A clinical-grade universal foundation model for intraoperative pathology

A clinical-grade universal foundation model for intraoperative pathology | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article A clinical-grade universal foundation model for intraoperative pathology Hao Chen, Zihan Zhao, Fengtao Zhou, Ronggang Li, Bing Chu, Xinke Zhang, and 17 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7805546/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Intraoperative pathology is pivotal to precision surgery, yet its clinical impact is constrained by diagnostic complexity and the limited availability of high-quality frozen-section data. While computational pathology has made significant strides, the lack of large-scale, prospective validation has impeded its routine adoption in surgical workflows. Here, we introduce CRISP, a clinical-grade foundation model developed on over 100,000 frozen sections from eight medical centers, specifically designed to provide Clinical-grade Robust Intraoperative Support for Pathology (CRISP). CRISP was comprehensively evaluated on more than 15,000 intraoperative slides across nearly 100 retrospective diagnostic tasks, including benign-malignant discrimination, key intraoperative decision-making, and pan-cancer detection, etc. The model demonstrated robust generalization across diverse institutions, tumor types, and anatomical sites-including previously unseen sites and rare cancers. In a prospective cohort of over 2,000 patients, CRISP sustained high diagnostic accuracy under real-world conditions, directly informing surgical decisions in 92.6% of cases. Human-AI collaboration further reduced diagnostic workload by 35%, avoided 105 ancillary tests and enhanced detection of micrometastases with 87.5% accuracy. Together, these findings position CRISP as a clinical-grade paradigm for AI-driven intraoperative pathology, bridging computational advances with surgical precision and accelerating the translation of artificial intelligence into routine clinical practice. Biological sciences/Cancer/Cancer models Biological sciences/Computational biology and bioinformatics/Machine learning Full Text Additional Declarations There is NO Competing Interest. Supplementary Files supplementaryinfo.docx Supplementary Materials RSChenCai.pdf Reporting Summary nrsoftwarepolicyChen.pdf Software Policy Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7805546","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":528970616,"identity":"a67e9abd-9baa-4beb-912a-ffcd9e898626","order_by":0,"name":"Hao Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAsUlEQVRIiWNgGAWjYBACxhkMjA9gHGaGA8RpYTaAaSBOC4MEA5sEaVqYZzc/q/jxx4bB4Pz5A8wFZ4hx2JxjZjd729IYDG4kMzDPuEGMlhk5bLcZGw4DtQAdxvOBSC3FDH/+Ax12mAQtzAxsBxgMDgAdxkOcw9KMJXvbknkkbyQbHOYhxvuGM5Iffvjxx06O7/zBh495jhGjpQFC84CIA0RoYGCQJ0rVKBgFo2AUjGwAAITwNJZ5nBIOAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0002-8400-3780","institution":"The Hong Kong University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Hao","middleName":"","lastName":"Chen","suffix":""},{"id":528970617,"identity":"02693303-2fbe-4eb3-b310-a0750450ce82","order_by":1,"name":"Zihan Zhao","email":"","orcid":"","institution":"Sun Yat-sen University Cancer Center","correspondingAuthor":false,"prefix":"","firstName":"Zihan","middleName":"","lastName":"Zhao","suffix":""},{"id":528970618,"identity":"e6b812c7-4599-4f3d-926e-39d3102b9fc5","order_by":2,"name":"Fengtao Zhou","email":"","orcid":"","institution":"The Hong Kong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Fengtao","middleName":"","lastName":"Zhou","suffix":""},{"id":528970619,"identity":"8567aca6-dbe2-4276-8560-8bec976468b6","order_by":3,"name":"Ronggang Li","email":"","orcid":"","institution":"Jiangmen Central Hospital, Jiangmen","correspondingAuthor":false,"prefix":"","firstName":"Ronggang","middleName":"","lastName":"Li","suffix":""},{"id":528970620,"identity":"82f425bc-9268-4819-80f8-e0e04925c47a","order_by":4,"name":"Bing Chu","email":"","orcid":"","institution":"Zhongshan People's Hospital","correspondingAuthor":false,"prefix":"","firstName":"Bing","middleName":"","lastName":"Chu","suffix":""},{"id":528970621,"identity":"b081c7fa-fd02-4022-8486-282f7d9f17da","order_by":5,"name":"Xinke Zhang","email":"","orcid":"https://orcid.org/0000-0002-3527-2140","institution":"Sun Yat-sen University Cancer Center","correspondingAuthor":false,"prefix":"","firstName":"Xinke","middleName":"","lastName":"Zhang","suffix":""},{"id":528970622,"identity":"e7b48bfc-aa33-4e9c-ae8f-5f6f3b761bf4","order_by":6,"name":"Xueyi Zheng","email":"","orcid":"https://orcid.org/0000-0003-1386-7052","institution":"Sun Yat-sen University Cancer Center","correspondingAuthor":false,"prefix":"","firstName":"Xueyi","middleName":"","lastName":"Zheng","suffix":""},{"id":528970623,"identity":"91100190-e9e3-4a1d-9694-4ff7e57b02fa","order_by":7,"name":"Ke Zheng","email":"","orcid":"","institution":"Sun Yat-Sen University Cancer Center","correspondingAuthor":false,"prefix":"","firstName":"Ke","middleName":"","lastName":"Zheng","suffix":""},{"id":528970624,"identity":"0186a697-94c9-49c7-b1ec-98c611855817","order_by":8,"name":"Xiaobo Wen","email":"","orcid":"","institution":"Sun Yat-Sen University Cancer Center","correspondingAuthor":false,"prefix":"","firstName":"Xiaobo","middleName":"","lastName":"Wen","suffix":""},{"id":528970625,"identity":"9d5c639d-0e98-4793-8657-5add7fd263e9","order_by":9,"name":"Jiabo MA","email":"","orcid":"https://orcid.org/0000-0001-8532-4466","institution":"Hong Kong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Jiabo","middleName":"","lastName":"MA","suffix":""},{"id":528970626,"identity":"07e239d1-9d82-4ca8-9716-25b72dba3f74","order_by":10,"name":"Yihui Wang","email":"","orcid":"https://orcid.org/0009-0002-7606-9816","institution":"The Hong Kong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Yihui","middleName":"","lastName":"Wang","suffix":""},{"id":528970627,"identity":"1a2d0469-fc59-49a0-92d2-b2fc9f6dd7c9","order_by":11,"name":"Jie-Wei Chen","email":"","orcid":"","institution":"State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-Sen University Cancer Center, Guangzhou 510060","correspondingAuthor":false,"prefix":"","firstName":"Jie-Wei","middleName":"","lastName":"Chen","suffix":""},{"id":528970628,"identity":"ccbd6193-151d-40eb-8eb6-99e596d8a5f6","order_by":12,"name":"Chengyou Zheng","email":"","orcid":"","institution":"Sun Yat-sen University Cancer Center","correspondingAuthor":false,"prefix":"","firstName":"Chengyou","middleName":"","lastName":"Zheng","suffix":""},{"id":528970629,"identity":"263e471f-b5ac-4e25-890f-1f9d8a47ee45","order_by":13,"name":"Jiangyu Zhang","email":"","orcid":"https://orcid.org/0000-0003-1714-3684","institution":"Affiliated Cancer Hospital \u0026 Institute of Guangzhou Medical University","correspondingAuthor":false,"prefix":"","firstName":"Jiangyu","middleName":"","lastName":"Zhang","suffix":""},{"id":528970630,"identity":"0c9d755a-231b-467d-80f5-55a61b471c82","order_by":14,"name":"Yongqin Wen","email":"","orcid":"","institution":"Dongguan People's Hospital","correspondingAuthor":false,"prefix":"","firstName":"Yongqin","middleName":"","lastName":"Wen","suffix":""},{"id":528970631,"identity":"9531d5ec-d937-480a-b54c-c67994eee81c","order_by":15,"name":"Jiajia Meng","email":"","orcid":"","institution":"Huizhou Central People's Hospital","correspondingAuthor":false,"prefix":"","firstName":"Jiajia","middleName":"","lastName":"Meng","suffix":""},{"id":528970632,"identity":"401b43db-dcfd-4dfd-bceb-1a0a24040d40","order_by":16,"name":"Ziqi Zeng","email":"","orcid":"","institution":"Soutern Medical University","correspondingAuthor":false,"prefix":"","firstName":"Ziqi","middleName":"","lastName":"Zeng","suffix":""},{"id":528970633,"identity":"811aa9b8-c0d7-46b6-96a0-e90222788970","order_by":17,"name":"Xiaoqing Li","email":"","orcid":"","institution":"Southern Medical University","correspondingAuthor":false,"prefix":"","firstName":"Xiaoqing","middleName":"","lastName":"Li","suffix":""},{"id":528970634,"identity":"da147756-44b0-4675-8534-4998ad816b4e","order_by":18,"name":"Jing Li","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Jing","middleName":"","lastName":"Li","suffix":""},{"id":528970635,"identity":"f728f99f-1e6c-4170-86b6-505d72703245","order_by":19,"name":"Dan Xie","email":"","orcid":"https://orcid.org/0000-0003-2242-3138","institution":"State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, China.","correspondingAuthor":false,"prefix":"","firstName":"Dan","middleName":"","lastName":"Xie","suffix":""},{"id":528970636,"identity":"56788c51-3037-4509-ac60-c2e865550d12","order_by":20,"name":"Yaping Ye","email":"","orcid":"https://orcid.org/0000-0001-5376-0124","institution":"Department of Pathology, Nanfang Hospital, Soutern Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yaping","middleName":"","lastName":"Ye","suffix":""},{"id":528970637,"identity":"939b21fd-661d-4b65-b16a-4805d5305c34","order_by":21,"name":"Yu Wang","email":"","orcid":"https://orcid.org/0000-0002-2842-0336","institution":"Southern Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Wang","suffix":""},{"id":528970638,"identity":"bf88b457-6311-474a-b1df-2eb459903cf8","order_by":22,"name":"Mu-Yan Cai","email":"","orcid":"https://orcid.org/0000-0002-4646-4391","institution":"Sun Yat-sen University Cancer Center","correspondingAuthor":false,"prefix":"","firstName":"Mu-Yan","middleName":"","lastName":"Cai","suffix":""}],"badges":[],"createdAt":"2025-10-08 08:16:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7805546/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7805546/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95655081,"identity":"cef5610c-ddc0-4f80-8ccc-b5e258278f1d","added_by":"auto","created_at":"2025-11-11 16:14:17","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":12336460,"visible":true,"origin":"","legend":"Article File #1","description":"","filename":"NMEDA146190Articleupdated.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7805546/v1_covered_bd4f734e-57af-4c3c-8d48-c3ae695bf6fb.pdf"},{"id":93506612,"identity":"7c4a504d-eeeb-4977-bf96-580df48337bf","added_by":"auto","created_at":"2025-10-14 14:51:35","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":12263972,"visible":true,"origin":"","legend":"Supplementary Materials","description":"","filename":"supplementaryinfo.docx","url":"https://assets-eu.researchsquare.com/files/rs-7805546/v1/f14e3ca1bdf5fbd39bfccc44.docx"},{"id":93506613,"identity":"cb7a50f9-7611-4006-9691-ed7242caa2c9","added_by":"auto","created_at":"2025-10-14 14:51:35","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":2396851,"visible":true,"origin":"","legend":"Reporting Summary","description":"","filename":"RSChenCai.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7805546/v1/834250c94fa7afb5a470a420.pdf"},{"id":93506611,"identity":"5d02414f-1f47-4b78-9106-7acd54dee423","added_by":"auto","created_at":"2025-10-14 14:51:35","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":1317055,"visible":true,"origin":"","legend":"Software Policy","description":"","filename":"nrsoftwarepolicyChen.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7805546/v1/bac04d192bdba155a6111d8e.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"A clinical-grade universal foundation model for intraoperative pathology","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7805546/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7805546/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Intraoperative pathology is pivotal to precision surgery, yet its clinical impact is constrained by diagnostic complexity and the limited availability of high-quality frozen-section data. While computational pathology has made significant strides, the lack of large-scale, prospective validation has impeded its routine adoption in surgical workflows. Here, we introduce CRISP, a clinical-grade foundation model developed on over 100,000 frozen sections from eight medical centers, specifically designed to provide Clinical-grade Robust Intraoperative Support for Pathology (CRISP). CRISP was comprehensively evaluated on more than 15,000 intraoperative slides across nearly 100 retrospective diagnostic tasks, including benign-malignant discrimination, key intraoperative decision-making, and pan-cancer detection, etc. The model demonstrated robust generalization across diverse institutions, tumor types, and anatomical sites-including previously unseen sites and rare cancers. In a prospective cohort of over 2,000 patients, CRISP sustained high diagnostic accuracy under real-world conditions, directly informing surgical decisions in 92.6% of cases. Human-AI collaboration further reduced diagnostic workload by 35%, avoided 105 ancillary tests and enhanced detection of micrometastases with 87.5% accuracy. Together, these findings position CRISP as a clinical-grade paradigm for AI-driven intraoperative pathology, bridging computational advances with surgical precision and accelerating the translation of artificial intelligence into routine clinical practice.","manuscriptTitle":"A clinical-grade universal foundation model for intraoperative pathology","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-14 14:51:30","doi":"10.21203/rs.3.rs-7805546/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"0990d2af-72ef-4eec-92f5-2e9c408f0b90","owner":[],"postedDate":"October 14th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":56222531,"name":"Biological sciences/Cancer/Cancer models"},{"id":56222532,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"}],"tags":[],"updatedAt":"2025-11-10T15:11:37+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-14 14:51:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7805546","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7805546","identity":"rs-7805546","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}