[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-345272-105":59,"doc-detail-345272-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","sthelar-a-multi-tissue-dataset-linking-spatial-transcriptomics-and-histology-for-cell-type-annotation","StHELaR, a multi-tissue dataset linking spatial transcriptomics and histology for cell type annotation","","StHELaR introduces a large-scale, pan-cancer reference dataset that integrates spatial transcriptomics with Hematoxylin and Eosin (H&E) whole-slide images to enable cell type annotation. The dataset includes 31 human Xenium FFPE sections spanning 16 tissue types across 22 cancerous and 9 non-cancerous patients, covering over 11 million uniquely assigned cells across curated cell-type categories. Tangram-based alignment, slide-specific clustering, and differential expression generate annotations, while co-registered H&E imagery yields segmentation- and classification-ready patch data with quality-control safeguards.",{"@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/sthelar-a-multi-tissue-dataset-linking-spatial-transcriptomics-and-histology-for-cell-type-annotation/345272/",{"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/sthelar-a-multi-tissue-dataset-linking-spatial-transcriptomics-and-histology-for-cell-type-annotation/345272.png","ImageObject",300,407,{"name":92,"@type":93},"Liam","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-28","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does StHELaR address in cancer research?","Question",{"text":112,"@type":113},"It addresses the need to characterize the tumor microenvironment and provide reliable cell type annotations by combining spatial transcriptomics with H&E whole-slide images.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What data and scale does the StHELaR dataset include?",{"text":117,"@type":113},"StHELaR comprises 31 human Xenium FFPE sections across 16 tissue types, covering 22 cancerous and 9 non-cancerous patients, with annotations for over 11 million unique biological cells.",{"name":119,"@type":110,"acceptedAnswer":120},"How are cell type annotations generated and validated?",{"text":121,"@type":113},"Annotations are derived via Tangram-based alignment to single-cell reference atlases, followed by slide-specific clustering and differential expression analysis, with quality control steps assessing segmentation accuracy and filtering low-confidence regions.","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},345272,1790670954,{"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":52,"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},8796095461564,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","[www. nature.com/scientificdata](www. nature.com/scientificdata)  \noPEN  \nData DESCRiPtoR  \nStHELaR, a multi-tissue dataset linking spatial transcriptomics and histology for cell type annotation  \nFélicie Giraud-Sauveur1,2 ✉, Quentin Blampey1,2, Hakim Benkirane1,2, arianna Marinello3, Paul-Henry Cournède1,2 ✉ & Stergios Christodoulidis1,2 ✉  \nUnderstanding the composition of the tumor microenvironment is critical for cancer research.  \nSpatial transcriptomics profiles gene expressions in spatial context, revealing tissue architecture and cellular heterogeneity, but its cost and technical complexity limit adoption. To address this issue, we introduce a pipeline to build StHELaR, a large-scale dataset that integrates spatial transcriptomics with Hematoxylin and Eosin (H&E) whole-slide images for cell type annotation. The dataset comprises 31 human Xenium FFPE sections across 16 tissue types, for 22 cancerous and 9 non-cancerous patients. It contains over 11 million unique biological cells, each assigned to one often curated celltype categories designed to accommodate a pan-cancer setting. Annotations were derived through Tangram-based alignment to single-cell reference atlases, followed by slide-specific clustering and differential expression analysis. Co-registered H&E images enabled the extraction of over 500,000 patches with segmentation and classification masks. Quality control steps assessed segmentation accuracy, filtered out low-confidence regions, and verified annotation integrity. STHELAR provides a reference resource for developing models to predict cell-type annotations directly from histological images.  \nBackground & Summary  \nCancer, a leading cause of mortality worldwide with nearly 10 million deaths in 2020, represents one of the most pressing public health challenges. Defined by uncontrolled cellular proliferation and invasive characteristics, cancer includes a broad spectrum of diseases affecting various tissues and organs 1. Modern oncology has evolved to view cancer as a complex ecosystem known as the tumor microenvironment (TME) . This evolving environment comprises cancer cells and a variety of non-malignant cell types embedded in a vascularized extracellular matrix. Immune, stromal, and vascular cells within the TME significantly influence tumor progression and resistance to treatments, and the composition of this environment varies considerably depending on tumor location, primary or metastatic sites, histological subtype, molecular features, previous systemic treatment or irradiation, response to treatment, and patient-specific characteristics. Consequently, a detailed characterization ofthe TME is essential for the development of effective anticancer therapies2.  \nSpatial transcriptomics (ST) has emerged as a powerful tool for understanding spatial organization and cellular heterogeneity within the TME, offering insights not possible through bulk or even single-cell RNA sequencing. ST offers the unique advantage of providing spatially resolved gene expression profiles, using either imaging-based or sequencing-based approaches. Imaging-based ST relies on fluorescent labeling and signal intensity to map targeted gene expression, whereas sequencing-based methods utilize spatial barcoding coupled with next-generation sequencing to spatially quantify gene expression within tissues. Among these technologies, the Xenium platform from 10x Genomics stands out as an advanced imaging-based method, providing subcellular spatial resolution while enabling exact alignment to whole-slide images (WSIs)3.  \n1 Paris-Saclay University, CentraleSupelec, Laboratory of Mathematics and Computer Science (MICS), Gif-surYvette, France. 2 IHU PRISM: National Center for Precision Medicine in Oncology, Gustave Roussy, Villejuif, France. 3 Department of Medical Oncology, Gustave Roussy, International Center for Thoracic Cancers, Villejuif, France. ✉[e-mail:](e-mail: felicie.giraud-sauveur@centralesupelec.fr)[ felicie.giraud-sauveur@c","cbCainUfm6ZSHWSC","https://ap.wps.com/l/cbCainUfm6ZSHWSC","pdf",13105685,38,"English","# Background & Summary\n## Tumor microenvironment and cancer research needs\n## Spatial transcriptomics and Xenium platform\n## Whole-slide images and digital pathology\n## Deep learning for histology workflows\n## Cell-level segmentation and classification foundations","[{\"question\":\"What problem does StHELaR address in cancer research?\",\"answer\":\"It addresses the need to characterize the tumor microenvironment and provide reliable cell type annotations by combining spatial transcriptomics with H\\u0026E whole-slide images.\"},{\"question\":\"What data and scale does the StHELaR dataset include?\",\"answer\":\"StHELaR comprises 31 human Xenium FFPE sections across 16 tissue types, covering 22 cancerous and 9 non-cancerous patients, with annotations for over 11 million unique biological cells.\"},{\"question\":\"How are cell type annotations generated and validated?\",\"answer\":\"Annotations are derived via Tangram-based alignment to single-cell reference atlases, followed by slide-specific clustering and differential expression analysis, with quality control steps assessing segmentation accuracy and filtering low-confidence regions.\"}]","StHELaR, a multi-tissue dataset linking spatial transcriptomics and histology for cell type annotation | PDF",1790057064,96,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/1fd3400926434fcdf7f8018dd2272e27.webp",983,1291,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/ba601d7a39f642f2ec408c1b16b02191.webp",982,1290,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/98e4009bfdb70d6fef412a350b863af2.webp",981,1289,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/08e6fbd1efb474fb0e2393104b321b20.webp",980,1287]