[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-354433-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-354433-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","survgrn-a-multi-feature-fusion-framework-for-bladder-cancer-survival-prediction","SurvGRN - a multi-feature fusion framework for bladder cancer survival prediction","","Bladder cancer survival outcomes show substantial heterogeneity driven by multifactorial influences. While AI-enabled digital pathology models are promising, they frequently miss complementary information: imaging omits cellular-level detail, whereas genomics and proteomics remain complex and costly. SurvGRN integrates clinical variables, transcriptomics, and digital pathology slides through a gated residual network, extracting pathology features via multiple instance learning and fusing them with an LSTM for survival risk assessment. On 400 patients, it improves the C-index by 12.6% versus DeepMISL and outperforms multiple graph- and attention-based baselines, with ablation confirming the contributions of each data source and fusion component.",{"@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/survgrn-a-multi-feature-fusion-framework-for-bladder-cancer-survival-prediction/354433/",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/survgrn-a-multi-feature-fusion-framework-for-bladder-cancer-survival-prediction/354433.png","ImageObject",300,407,{"name":42,"@type":43},"Well Done","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-25","2026-09-22",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",6,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does SurvGRN address in bladder cancer survival prediction?","Question",{"text":63,"@type":64},"SurvGRN targets the heterogeneity of bladder cancer survival and the limitations of existing models that rely on only one data type. It aims to improve prediction by integrating complementary clinical, transcriptomic, and digital pathology information.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does SurvGRN fuse pathology, clinical, and transcriptomic data?",{"text":68,"@type":64},"SurvGRN uses multiple instance learning to extract pathological features, treats clinical and transcriptomic inputs as static features, and then dynamically fuses the multi-source representations using an LSTM-based mechanism for survival risk assessment.",{"name":70,"@type":61,"acceptedAnswer":71},"How well does SurvGRN perform compared with existing approaches?",{"text":72,"@type":64},"Evaluated on 400 bladder cancer patients, SurvGRN improves the C-index by 12.6% over DeepMISL and by 20.6% and 7.1% over graph-based models. It also shows gains over attention-based approaches and is supported by ablation studies validating each component.","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},354433,1791450239,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,105,110,114,119,122,126],{"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":55,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"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":111,"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},5909892210082,"https://ap-avatar.wpscdn.com/avatar/56001069da27c9f41e8?x-image-process=image/resize,m_fixed,w_180,h_180&k=1789614185077863061","SurvGRN: a multi-feature fusion framework for bladder cancer survival prediction  \nQiangjian Zhang, MSca , Na Zhao, PhDa , Kai Song, MScb , Xun Ye, MSca , Hongxin Xiang, PhDc , ZhiWei Zhao, BSa ,  \nLi Qi, BSa , Qing Zhang, PhDb , Rui Guo, MScb , Junwei He, MScb , Jiaxin Liang, MScb , Shi Fu, MDd , Haifeng Wang, MDd , Xiaogang Li, MDe , Yingxia Wang, MDf, Yingying Pu, PhDg , Jian Wang, PhDh ,*, Chunming Guo, PhDb ,*  \nAbstract  \nBladder cancer survival outcomes exhibit significant heterogeneity, influenced by multifaceted factors. While digital pathologybased survival models leveraging artificial intelligence show promise, they often overlook complementary data sources. Conversely, imaging lacks cellular detail, and genomics/proteomics entail complexity and cost. To integrate multidimensional data for enhanced survival prediction, we propose SurvGRN, a multi-feature fusion framework. SurvGRN synergistically combines clinical variables, transcriptomics, and digital pathology slides using a gated residual network architecture. Pathological features are extracted via multiple instance learning, while clinical and transcriptomic data are processed as static inputs. These features are dynamically fused using a long short-term memory (LSTM) network for comprehensive survival risk assessment. Evaluated on 400 bladder cancer patients, SurvGRN significantly outperformed existing methods: improving the C-index by 12.6% over DeepMISL; 20.6% and 7. 1% over graph-based models (DeepGraphConv and Patch-GCN); and 5.4% and 4.0% over attentionbased approaches (Surformer and HVTSurv) . Ablation studies confirmed the contributions of pathology features (extracted via ResNet-50 pre-trained on bladder tissue), clinical/transcriptomic data, and the LSTM fusion. SurvGRN also enabled significant stratification of patients into distinct risk cohorts. This work demonstrates that holistic integration of multi-source data through tailored fusion architectures substantially improves bladder cancer survival prediction.  \nKeywords: bladder cancer, gated residual networks, multi-feature fusion, patient survival outcomes prediction  \nIntroduction  \nAs a common urological malignancy, the incidence of bladder cancer has been steadily increasing[1] . In 2020, there were nearly  \naSchool of Software and AI, Yunnan University, Kunming, Yunnan, China, bYunnan Key Laboratory of Cell Metabolism and Disease, and Center for Life Sciences, School of Life Sciences, Yunnan University, Kunming, Yunnan, China, cCollege of Computer Science and Electronic Engineering, Hunan University, Changsha, China, dDepartment of Urology, The Second Affiliated Hospital of Kunming Medical  \nUniversity, Kunming, China, eDepartment of General Surgery, Affiliated Hospital of Yunnan University, Kunming, Yunnan, China, fThe Department of Pathology of First affiliated Hospital, Kunming Medical University, Kunming, Yunnan, China, gThe State Key Laboratory Breeding Base of Basic Science ofStomatology & Key Laboratory of Oral Biomedicine Ministry of Education, School & Hospital ofStomatology, Medical Research Institute, Wuhan University, China and hCollege of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China Qiangjian Zhang and Na Zhao contributed equally to this work.  \nSponsorships or competing interests that may be relevant to content are disclosed at the end of this article.  \n*Corresponding authors. Address: Yunnan Key Laboratory of Cell Metabolism and Disease, Center forLife Sciences, School ofLife Sciences, Yunnan University, Kunming, Yunnan 650500, China. Tel.: +[86 13099424960. E-mail: jianwang@kust.edu.cn](86 13099424960. E-mail: jianwang@kust.edu.cn)[ ](86 13099424960. E-mail: jianwang@kust.edu.cn)(J. Wang); Tel.: +[86 13472581860. E-mail: chunmingguo@ynu.edu.cn](86 13472581860. E-mail: chunmingguo@ynu.edu.cn) (C. Guo). Copyright © 2026 The Author(s). Published by Wolters Kluwer Health, Inc. This is an open access article distributed under","cbCaikjgTWbVrpQL","https://ap.wps.com/l/cbCaikjgTWbVrpQL","pdf",2025234,13,"English","# Abstract\n# Introduction\n# Highlights","[{\"question\":\"What problem does SurvGRN address in bladder cancer survival prediction?\",\"answer\":\"SurvGRN targets the heterogeneity of bladder cancer survival and the limitations of existing models that rely on only one data type. It aims to improve prediction by integrating complementary clinical, transcriptomic, and digital pathology information.\"},{\"question\":\"How does SurvGRN fuse pathology, clinical, and transcriptomic data?\",\"answer\":\"SurvGRN uses multiple instance learning to extract pathological features, treats clinical and transcriptomic inputs as static features, and then dynamically fuses the multi-source representations using an LSTM-based mechanism for survival risk assessment.\"},{\"question\":\"How well does SurvGRN perform compared with existing approaches?\",\"answer\":\"Evaluated on 400 bladder cancer patients, SurvGRN improves the C-index by 12.6% over DeepMISL and by 20.6% and 7.1% over graph-based models. It also shows gains over attention-based approaches and is supported by ablation studies validating each component.\"}]","SurvGRN - a multi-feature fusion framework for bladder cancer survival prediction | PDF",1790110634,33,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/5a503a7c88136f6b88b6041b3c44c879.webp",983,1310,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/6eae09645c1f94d4e178b8dc4ee3c29d.webp",982,1309,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/fa7a1371e3114af7b640999a09beaba3.webp",981,1308,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/7cd3e226f45c6d46856e69057b29af20.webp",980,1306]