Subspecialty-Specific Foundation Model for Intelligent Gastrointestinal 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 Subspecialty-Specific Foundation Model for Intelligent Gastrointestinal Pathology Yonghong He, Lianghui Zhu, Xitong Ling, Minxi Ouyang, Xiao-Ping Liu, and 21 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6836189/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Gastrointestinal (GI) diseases represent a clinically significant burden, necessitating precise diagnostic approaches to optimize patient outcomes. Conventional histopathological diagnosis suffers from limited reproducibility and diagnostic variability. To overcome these limitations, we develop Digepath, a specialized foundation model for GI pathology. Our framework introduces a dual-phase iterative optimization strategy combining pretraining with fine-screening, specifically designed to address the detection of sparsely distributed lesion areas in whole-slide images. Digepath is pretrained on over 353 million multi-scale images from 210,043 H&E-stained slides of GI diseases. It attains state-of-the-art performance on 33 out of 34 tasks related to GI pathology, including pathological diagnosis, protein expression status prediction, gene mutation prediction, and prognosis evaluation. We further translate the intelligent screening module for early GI cancer and achieve near-perfect 99.70% sensitivity across nine independent medical institutions. This work not only advances AI-driven precision pathology for GI diseases but also bridge critical gaps in histopathological practice. Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Computational biology and bioinformatics/Image processing Gastrointestinal diseases Foundation model Computational pathology Early cancer screening Self-supervised learning Full Text Additional Declarations There is NO Competing Interest. Supplementary Files supplementary.docx Supplementary Material ex1.pdf Extended Data Figure 1 ex2.pdf Extended Data Figure 2 ex3.pdf Extended Data Figure 3 ex4.pdf Extended Data Figure 4 ex5.pdf Extended Data Figure 5 ex6.pdf Extended Data Figure 6 ex7.pdf Extended Data Figure 7 ex8.pdf Extended Data Figure 8 ex9.pdf Extended Data Figure 9 Cite Share Download PDF Status: Under Review 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-6836189","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":470263499,"identity":"c01d4c1b-16a2-48e6-b253-062b2fa2bd81","order_by":0,"name":"Yonghong He","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABB0lEQVRIiWNgGAWjYBACAwYGNoYPYCZjAwhBBQloYZwBZPCQpIWZB6wFYhFhLebsPWaPbf7UMdjzH257+HXHYXkG9uZtEgw1d3Bqsew5Y26c28bGwCOR2G4se+awYQPPsTIJhmPPcDvsRo6ZdG4DD1ALY5u0ZNthxgaJHDMJxobDuLXcf2MmbfFHgoGH/yBYi32D/BsCWm7wmEkzsBkAvZ/YJvmx7XBigwQPAS1n0soke9sSeHhuJLZJM7alJ7fxpBVbJBzDo+X44W0SP/7UybH3H38m+bPN2raf/fDGGx9qcGthYOAAxwI4WsARxAZiJeDRwMDA/gDOZPyBV+UoGAWjYBSMVAAA0FhOZJ0muCIAAAAASUVORK5CYII=","orcid":"","institution":"Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School","correspondingAuthor":true,"prefix":"","firstName":"Yonghong","middleName":"","lastName":"He","suffix":""},{"id":470263500,"identity":"1c86e77a-a8a0-4bee-bd38-244f3a3fa718","order_by":1,"name":"Lianghui Zhu","email":"","orcid":"https://orcid.org/0009-0005-3067-0210","institution":"Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School","correspondingAuthor":false,"prefix":"","firstName":"Lianghui","middleName":"","lastName":"Zhu","suffix":""},{"id":470263501,"identity":"11979532-bf2f-4f29-8276-6768aae42b83","order_by":2,"name":"Xitong Ling","email":"","orcid":"","institution":"Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School","correspondingAuthor":false,"prefix":"","firstName":"Xitong","middleName":"","lastName":"Ling","suffix":""},{"id":470263502,"identity":"a3323ef7-7503-4fc6-acca-7cae1529fed7","order_by":3,"name":"Minxi Ouyang","email":"","orcid":"","institution":"Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School","correspondingAuthor":false,"prefix":"","firstName":"Minxi","middleName":"","lastName":"Ouyang","suffix":""},{"id":470263503,"identity":"23a10e3d-41c8-489b-9b91-215c41179498","order_by":4,"name":"Xiao-Ping Liu","email":"","orcid":"https://orcid.org/0000-0001-6179-0964","institution":"Zhongnan Hospital of Wuhan University","correspondingAuthor":false,"prefix":"","firstName":"Xiao-Ping","middleName":"","lastName":"Liu","suffix":""},{"id":470263504,"identity":"cc5c9af3-f676-4e77-a2b4-e4234569e9d5","order_by":5,"name":"Mingxi Fu","email":"","orcid":"","institution":"Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School","correspondingAuthor":false,"prefix":"","firstName":"Mingxi","middleName":"","lastName":"Fu","suffix":""},{"id":470263505,"identity":"d151e03f-7117-4426-9b9a-b7d05d56c7a7","order_by":6,"name":"Tian Guan","email":"","orcid":"","institution":"Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School","correspondingAuthor":false,"prefix":"","firstName":"Tian","middleName":"","lastName":"Guan","suffix":""},{"id":470263506,"identity":"04cb5e04-d0af-458c-b848-79d791d46860","order_by":7,"name":"Fanglei Fu","email":"","orcid":"","institution":"Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School","correspondingAuthor":false,"prefix":"","firstName":"Fanglei","middleName":"","lastName":"Fu","suffix":""},{"id":470263507,"identity":"4b0d8019-37a5-49d0-aa91-9b6381fafbd3","order_by":8,"name":"Maomao Zeng","email":"","orcid":"","institution":"Shenzhen Zhengjingda Instrument Co., Ltd., Shenzhen, Guangdong","correspondingAuthor":false,"prefix":"","firstName":"Maomao","middleName":"","lastName":"Zeng","suffix":""},{"id":470263508,"identity":"92ce2d13-a9d8-48f9-bbd6-b862c61165b6","order_by":9,"name":"Mingxi Zhu","email":"","orcid":"","institution":"Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School","correspondingAuthor":false,"prefix":"","firstName":"Mingxi","middleName":"","lastName":"Zhu","suffix":""},{"id":470263509,"identity":"9190def1-271f-4589-8102-cf839b2c6a55","order_by":10,"name":"Yibo Jin","email":"","orcid":"","institution":"School of Foreign Studies, Guangzhou University, Guangzhou, Guangdong 510006, China","correspondingAuthor":false,"prefix":"","firstName":"Yibo","middleName":"","lastName":"Jin","suffix":""},{"id":470263510,"identity":"e66ff107-9ff2-4001-a93f-28c309d0172a","order_by":11,"name":"Liming Liu","email":"","orcid":"","institution":"Department of Pathology, The Second Affiliated Hospital of Southern University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Liming","middleName":"","lastName":"Liu","suffix":""},{"id":470263511,"identity":"4c60c409-fe35-411c-a61e-c17cb78810c3","order_by":12,"name":"Xuanyu Wang","email":"","orcid":"","institution":"Department of Pathology, Zhongnan Hospital of Wuhan University, Wuhan, Hubei Province","correspondingAuthor":false,"prefix":"","firstName":"Xuanyu","middleName":"","lastName":"Wang","suffix":""},{"id":470263512,"identity":"2459b358-3abf-41ea-be28-3972055da647","order_by":13,"name":"Song Duan","email":"","orcid":"","institution":"Department of Pathology, Chongqing University Affiliated Three Gorges Hospital","correspondingAuthor":false,"prefix":"","firstName":"Song","middleName":"","lastName":"Duan","suffix":""},{"id":470263513,"identity":"9d0744d4-7ab9-4394-b074-909fa6496345","order_by":14,"name":"Qiming He","email":"","orcid":"","institution":"Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School","correspondingAuthor":false,"prefix":"","firstName":"Qiming","middleName":"","lastName":"He","suffix":""},{"id":470263514,"identity":"b449330e-1def-4908-a662-96015bf693a8","order_by":15,"name":"Luxi Xie","email":"","orcid":"","institution":"Department of Pathology, Liuzhou People's Hospital Affiliated to Guangxi Medical University,","correspondingAuthor":false,"prefix":"","firstName":"Luxi","middleName":"","lastName":"Xie","suffix":""},{"id":470263515,"identity":"0ec090d3-d390-4b7e-bf92-0213fec65798","order_by":16,"name":"Houqiang Li","email":"","orcid":"","institution":"Department of Pathology, Fuzhou University Affiliated Provincial Hospital","correspondingAuthor":false,"prefix":"","firstName":"Houqiang","middleName":"","lastName":"Li","suffix":""},{"id":470263516,"identity":"76b4731b-a356-498a-adce-b12dc7ed2bf6","order_by":17,"name":"Sufang Tian","email":"","orcid":"","institution":"Department of Pathology, Zhongnan Hospital of Wuhan University","correspondingAuthor":false,"prefix":"","firstName":"Sufang","middleName":"","lastName":"Tian","suffix":""},{"id":470263517,"identity":"649a437e-df63-4c75-b422-ef08997cb041","order_by":18,"name":"Qiang Huang","email":"","orcid":"","institution":"Shenzhen Shengqiang Technology Co., Ltd., Shenzhen, Guangdong","correspondingAuthor":false,"prefix":"","firstName":"Qiang","middleName":"","lastName":"Huang","suffix":""},{"id":470263518,"identity":"d93e3bec-0081-4968-8a64-510241a720f8","order_by":19,"name":"Ying Xiao","email":"","orcid":"","institution":"Beijing Tsinghua Changgung Hospital","correspondingAuthor":false,"prefix":"","firstName":"Ying","middleName":"","lastName":"Xiao","suffix":""},{"id":470263519,"identity":"8aeefe4f-0db0-46b8-8626-4564a7352f66","order_by":20,"name":"Junru Cheng","email":"","orcid":"","institution":"Medical Optical Technology R\u0026D Center, Research Institute of Tsinghua, Pearl River Delta, Guangzhou","correspondingAuthor":false,"prefix":"","firstName":"Junru","middleName":"","lastName":"Cheng","suffix":""},{"id":470263520,"identity":"7330fbcb-3a2f-47f9-8ffa-943fc09e04d2","order_by":21,"name":"Zhiqiang Cheng","email":"","orcid":"","institution":"Department of Pathology, The Second Clinical Medical College, Shenzhen People’s Hospital, Jinan University, Shenzhen, Guangdong","correspondingAuthor":false,"prefix":"","firstName":"Zhiqiang","middleName":"","lastName":"Cheng","suffix":""},{"id":470263521,"identity":"40d12629-48a2-421e-84cd-3daf3e7614b9","order_by":22,"name":"Jianming Li","email":"","orcid":"","institution":"Nanchang University","correspondingAuthor":false,"prefix":"","firstName":"Jianming","middleName":"","lastName":"Li","suffix":""},{"id":470263522,"identity":"742dc279-2550-4a8d-b987-178f21891a5d","order_by":23,"name":"Shanming Lu","email":"","orcid":"","institution":"Longgang Central Hospital of Shenzhen","correspondingAuthor":false,"prefix":"","firstName":"Shanming","middleName":"","lastName":"Lu","suffix":""},{"id":470263523,"identity":"d84d7466-e15e-4d83-bf9b-2b7fd80e42d4","order_by":24,"name":"Shan Xu","email":"","orcid":"","institution":"Provincial Key Laboratory for Precision Pathology and Intelligent Diagnosis, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University","correspondingAuthor":false,"prefix":"","firstName":"Shan","middleName":"","lastName":"Xu","suffix":""},{"id":470263524,"identity":"7a2fc9df-8301-413b-bfd3-86f22324c65c","order_by":25,"name":"Yizhi Wang","email":"","orcid":"","institution":"Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School","correspondingAuthor":false,"prefix":"","firstName":"Yizhi","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-06-06 10:35:52","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6836189/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6836189/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":85168392,"identity":"b324b0e5-d4b8-474c-a5e4-460c555822b1","added_by":"auto","created_at":"2025-06-23 04:46:14","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3384698,"visible":true,"origin":"","legend":"","description":"","filename":"article.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6836189/v1_covered_ffca94b0-e2ae-45b1-94c2-6a4a03c72462.pdf"},{"id":85166841,"identity":"e0d7c10d-374c-43dc-a0e7-c7e3c87794ec","added_by":"auto","created_at":"2025-06-23 04:22:05","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":107500,"visible":true,"origin":"","legend":"Supplementary Material","description":"","filename":"supplementary.docx","url":"https://assets-eu.researchsquare.com/files/rs-6836189/v1/a39920682dfe823179fd1d26.docx"},{"id":85167481,"identity":"cae9e137-b322-4d5e-b1a6-6b383602fb0e","added_by":"auto","created_at":"2025-06-23 04:30:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2892542,"visible":true,"origin":"","legend":"Extended Data Figure 1","description":"","filename":"ex1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6836189/v1/0a381e86b1229f05c2dcbadf.pdf"},{"id":85167832,"identity":"ac4aedd0-59fe-44ed-bf44-f4dc80bea106","added_by":"auto","created_at":"2025-06-23 04:38:05","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":1824635,"visible":true,"origin":"","legend":"Extended Data Figure 2","description":"","filename":"ex2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6836189/v1/0d70208e743b151f65363d27.pdf"},{"id":85167833,"identity":"e59aed5a-6b11-453b-8b1c-b57738dffc7e","added_by":"auto","created_at":"2025-06-23 04:38:05","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":6718034,"visible":true,"origin":"","legend":"Extended Data Figure 3","description":"","filename":"ex3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6836189/v1/2c55977075b99b5ca877d26d.pdf"},{"id":85166849,"identity":"3e31cb48-7e03-4419-99c4-4e98500abd13","added_by":"auto","created_at":"2025-06-23 04:22:05","extension":"pdf","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":4974457,"visible":true,"origin":"","legend":"Extended Data Figure 4","description":"","filename":"ex4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6836189/v1/8004697f1308607cbadb28f8.pdf"},{"id":85166842,"identity":"61b8133b-397d-42d9-ab33-c09f40968783","added_by":"auto","created_at":"2025-06-23 04:22:05","extension":"pdf","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":807456,"visible":true,"origin":"","legend":"Extended Data Figure 5","description":"","filename":"ex5.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6836189/v1/708c3efee4a71d44f9c49099.pdf"},{"id":85167479,"identity":"b34e67be-0702-4c1b-b504-770a45fb25f0","added_by":"auto","created_at":"2025-06-23 04:30:05","extension":"pdf","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":1881947,"visible":true,"origin":"","legend":"Extended Data Figure 6","description":"","filename":"ex6.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6836189/v1/75339d43bc10294a34cc6a87.pdf"},{"id":85166843,"identity":"503561b3-94e6-4ab3-bd45-a0efe0a782f5","added_by":"auto","created_at":"2025-06-23 04:22:05","extension":"pdf","order_by":7,"title":"","display":"","copyAsset":false,"role":"supplement","size":1600281,"visible":true,"origin":"","legend":"Extended Data Figure 7","description":"","filename":"ex7.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6836189/v1/5f1bcb435a2fb9f31b53e1aa.pdf"},{"id":85166846,"identity":"f94d5533-0893-41da-b6c5-474f86209bee","added_by":"auto","created_at":"2025-06-23 04:22:05","extension":"pdf","order_by":8,"title":"","display":"","copyAsset":false,"role":"supplement","size":1243245,"visible":true,"origin":"","legend":"Extended Data Figure 8","description":"","filename":"ex8.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6836189/v1/27169792aa7dec147d7c3a71.pdf"},{"id":85166850,"identity":"cbfef319-cd1c-472a-94f9-213ab24738f9","added_by":"auto","created_at":"2025-06-23 04:22:05","extension":"pdf","order_by":9,"title":"","display":"","copyAsset":false,"role":"supplement","size":1014836,"visible":true,"origin":"","legend":"Extended Data Figure 9","description":"","filename":"ex9.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6836189/v1/de58dba3935c9769cd92d77a.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Subspecialty-Specific Foundation Model for Intelligent Gastrointestinal Pathology","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Gastrointestinal diseases, Foundation model, Computational pathology, Early cancer screening, Self-supervised learning","lastPublishedDoi":"10.21203/rs.3.rs-6836189/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6836189/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Gastrointestinal (GI) diseases represent a clinically significant burden, necessitating precise diagnostic approaches to optimize patient outcomes. Conventional histopathological diagnosis suffers from limited reproducibility and diagnostic variability. To overcome these limitations, we develop Digepath, a specialized foundation model for GI pathology. Our framework introduces a dual-phase iterative optimization strategy combining pretraining with fine-screening, specifically designed to address the detection of sparsely distributed lesion areas in whole-slide images. Digepath is pretrained on over 353 million multi-scale images from 210,043 H\u0026E-stained slides of GI diseases. It attains state-of-the-art performance on 33 out of 34 tasks related to GI pathology, including pathological diagnosis, protein expression status prediction, gene mutation prediction, and prognosis evaluation. We further translate the intelligent screening module for early GI cancer and achieve near-perfect 99.70% sensitivity across nine independent medical institutions. This work not only advances AI-driven precision pathology for GI diseases but also bridge critical gaps in histopathological practice.","manuscriptTitle":"Subspecialty-Specific Foundation Model for Intelligent Gastrointestinal Pathology","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-23 04:22:00","doi":"10.21203/rs.3.rs-6836189/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"
[email protected]","identity":"nature-cancer","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"natcancer","sideBox":"Learn more about [Nature Cancer](http://www.nature.com/natcancer/)","snPcode":"","submissionUrl":"","title":"Nature Cancer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Research","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"958acf32-dd68-4760-849c-40a59c9fba0c","owner":[],"postedDate":"June 23rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":49935381,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":49935382,"name":"Biological sciences/Computational biology and bioinformatics/Image processing"}],"tags":[],"updatedAt":"2025-06-23T04:22:01+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-23 04:22:00","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6836189","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6836189","identity":"rs-6836189","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.