprising CLAHE, histogram matching, Shades-of-Gray correction, and Macenko stain normalization was developed to standardize color distribution and enhance structural clarity across 7909 images. To address severe class imbalance, a targeted magnification-specific augmentation strategy expanded the dataset to 11,848 images with equal benign and malignant representation. A Vision Transformer (ViT) model was designed for each of the four magnifications (40X, 100X, 200X, 400X), and further optimized using the Grey Wolf Optimizer (GWO) to automatically tune hyperparameters such as transformer depth, attention heads, embedding dimensions, dropout, and learning rate. Experimental results demonstrate high and consistent performance across magnifications, with accuracies of 92.1%, 92.9%, 93.5%, and 94.0%, respectively. Cross-validation reveals minimal variance, confirming model robustness and generalization. The proposed GWO-ViT framework establishes a reliable, magnification-invariant, and computationally efficient solution for automated breast cancer histopathology classification, offering strong potential for clinical integration.  \nKeywords BreakHis dataset, Vision transformer (ViT), Grey wolf optimizer (GWO), Stain normalization, Data augmentation, Magnification-invariant modeling, Deep learning  \nBreast cancer is still a widespread and dangerous illness globally, remaining a significant health issue because many people get it, it has different forms, and deaths from it are increasing. According to recent worldwide cancer reports, breast cancer now has more new cases each year than any other cancer, with millions diagnosed and a large number of women dying from it. Early detection is critical because survival rates are significantly higher when the disease is identified in its initial stages, allowing clinicians to provide personalized and effective treatment strategies. Histopathological examination of biopsy tissue is the clinical gold standard for diagnosing breast cancer, as it allows detailed evaluation of cellular morphology, structural abnormalities, and tumor invasiveness. Nevertheless, making diagnoses by hand using microscopes demands a lot of effort, takes a significant amount of time, and can differ based on who is looking at the samples, especially when slight variations in tissue need to be spotted using different levels of magnification.  \nArtificial intelligence has significantly improved the automation of medical imaging processes, especially fortasks involving image classification, segmentation, and object detection. Within AI, deep learning has become a dominant approach for developing modern computer-aided diagnosis (CAD) systems1,2.In the past, the majority of computer-aided detection (CAD) systems designed to identify breast cancer have used convolutional neural networks (CNNs) as the primary structural component. Rapid advancement of deep neural networks that use  \n1Department of Computer Science and Engineering, Siksha ‘O’ Anusandhan (Deemed to be University), Bhubaneswar, Odisha, India. 2Department of Computer Science and Information Technology, Siksha ‘O’Anusandhan (Deemed to be University), Bhubaneswar, Odisha, India. 3Department of Mechanical Engineering, Siksha ‘O’ Anusand","cbCaieR8i8ys1Yfx","https://ap.wps.com/l/cbCaieR8i8ys1Yfx","pdf",4979222,24,"English","# Background and Motivation\n# Histopathology and Staining/Magnification Challenges\n# AI and Vision Transformers for CAD\n# Proposed Framework\n## Multi-stage Stain Normalization\n## Magnification-wise Augmentation for Class Imbalance\n## GWO-optimized Multi-magnification ViT Models\n# Experimental Results and Robustness\n# Conclusion and Clinical Potential","[{\"question\":\"Why is magnification-independent breast cancer diagnosis difficult in histopathology images?\",\"answer\":\"Staining variability, differences in magnification, and complex tissue morphology make manual and automated diagnosis inconsistent across samples.\"},{\"question\":\"What stain normalization pipeline is used in the proposed framework?\",\"answer\":\"The method applies a four-stage normalization sequence: CLAHE, histogram matching, Shades-of-Gray correction, and Macenko stain normalization to standardize color distribution and structure clarity.\"},{\"question\":\"How does the approach address class imbalance and improve model performance?\",\"answer\":\"A targeted magnification-specific augmentation expands the dataset to equalize benign and malignant representation, and separate ViT models are tuned with Grey Wolf Optimizer for robust performance across magnifications.\"}]","Magnification-independent breast cancer diagnosis using a GWO-enhanced vision transformer with multi-stage stain normalization | PDF",1790119006,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/e1ab6d45fd521be8ebce10b012a989cf.webp",983,1291,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/30ce6a98c0795805a7454930d4f337cd.webp",982,1290,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/7b933272c33a9f81ea84f38d1fe50a57.webp",981,1289,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/58f8951ea58061530683215a894392cc.webp",980,1287]