[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-369474-105":59,"doc-detail-369474-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","mmsurv-a-multimodal-multi-instance-multi-cancer-survival-prediction-model-integrating-pathological-images-clinical-information-and-sequencing-data","MMsurv - a multimodal multi-instance multi-cancer survival prediction model integrating pathological images, clinical information, and sequencing data","","Accurate prediction of patient survival rates in cancer treatment is essential for effective therapeutic planning. MMSurv is an interpretable multimodal deep learning model that integrates hematoxylin and eosin-stained whole-slide images with clinical information and sequencing data. Tumor regions are segmented into tiles, encoded into one-dimensional features, and clinical variables are optimized via word-embedding inspired representations. A compact bilinear pooling plus transformer fusion method feeds a dual-layer multi-instance learning framework to filter irrelevant patches and predict survival risk. Cell segmentation of high-attention tiles improves interpretability. Evaluations on six cancers from The Cancer Genome Atlas show improved accuracy over single-image approaches, with average C-index rising from 0.6750 to 0.7283, and nearly 10% gains versus state-of-the-art baselines using C-index with five-fold cross-validation.",{"@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/mmsurv-a-multimodal-multi-instance-multi-cancer-survival-prediction-model-integrating-pathological-images-clinical-information-and-sequencing-data/369474/",{"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/mmsurv-a-multimodal-multi-instance-multi-cancer-survival-prediction-model-integrating-pathological-images-clinical-information-and-sequencing-data/369474.png","ImageObject",300,407,{"name":92,"@type":93},"Sophia Brooks","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-05","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",11,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does MMSurv address in cancer survival prediction?","Question",{"text":113,"@type":114},"It targets the need for more accurate survival-rate prediction while addressing limitations of existing models that do not fully exploit multimodal data for reliable confidence.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does MMSurv use whole-slide images, clinical data, and sequencing data?",{"text":118,"@type":114},"It segments tumor regions from WSIs into tiles and encodes each tile into feature vectors, optimizes clinical features using word-embedding inspired techniques, and fuses modalities using a compact bilinear pooling plus transformer method before multi-instance learning prediction.",{"name":120,"@type":111,"acceptedAnswer":121},"What evidence supports MMSurv’s performance and interpretability?",{"text":122,"@type":114},"On six cancer types from The Cancer Genome Atlas, multimodal modeling improves average C-index from 0.6750 to 0.7283 versus single-modal image input, and uses cell segmentation on high-attention tiles to enhance interpretability.","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},369474,1790212100,{"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":146,"preview_page_count":19,"preview_urls":147},962084925636,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","Briefings in Bioinformatics, 2025, 26(3), bbaf209  \n[https://doi.org/10.1093/bib/bbaf209](https://doi.org/10.1093/bib/bbaf209)  \nProblem Solving Protocol  \nMMsurv: a multimodal multi-instance multi-cancer survival prediction model integrating pathological images, clinical information, and sequencing data  \nHailong Yang1 , 2 ,‡, Jia Wang3 ,‡, Wenyan Wang1 , Shufang Shi2 ,4 , Lijing Liu5 , Yuhua Yao6 , Geng Tian2 , Peizhen Wang1 , *, Jialiang Yang2 , *  \n1 School of Electrical and Information Engineering, Anhui University of Technology, No. 1530 Maxiang Road, Huashan District, Ma’anshan, Anhui 243032, China  \n2 Department of Sciences, Geneis Beijing Co. , Ltd. , No. 31 Xinbei Road, Laiguangying, Chaoyang District, Beijing 100102, China  \n3 Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Thoracic Surgery II, Peking University Cancer Hospital & Institute, No. 52 Fucheng Road, Haidian District, Beijing 100142, P.R. China  \n4 Department of Pathology, Beijing Friendship Hospital, Capital Medical University, No. 95 Yong’an Road, Xicheng District, Beijing 100050, China  \n5 Qinghe Clinic, Beijing North Medical District, Chinese PLA General Hospital, No. 100 Youyi Road, Haidian District, Beijing 100080, China  \n6 School of Mathematics and Statistics, Hainan Normal University, No. 99 Longkunnan Road, Longhua District, Haikou, Hainan 571158, China  \n*Corresponding authors. Peizhen Wang, School of Electrical and Information Engineering, Anhui University of Technology, No. 1530 Maxiang Road, Huashan District, Ma’anshan, Anhui 243032, [China. E-mail:](China. E-mail: pzhwang@ahut.edu.cn)[ pzhwang@ahut.edu.cn](China. E-mail: pzhwang@ahut.edu.cn); Jialiang Yang, Department of Sciences, Geneis Beijing Co. , Ltd. , No. 31 Xinbei Road,  \nLaiguangying, Chaoyang District, Beijing 100102, [China. E-mail:](China. E-mail: yangjl@geneis.cn)[ yangjl@geneis.cn](China. E-mail: yangjl@geneis.cn)  \n‡Hailong Yang and Jia Wang contributed equally to this study.  \nAbstract  \nAccurate prediction of patient survival rates in cancer treatment is essential for effective therapeutic planning. Unfortunately, current models often underutilize the extensive multimodal data available, affecting confidence in predictions. This study presents MMSurv, an interpretable multimodal deep learning model to predict survival in different types of cancer. MMSurv integrates clinical information, sequencing data, and hematoxylin and eosin-stained whole-slide images (WSIs) to forecast patient survival. Specifically, we segment tumor regions from WSIs into image tiles and employ neural networks to encode each tile into one-dimensional feature vectors. We then optimize clinical features by applying word embedding techniques, inspired by natural language processing, to the clinical data. To better utilize the complementarity of multimodal data, this study proposes a novel fusion method, multimodal fusion method based on compact bilinear pooling and transformer, which integrates bilinear pooling with Transformer architecture. The fused features are then processed through a dual-layer multi-instance learning model to remove prognosis-irrelevant image patches and predict each patient’s survival risk. Furthermore, we employ cell segmentation to investigate the cellular composition within the tiles that received high attention from the model, thereby enhancing its interpretive capacity. We evaluate our approach on six cancer types from The Cancer Genome Atlas. The results demonstrate that utilizing multimodal data leads to higher predictive accuracy compared to using single-modal image data, with an average C-index increase from 0.6750 to 0.7283. Additionally, we compare our proposed baseline model with state-of-the-art methods using the C-index and five-fold cross-validation approach, revealing a significant average improvement of nearly 10% in our model’s performance.  \nKeywords: multi-instance learning; survival prediction; word em","cbCairJIhGE7W05T","https://ap.wps.com/l/cbCairJIhGE7W05T","pdf",2283210,14,"English","# Abstract\n# Keywords\n# Introduction","[{\"question\":\"What problem does MMSurv address in cancer survival prediction?\",\"answer\":\"It targets the need for more accurate survival-rate prediction while addressing limitations of existing models that do not fully exploit multimodal data for reliable confidence.\"},{\"question\":\"How does MMSurv use whole-slide images, clinical data, and sequencing data?\",\"answer\":\"It segments tumor regions from WSIs into tiles and encodes each tile into feature vectors, optimizes clinical features using word-embedding inspired techniques, and fuses modalities using a compact bilinear pooling plus transformer method before multi-instance learning prediction.\"},{\"question\":\"What evidence supports MMSurv’s performance and interpretability?\",\"answer\":\"On six cancer types from The Cancer Genome Atlas, multimodal modeling improves average C-index from 0.6750 to 0.7283 versus single-modal image input, and uses cell segmentation on high-attention tiles to enhance interpretability.\"}]","MMsurv - a multimodal multi-instance multi-cancer survival prediction model integrating pathological images, clinical information, and sequencing data | PDF",1790182884,35,[148,152,156,160],{"page_no":8,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/eebdf9814bd442a67d409e5c4df16974.webp",983,1291,{"page_no":14,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/f69c2eff9361b7fc44b9201c5de85434.webp",982,1290,{"page_no":81,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/16f4459334cb9805c84b400e4bcc6233.webp",981,1289,{"page_no":19,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/ccbacf42bdc3dbed05dd6949591d7d4a.webp",980,1287]