[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-332118-105":59,"doc-detail-332118-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","harnessing-tme-depicted-by-histological-images-to-improve-cancer-prognosis-through-a-deep-learning-system","Harnessing TME depicted by histological images to improve cancer prognosis - Through a deep learning system","","Spatial transcriptomics (ST) offers a detailed view of the tumor microenvironment (TME), which is tightly linked to cancer prognosis, but ST is limited in routine clinical use. This study introduces a deep learning system that augments TME information from histological images alone, enabling prognosis for patients without ST data. The integrated graph and image deep learning (IGI-DL) model predicts ST expression from histology, while a survival model uses predicted ST features to achieve strong accuracy on multiple cohorts and stable advantage on external data.",{"@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/harnessing-tme-depicted-by-histological-images-to-improve-cancer-prognosis-through-a-deep-learning-system/332118/",{"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/harnessing-tme-depicted-by-histological-images-to-improve-cancer-prognosis-through-a-deep-learning-system/332118.png","ImageObject",300,407,{"name":92,"@type":93},"Ivy","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-25","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":39},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the study address in cancer prognosis prediction?","Question",{"text":112,"@type":113},"It targets the difficulty of accurate survival prediction while fully capturing tumor microenvironment complexity at a molecular level, and the limited availability of spatial transcriptomics in clinical settings.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the proposed system work when ST data are unavailable?",{"text":117,"@type":113},"It uses histological images to predict spatial transcriptomics-related features through the IGI-DL model, then feeds these predicted features into a survival prediction model.",{"name":119,"@type":110,"acceptedAnswer":120},"What performance improvements are reported for survival prediction?",{"text":121,"@type":113},"The survival model using graphs with predicted ST features achieves superior accuracy, with concordance indices reported as 0.747 and 0.725 for TCGA breast cancer and colorectal cancer, and it maintains a stable advantage on an external colorectal cohort.","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},332118,1791062523,{"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":39,"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":4},549758252649,"https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819","Article  \nHarnessing TME depicted by histological images to improve cancer prognosis through a deep learning system  \nAuthors  \nRuitian Gao, Xin Yuan, Yanran Ma, ..., Jing Sun, Yu Guang Wang, Zhangsheng Yu  \nCorrespondence  \n[sj11788@rjh.com.cn](sj11788@rjh.com.cn) (J.S.),  \n[yuguang.wang@sjtu.edu.cn](yuguang.wang@sjtu.edu.cn) (Y.G.W.),  \n[yuzhangsheng@sjtu.edu.cn](yuzhangsheng@sjtu.edu.cn) (Z.Y.)  \nIn brief  \nGao et al. provide a powerful deep learning system for TME analysis and cancer prognosis from the aspect of histological images. The system can enhance survival prediction accuracy for all publicly available cancer cohorts using only histological images without the need for ST data.  \nd The IGI-DL model predicts molecular-level information based on histological images  \nd TME characterized by IGI-DL enhances cancer survival prediction accuracy  \nd The estimated risk score in our system is an independent cancer prognosis indicator  \nGao et al., 2024, Cell Reports Medicine 5, 101536  \nMay 21, 2024 ª 2024 The Authors. Published by Elsevier Inc.  \n[https://doi.org/10.1016/j.xcrm.2024.101536](https://doi.org/10.1016/j.xcrm.2024.101536)  \nll  \nll  \nOPEN ACCESS  \nArticle  \nHarnessing TME depicted by histological images to improve cancer prognosis  \nthrough a deep learning system  \nRuitian Gao,1,2 Xin Yuan,1,2 Yanran Ma,1,2 Ting Wei,1,2 Luke Johnston,3 Yanfei Shao,4 Wenwen Lv,5 Tengteng Zhu,5 Yue Zhang,1,2 Junke Zheng,6 Guoqiang Chen,7 Jing Sun,4,* Yu Guang Wang,3,8,9,* and Zhangsheng Yu1,2,3,5,10,*  \n1Department of Bioinformatics and Biostatistics, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai 200240, China  \n2SJTU-Yale Joint Center for Biostatistics and Data Science, Shanghai Jiao Tong University, Shanghai 200240, China  \n3School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai 200240, China  \n4Department of General Surgery, Shanghai Minimally Invasive Surgery Center, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China  \n5Clinical Research Institute, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China  \n6Key Laboratory of Cell Differentiation and Apoptosis of the Chinese Ministry of Education, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China  \n7State Key Laboratory of Systems Medicine for Cancer, Ren-Ji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China  \n8Institute of Natural Sciences, Shanghai Jiao Tong University, Shanghai 200240, China  \n9Zhangjiang Institute of Advanced Research, Shanghai Jiao Tong University, Shanghai 201203, China  \n10Lead contact  \n*Correspondence: [sj11788@rjh.com.cn](sj11788@rjh.com.cn) (J.S.), [yuguang.wang@sjtu.edu.cn](yuguang.wang@sjtu.edu.cn) (Y.G.W.), [yuzhangsheng@sjtu.edu.cn](yuzhangsheng@sjtu.edu.cn) (Z.Y.) [https://doi.org/10.1016/j.xcrm.2024.101536](https://doi.org/10.1016/j.xcrm.2024.101536)  \nSUMMARY  \nSpatial transcriptomics (ST) provides insights into the tumor microenvironment (TME), which is closely associated with cancer prognosis, but ST has limited clinical availability. In this study, we provide a powerful deep learning system to augment TME information based on histological images for patients without ST data, thereby empowering precise cancer prognosis. The system provides two connections to bridge existing gaps. The first is the integrated graph and image deep learning (IGI-DL) model, which predicts ST expression based on histological images with a 0.171 increase in mean correlation across three cancer types compared with five existing methods. The second connection is the cancer prognosis prediction model, based on TME depicted by spatial gene expression. Our survival model, using graphs with predicted ST features, achieves superior accuracy with a concordance index of 0.747 and 0.725 for The Cancer Genome Atlas breast cancer and colorectal cancer cohorts, outperforming other survival models. For the external Mol","cbCais6QA1CGzSh6","https://ap.wps.com/l/cbCais6QA1CGzSh6","pdf",8404067,22,"English","# Summary\n# Introduction\n## Prognosis prediction challenges and the role of histology\n## Limitations of spatial transcriptomics\n## Motivation for a deep learning approach","[{\"question\":\"What problem does the study address in cancer prognosis prediction?\",\"answer\":\"It targets the difficulty of accurate survival prediction while fully capturing tumor microenvironment complexity at a molecular level, and the limited availability of spatial transcriptomics in clinical settings.\"},{\"question\":\"How does the proposed system work when ST data are unavailable?\",\"answer\":\"It uses histological images to predict spatial transcriptomics-related features through the IGI-DL model, then feeds these predicted features into a survival prediction model.\"},{\"question\":\"What performance improvements are reported for survival prediction?\",\"answer\":\"The survival model using graphs with predicted ST features achieves superior accuracy, with concordance indices reported as 0.747 and 0.725 for TCGA breast cancer and colorectal cancer, and it maintains a stable advantage on an external colorectal cohort.\"}]","Harnessing TME depicted by histological images to improve cancer prognosis - Through a deep learning system | PDF",1789996890,55]