[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-detail-346475-en":59,"doc-seo-346475-105":98},{"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":5,"data":60},{"doc_id":61,"user_id":62,"nickname":63,"user_avatar":64,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":66,"doc_content":67,"file_id":68,"file_url":69,"file_type":70,"file_size":71,"view_count":52,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":44,"language":72,"language_code":73,"site_id":74,"html_lang":73,"table_of_contents":75,"faqs":76,"seo_title":77,"seo_description":66,"update_tm":78,"read_time":79,"preview_page_count":19,"preview_urls":80},346475,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487","Beyond origin - multimodal AI synthesis to resolve cancers of unknown primary","Oncology’s origin-based paradigm often breaks down for cancer of unknown primary (CUP), where metastatic disease is present but the primary tumor cannot be identified. CUP affects about 1%–3% of diagnoses and has a median overall survival of only 2–12 months, limiting patients to broad empirical chemotherapy and excluding many from targeted therapy. The article argues that combining high-dimensional biological data with advanced AI enables prospective, multimodal synthesis, improving tumor of origin inference and offering new diagnostic and therapeutic pathways.","Cancer Biol Med 2026. doi: 10.20892/j.issn.2095-3941.2025.0636  \nPERSPECTIVE  \nBeyond origin: multimodal AI synthesis to resolve cancers of unknown primary  \nHongru Shen, Xiangchun Li  \nKey Laboratory of Cancer Prevention and Therapy, Tianjin’s Clinical Research Center for Cancer, Tianjin Medical University Cancer Institute & Hospital, National Clinical Research Center for Cancer, Tianjin Medical University, Tianjin 300060, China  \nFor decades, the central dogma of oncology has been that a cancer’s identity is inextricably linked to its anatomical origin. This principle underpins the entire diagnostic and therapeutic framework, from histology-based classification to site-specific treatment guidelines. Yet, this framework catastrophically fails for a substantial population of patients diagnosed with cancer of unknown primary (CUP). These patients present metastatic disease, yet their primary tumors remain elusive despite exhaustive clinical workup 1. CUP, accounting for 1%–3% of all cancer diagnoses, is an enigma with devastating consequences; the median overall survival is only 2–12 months2-4. The inability to pinpoint an origin forces clinicians to rely on broad-spectrum empirical chemotherapy, such as taxane-carboplatin regimens, which have limited efficacy and exclude patients from the promise of targeted therapies and clinical trials5. CUP is not only a diagnostic challenge but also an indictment of the siloed approach to understanding malignancy: this cancer highlights the limitations of origin-based diagnostic frameworks. However, the confluence of high-dimensional biological data and advanced artificial intelligence (AI) is now poised to address this long-standing diagnostic limitation and to herald a new era for not only CUP but also oncology as a whole (Figure 1) .  \nA revolution in silos: the rise of unimodal predictors  \nThe past decade has witnessed a remarkable, albeit fragmented, revolution in the ability to infer a tumor’s tissue of origin (TOO). AI and machine learning have been the driving  \nCorrespondence to: Xiangchun Li  \nE-mail: [lixiangchun@tmu.edu.cn](lixiangchun@tmu.edu.cn)  \nORCID ID: [https://orcid.org/0000-0002-2230-2152](https://orcid.org/0000-0002-2230-2152)  \n[Received October 15](Received October 15), 2025; accepted December 22, 2025. Available [at www.cancerbiomed.org](at www.cancerbiomed.org)  \n©2026 The Authors. Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4 .0)  \nforce enabling the extraction of subtle, predictive patterns from complex biological data that were previously invisible to human experts.  \nIn genomics, comprehensive profiling has moved beyond identifying single driver mutations to providing rich molecular fingerprints of individual tumors. Gene expression profiling and next-generation sequencing have become foundational. AI models such as CUP-AI-Dx have demonstrated high accuracy in predicting TOO from RNA expression data6. More recently, a new generation of deep learning models such as OncoNPC and GDD-ENS has enabled patterns in somatic mutations from clinically standard gene panels to be leveraged to classify tumor types with impressive performance, thus offering a more accessible route to genomic diagnosis7,8 . The emergence of large language models such as OncoChat, trained on vast genomic datasets, has further advanced the frontier of classification and diagnostic support9. These tools are beginning to deliver on the promise of molecularly guided therapy. The landmark CUPISCO and Fudan CUP-001 clinical trials have recently demonstrated that using molecular information to guide treatment, through either histology-agnostic targeted therapy or site-specific therapy, results in longer progression-free survival than standard empirical chemotherapy, thus providing definitive evidence of the clinical utility of this approach4,10,11 .  \nSimultaneously, a parallel revolution has unfolded in pathology. Deep learning models have shown that cellular morp","cbCairCvJ3lUlbIO","https://ap.wps.com/l/cbCairCvJ3lUlbIO","pdf",1247272,"English","en",105,"# Beyond origin: multimodal AI synthesis to resolve cancers of unknown primary\n## A revolution in silos: the rise of unimodal predictors\n## Against the current: the challenge of conventional diagnosis\n## With the current: multimodal AI-powered diagnostic synthesis\n## Defining the flow","[{\"question\":\"What is the core problem addressed by the article regarding cancer of unknown primary (CUP)?\",\"answer\":\"CUP presents metastatic disease while the primary tumor remains elusive despite exhaustive clinical workup, making origin-based diagnosis and treatment ineffective for many patients.\"},{\"question\":\"Why do origin-based diagnostic frameworks fail for CUP?\",\"answer\":\"The inability to pinpoint anatomical origin forces clinicians into broad-spectrum empirical chemotherapy, which has limited efficacy and prevents access to targeted therapies and clinical trials.\"},{\"question\":\"How does multimodal AI aim to improve CUP diagnosis and treatment selection?\",\"answer\":\"The article highlights advances where genomics, pathology images, and imaging features are integrated with AI models to infer tumor identity more effectively and support molecularly guided therapeutic strategies.\"}]","Beyond origin - multimodal AI synthesis to resolve cancers of unknown primary | PDF",1790061595,23,[81,85,89,94],{"page_no":8,"url":82,"width":83,"height":84},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/1f0316e3ad5d412104b86d903d3405ba.webp",983,1287,{"page_no":14,"url":86,"width":87,"height":88},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/052b935d30055ccec16f09345b3028d5.webp",982,1286,{"page_no":90,"url":91,"width":92,"height":93},3,"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/29d13c4c3029beee60c802f0c9296db1.webp",981,1284,{"page_no":19,"url":95,"width":96,"height":97},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/6502dde20098e701637e0f1d52bc9b90.webp",980,1283,{"code":4,"msg":99,"data":100},"ok",{"site_id":74,"language":73,"slug":101,"title":65,"keywords":102,"description":66,"schema_data":103,"social_meta":156,"head_meta":158,"extra_data":160,"updated_unix":161},"beyond-origin-multimodal-ai-synthesis-to-resolve-cancers-of-unknown-primary","",{"@graph":104,"@context":155},[105,118,138],{"@type":106,"itemListElement":107},"BreadcrumbList",[108,112,114,116],{"item":109,"name":110,"@type":111,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":113,"name":9,"@type":111,"position":14},"https://docshare.wps.com/document/",{"item":115,"name":40,"@type":111,"position":90},"https://docshare.wps.com/document/research-report/",{"item":117,"name":65,"@type":111,"position":19},"https://docshare.wps.com/document/beyond-origin-multimodal-ai-synthesis-to-resolve-cancers-of-unknown-primary/346475/",{"url":117,"name":65,"@type":119,"image":120,"author":125,"headline":65,"publisher":127,"fileFormat":130,"inLanguage":73,"description":66,"dateModified":131,"datePublished":132,"encodingFormat":130,"isAccessibleForFree":133,"interactionStatistic":134},"DigitalDocument",{"url":121,"@type":122,"width":123,"height":124},"https://docshare.wps.com/thumbnails/beyond-origin-multimodal-ai-synthesis-to-resolve-cancers-of-unknown-primary/346475.png","ImageObject",300,407,{"name":63,"@type":126},"Person",{"url":109,"name":128,"@type":129},"DocShare","Organization","application/pdf","2026-11-11","2026-09-22",true,{"@type":135,"interactionType":136,"userInteractionCount":52},"InteractionCounter",{"@type":137},"ViewAction",{"@type":139,"mainEntity":140},"FAQPage",[141,147,151],{"name":142,"@type":143,"acceptedAnswer":144},"What is the core problem addressed by the article regarding cancer of unknown primary (CUP)?","Question",{"text":145,"@type":146},"CUP presents metastatic disease while the primary tumor remains elusive despite exhaustive clinical workup, making origin-based diagnosis and treatment ineffective for many patients.","Answer",{"name":148,"@type":143,"acceptedAnswer":149},"Why do origin-based diagnostic frameworks fail for CUP?",{"text":150,"@type":146},"The inability to pinpoint anatomical origin forces clinicians into broad-spectrum empirical chemotherapy, which has limited efficacy and prevents access to targeted therapies and clinical trials.",{"name":152,"@type":143,"acceptedAnswer":153},"How does multimodal AI aim to improve CUP diagnosis and treatment selection?",{"text":154,"@type":146},"The article highlights advances where genomics, pathology images, and imaging features are integrated with AI models to infer tumor identity more effectively and support molecularly guided therapeutic strategies.","https://schema.org",{"og:url":117,"og:type":157,"og:title":65,"og:site_name":128,"og:description":66},"article",{"robots":159,"canonical":117},"index,follow",{"doc_id":61,"site_id":74},1790547888]