Prognosis Prediction in Bladder Cancer Pathological Images Based on Nuclear Structure Encoding

Prognosis Prediction in Bladder Cancer Pathological Images Based on Nuclear Structure Encoding | 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 Research Article Prognosis Prediction in Bladder Cancer Pathological Images Based on Nuclear Structure Encoding Bo Guan, Yuan Gao, Feng Wang, Guangdi Chu, Jianchang Zhao, Haitao Niu, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8159636/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 6 You are reading this latest preprint version Abstract Background: Bladder cancer is identified as a common malignancy in the male urinary system. Muscle-invasive bladder cancer (MIBC) is known for rapid disease progression and poor prognosis. Traditional pathological evaluation using tissue slides is challenged by subjectivity and inter-observer variability, whereby precise prognostic tools are required for personalized treatment plans. Methods: A deep learning framework integrating graph neural networks and knowledge distillation is designed to predict bladder cancer prognosis using hematoxylin and eosin (H\&E) stained whole slide images (WSI). An MIBC cohort from TCGA (N=387) is utilized to create datasets for nuclear classification and prognosis assessment. A multi-scale feature fusion and knowledge distillation module is designed, where the pre-trained Segment Anything Model (SAM) is employed for nuclear feature extraction. These features are transmitted to Vision Transformer (ViT) through knowledge distillation. A graph neural network framework based on an attention mechanism is constructed, where nuclear morphological features are mapped to graph nodes and spatial relationships between nuclei are explored. Results: The effectiveness of using WSI images to support MIBC treatment decision-making is significantly improved by the proposed method, as demonstrated by experimental results. Conclusions: Accurate MIBC prognosis classification is achieved by the proposed method through effectively capturing nuclear morphological characteristics and their spatial distribution patterns, demonstrating its capability in precise prognostic stratification. Bladder cancer Muscle-invasive bladder cancer Deep learning Graph neural networks Knowledge distillation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 07 Feb, 2026 Reviewers agreed at journal 30 Jan, 2026 Reviewers invited by journal 25 Dec, 2025 Editor assigned by journal 25 Dec, 2025 Submission checks completed at journal 24 Nov, 2025 First submitted to journal 19 Nov, 2025 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-8159636","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":565514668,"identity":"d78aa40a-6746-4a8d-a353-d7bdeecb77af","order_by":0,"name":"Bo Guan","email":"","orcid":"","institution":"Tianjin University","correspondingAuthor":false,"prefix":"","firstName":"Bo","middleName":"","lastName":"Guan","suffix":""},{"id":565514669,"identity":"9ce28712-3eae-4fb6-bc4f-494971e96868","order_by":1,"name":"Yuan Gao","email":"","orcid":"","institution":"Tianjin University","correspondingAuthor":false,"prefix":"","firstName":"Yuan","middleName":"","lastName":"Gao","suffix":""},{"id":565514670,"identity":"dffcc43c-4671-41e4-819b-48cc17c3d254","order_by":2,"name":"Feng Wang","email":"","orcid":"","institution":"Tianjin University","correspondingAuthor":false,"prefix":"","firstName":"Feng","middleName":"","lastName":"Wang","suffix":""},{"id":565514671,"identity":"91251a31-9a66-4003-a893-185b72b162cc","order_by":3,"name":"Guangdi Chu","email":"","orcid":"","institution":"Affiliated Hospital of Qingdao University","correspondingAuthor":false,"prefix":"","firstName":"Guangdi","middleName":"","lastName":"Chu","suffix":""},{"id":565514672,"identity":"c1159025-cf7a-4047-9aeb-ba3ae397a6c5","order_by":4,"name":"Jianchang Zhao","email":"","orcid":"","institution":"Tianjin University","correspondingAuthor":false,"prefix":"","firstName":"Jianchang","middleName":"","lastName":"Zhao","suffix":""},{"id":565514673,"identity":"7d52a52c-ed25-4103-a6c9-59d449965c66","order_by":5,"name":"Haitao Niu","email":"","orcid":"","institution":"Affiliated Hospital of Qingdao University","correspondingAuthor":false,"prefix":"","firstName":"Haitao","middleName":"","lastName":"Niu","suffix":""},{"id":565514674,"identity":"978013df-1fbb-489c-a875-8338cb3f66e0","order_by":6,"name":"Jianmin Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAqUlEQVRIiWNgGAWjYFCCww0HPjCwgVgGxGo52HBwRgJpWhgbmHkSGEjQott4sPGw7Q++xAb25m0SDDV3CGsxO3Cw4XBOAltiA8+xMgmGY89I0SKRYybB2HCYSC0WIC3yb0jRwgC2hYcELQd70tiM23jSii0SjhGj5cbhwx9+2ByT7Wc/vPHGhxoitDBIHACRxyDxn0CEBgYG/gYQWUOU2lEwCkbBKBihAABGqT/0Bp4g5gAAAABJRU5ErkJggg==","orcid":"","institution":"Tianjin University","correspondingAuthor":true,"prefix":"","firstName":"Jianmin","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-11-20 02:53:05","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8159636/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8159636/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":99131001,"identity":"fcd9d92f-8c57-44ff-9302-b3e6750e6817","added_by":"auto","created_at":"2025-12-29 04:29:34","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8088,"visible":true,"origin":"","legend":"","description":"","filename":"dc03e0fa367a4888894981864784d377.json","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1/9e5879b151ee6c846023a71a.json"},{"id":99315205,"identity":"09404d23-882e-48f3-b45c-537c2dc4af18","added_by":"auto","created_at":"2025-12-31 16:26:36","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":88833,"visible":true,"origin":"","legend":"","description":"","filename":"dc03e0fa367a4888894981864784d3771enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1/9998d1d174043a19e110aa79.xml"},{"id":99131004,"identity":"64896b73-7152-4f1c-ac2c-7e48b01dde5e","added_by":"auto","created_at":"2025-12-29 04:29:34","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":141306,"visible":true,"origin":"","legend":"","description":"","filename":"Coveringletter.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1/d937ac90866354b84bdd143f.pdf"},{"id":99131018,"identity":"1776a917-4db9-4fd9-9dc3-065ebd37b250","added_by":"auto","created_at":"2025-12-29 04:29:35","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1176190,"visible":true,"origin":"","legend":"","description":"","filename":"Figure1.png","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1/ba8d421f8a0933a0075f9dfd.png"},{"id":99131003,"identity":"c3aab584-6766-48ae-9769-899bb72841bd","added_by":"auto","created_at":"2025-12-29 04:29:34","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":441228,"visible":true,"origin":"","legend":"","description":"","filename":"Figure2.png","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1/85942df07c1034b444afd8ed.png"},{"id":99314986,"identity":"e8c6a36d-1414-46df-8417-c79dd6d2062f","added_by":"auto","created_at":"2025-12-31 16:25:23","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":76604,"visible":true,"origin":"","legend":"","description":"","filename":"Figure3.png","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1/2a970834b31d0c34e8c6c186.png"},{"id":99131011,"identity":"63bd679f-2fd3-4360-bafe-6e7a70c2b7ff","added_by":"auto","created_at":"2025-12-29 04:29:34","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20027606,"visible":true,"origin":"","legend":"","description":"","filename":"Figure4.png","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1/bb090058b99954eb13383235.png"},{"id":99316409,"identity":"51908448-59cd-4f45-b34a-9aeddceb5085","added_by":"auto","created_at":"2025-12-31 16:28:26","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":790495,"visible":true,"origin":"","legend":"","description":"","filename":"Figure5.png","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1/ff14b02dfc596922d97b4eaf.png"},{"id":99315494,"identity":"ab3a191d-1006-450b-81e3-7672d31d5a50","added_by":"auto","created_at":"2025-12-31 16:26:59","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8927323,"visible":true,"origin":"","legend":"","description":"","filename":"Figure6.png","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1/dda4a5e2d248342517f243ec.png"},{"id":99315541,"identity":"8f76dd04-673b-4e6d-bc21-9803462c4d8a","added_by":"auto","created_at":"2025-12-31 16:27:03","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7914911,"visible":true,"origin":"","legend":"","description":"","filename":"Figure7.png","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1/373c0177fe30b6dedf66c052.png"},{"id":99131017,"identity":"8ff18962-e48d-4a01-9b00-980f2e140b3b","added_by":"auto","created_at":"2025-12-29 04:29:35","extension":"pdf","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39497789,"visible":true,"origin":"","legend":"","description":"","filename":"PrognosisPredictioninBladderCancerPathologicalImagesBasedonNuclearStructureEncoding.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1/2d76b1da8d3151bc0cc49b8e.pdf"},{"id":99314769,"identity":"e16be5b1-01c1-4434-8a9f-39fec606bfeb","added_by":"auto","created_at":"2025-12-31 16:23:04","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2634057,"visible":true,"origin":"","legend":"","description":"","filename":"TypeResults.png","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1/f0a2ab7d7d493b8c41b7a503.png"},{"id":99131006,"identity":"0fa4eac3-f7f7-4a1b-b0ea-6281f6fd7463","added_by":"auto","created_at":"2025-12-29 04:29:34","extension":"pdf","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":390370,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1/10fe69605e300238c0b309a9.pdf"},{"id":99131007,"identity":"c186c8f5-1231-4e94-95c5-a43ac6b302cc","added_by":"auto","created_at":"2025-12-29 04:29:34","extension":"cls","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55331,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1/818f1692ca3fe2374f69bcce.cls"},{"id":99314997,"identity":"bea82d3a-dd48-4f47-b625-0aa8f9029873","added_by":"auto","created_at":"2025-12-31 16:25:30","extension":"bst","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64141,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1/bc1f4aeaab9dd726653bb5d2.bst"},{"id":99131014,"identity":"c33fdd1a-7f2b-45c9-84ed-134380e5fc4d","added_by":"auto","created_at":"2025-12-29 04:29:34","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2287500,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineTypeResults.png","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1/1a7cfc172f1f25398b8bf51a.png"},{"id":99131015,"identity":"f1ed842d-dcc2-464c-b512-0bfb397374e3","added_by":"auto","created_at":"2025-12-29 04:29:34","extension":"xml","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":94289,"visible":true,"origin":"","legend":"","description":"","filename":"dc03e0fa367a4888894981864784d3771structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1/9302e3b36ec2a1fc420afe20.xml"},{"id":99131013,"identity":"15ebaca7-86a8-45a9-8359-a7cb6db105c8","added_by":"auto","created_at":"2025-12-29 04:29:34","extension":"html","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":103005,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1/4abb35aae1899adb9b5833d8.html"},{"id":99787812,"identity":"3ea142c4-0846-43e8-9023-d0980be62253","added_by":"auto","created_at":"2026-01-08 12:36:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3394081,"visible":true,"origin":"","legend":"","description":"","filename":"PrognosisPredictioninBladderCancerPathologicalImagesBasedonNuclearStructureEncoding.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8159636/v1_covered_a04f2ea0-2035-4de1-a12f-b35ec615044e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Prognosis Prediction in Bladder Cancer Pathological Images Based on Nuclear Structure Encoding","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"cluster-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Cluster Computing](https://www.springer.com/journal/10586)","snPcode":"10586","submissionUrl":"https://submission.nature.com/new-submission/10586/3","title":"Cluster Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Bladder cancer, Muscle-invasive bladder cancer, Deep learning, Graph neural networks, Knowledge distillation","lastPublishedDoi":"10.21203/rs.3.rs-8159636/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8159636/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground: \u003c/h2\u003e\u003cp\u003eBladder cancer is identified as a common malignancy in the male urinary system. Muscle-invasive bladder cancer (MIBC) is known for rapid disease progression and poor prognosis. Traditional pathological evaluation using tissue slides is challenged by subjectivity and inter-observer variability, whereby precise prognostic tools are required for personalized treatment plans.\u003c/p\u003e\u003ch2\u003eMethods: \u003c/h2\u003e\u003cp\u003eA deep learning framework integrating graph neural networks and knowledge distillation is designed to predict bladder cancer prognosis using hematoxylin and eosin (H\\\u0026amp;E) stained whole slide images (WSI). An MIBC cohort from TCGA (N=387) is utilized to create datasets for nuclear classification and prognosis assessment. A multi-scale feature fusion and knowledge distillation module is designed, where the pre-trained Segment Anything Model (SAM) is employed for nuclear feature extraction. These features are transmitted to Vision Transformer (ViT) through knowledge distillation. A graph neural network framework based on an attention mechanism is constructed, where nuclear morphological features are mapped to graph nodes and spatial relationships between nuclei are explored.\u003c/p\u003e\u003ch2\u003eResults: \u003c/h2\u003e\u003cp\u003eThe effectiveness of using WSI images to support MIBC treatment decision-making is significantly improved by the proposed method, as demonstrated by experimental results.\u003c/p\u003e\u003ch2\u003eConclusions: \u003c/h2\u003e\u003cp\u003eAccurate MIBC prognosis classification is achieved by the proposed method through effectively capturing nuclear morphological characteristics and their spatial distribution patterns, demonstrating its capability in precise prognostic stratification.\u003c/p\u003e","manuscriptTitle":"Prognosis Prediction in Bladder Cancer Pathological Images Based on Nuclear Structure Encoding","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-29 04:29:29","doi":"10.21203/rs.3.rs-8159636/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-02-07T18:47:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"14066361793111896362542589366958670355","date":"2026-01-30T18:01:58+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-25T14:39:14+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-25T14:38:29+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-11-24T14:47:55+00:00","index":"","fulltext":""},{"type":"submitted","content":"Cluster Computing","date":"2025-11-20T02:37:06+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"cluster-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Cluster Computing](https://www.springer.com/journal/10586)","snPcode":"10586","submissionUrl":"https://submission.nature.com/new-submission/10586/3","title":"Cluster Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"33da18df-5d49-4dab-adc5-b7566abd88b3","owner":[],"postedDate":"December 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-12-29T04:29:29+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-29 04:29:29","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8159636","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8159636","identity":"rs-8159636","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}