[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-355213-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-355213-en":130},{"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","hist-histological-images-reconstruct-tumor-spatial-transcriptomics-via-multiscale-fusion-deep-learning","HiST: Histological Images Reconstruct Tumor Spatial Transcriptomics via MultiScale Fusion Deep Learning","","Spatial transcriptomics (ST) integrates molecular features with spatial context to clarify the tumor microenvironment, yet its clinical adoption is constrained by high costs. HiST presents a multi-scale convolutional deep learning framework that maps spatial gene expression profiles (GEPs) to histological morphology from H&E images. HiST predicts tumor regions across multiple cancer types with strong agreement to pathologist labels and reconstructs spatially resolved GEPs with substantially improved correlation and enables prognosis, immunotherapy response, and pathway marker analyses.",{"@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/hist-histological-images-reconstruct-tumor-spatial-transcriptomics-via-multiscale-fusion-deep-learning/355213/",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/hist-histological-images-reconstruct-tumor-spatial-transcriptomics-via-multiscale-fusion-deep-learning/355213.png","ImageObject",300,407,{"name":42,"@type":43},"Riley","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-03","2026-09-22",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",9,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What limitation of spatial transcriptomics does HiST target?","Question",{"text":63,"@type":64},"HiST addresses the high cost and limited feasibility of spatial transcriptomics for routine clinical use.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does HiST use histological images in its modeling approach?",{"text":68,"@type":64},"HiST uses multi-scale convolutional deep learning to learn the relationship between spatially resolved gene expression profiles and histological morphology from histological images.",{"name":70,"@type":61,"acceptedAnswer":71},"What downstream clinical tasks are supported by HiST’s reconstructed profiles?",{"text":72,"@type":64},"The predicted spatial GEPs enable tumor heterogeneity assessment, patient prognosis stratification, and immunotherapy response prediction with pathway enrichment analyses.","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},355213,1790615270,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,119,122,126],{"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":55,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":33,"preview_urls":146},1374391975076,"https://ap-avatar.wpscdn.com/avatar/14000253ca4ec9f6853?x-image-process=image/resize,m_fixed,w_180,h_180&k=1783305029341752051","Advanced Science    \n[www.advancedscience.com](www.advancedscience.com)  \n RESEARCH ARTICLE   \nHiST: Histological Images Reconstruct Tumor Spatial Transcriptomics via MultiScale Fusion Deep Learning  \nWei Li1  Dong Zhang2  Eryu Peng2  Shijun Shen1  Hamid Alinejad-Rokny5  Yao Liu3  Junke Zheng4  Cizhong Jiang1  Youqiong Ye2   \n1 Shanghai Tenth People’s Hospital, Shanghai Key Laboratory of Signaling and Disease Research, School of Life Sciences and Technology, Tongji University, Shanghai, China  2 Shanghai Institute of Immunology, Department of Immunology and Microbiology, Shanghai Jiao Tong University School of Medicine, Shanghai, China  3 Department of Hepatobiliary Surgery, State Key Laboratory of Immune Response and Immunotherapy, Centre For Leading Medicine and Advanced Technologies of IHM, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, China  4 Institute for Translational Medicine On Cell Fate and Disease, Shanghai Ninth People’s Hospital, Key Laboratory of Cell Differentiation and Apoptosis of National Ministry of Education, Department of Pathophysiology, Shanghai Jiao Tong University School of Medicine, Shanghai, China   \n5UNSW BioMedical Machine Learning Lab (BML) School of Biomedical Engineering, UNSW Sydney, Sydney, NSW, Australia  \nCorrespondence: Yao Liu ([liuyao66@ustc.edu.cn](liuyao66@ustc.edu.cn))  Junke Zheng (zhengjunke@shsmu.edu.cn)  Cizhong Jiang (czjiang@tongji.edu.cn)  Youqiong Ye ([youqiong.ye@shsmu.edu.cn](youqiong.ye@shsmu.edu.cn))  \nReceived: 29 July 2025  Revised: 3 December 2025  Accepted: 15 December 2025  \nKeywords: HiST | histological image | prognosis and immunotherapy efficacy prediction | spatial transcriptomics | tumor spot identification  \nABSTRACT  \nSpatial transcriptomics (ST) provides valuable insights into the tumor microenvironment by integrating molecular features with spatial context; however, its clinical utility is limited by high costs. To address this, we develop a multi-scale convolutional deep learning framework, HiST, which utilizes ST to learn the relationship between spatially resolved gene expression profiles (GEPs) and histological morphology. HiST accurately predicts tumor regions across multiple cancer types (e.g., breast cancer; area under the curve: 0.96), demonstrating high concordance with pathologist annotations. Moreover, HiST reconstructs spatially resolved GEPs from histological images with an average Pearson correlation coefficient of 0.74 across five cancer types, outperforming existing models by about two-fold. These high-fidelity spatial GEPs enable tumor heterogeneity assessment from histological images, including identification of tumor subtypes with distinct DNA copy number variations. We demonstrate the clinical utility of the predicted GEPs, which robustly stratify patient prognosis across five cancer types from The Cancer Genome Atlas (e.g., breast cancer; concordance index: 0.78) . The predicted profiles further facilitate immunotherapy response prediction and enrichment analyses of relevant biological pathways and markers. Collectively, HiST achieves state-of-the-art performance in spatial GEPreconstruction, providing a reliable molecular representation that enhances downstream tasks such as tumor profiling and clinical analyses.  \n1  Introduction  \nIn clinical practice, pathologists diagnose cancer by analyzing tissue structure and cellular abnormalities in histological images,  \nsuch as Hematoxylin and Eosin (HE)-stained sections [1, 2] . However, the complexity and diversity of stained images, coupled with differences in pathologist experience and subjectivity, may lead to diagnostic inconsistencies [3–6] . Moreover, the tumor  \n\n| Wei Li and Dong Zhang contributed equally to this work.\u003Cbr>|\n| --- |\n| This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provi","cbCaih3rf7Z67dVJ","https://ap.wps.com/l/cbCaih3rf7Z67dVJ","pdf",12731137,17,"English","# Abstract\n# Introduction","[{\"question\":\"What limitation of spatial transcriptomics does HiST target?\",\"answer\":\"HiST addresses the high cost and limited feasibility of spatial transcriptomics for routine clinical use.\"},{\"question\":\"How does HiST use histological images in its modeling approach?\",\"answer\":\"HiST uses multi-scale convolutional deep learning to learn the relationship between spatially resolved gene expression profiles and histological morphology from histological images.\"},{\"question\":\"What downstream clinical tasks are supported by HiST’s reconstructed profiles?\",\"answer\":\"The predicted spatial GEPs enable tumor heterogeneity assessment, patient prognosis stratification, and immunotherapy response prediction with pathway enrichment analyses.\"}]","HiST: Histological Images Reconstruct Tumor Spatial Transcriptomics via MultiScale Fusion Deep Learning | PDF",1790116765,43,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/b3efab6f735bc40bff1913f36e34bb0e.webp",983,1291,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/6a2ab6a22dab76fa80647fbec28e2399.webp",982,1290,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/4b01fbbc09d218812ff7bc4d512e471f.webp",981,1289,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/60aa3033ba333eae5dae04ddab29c7e2.webp",980,1287]