MRAN: A Reconstructive Attention Network for Handling Modality Sparsity in Multimodal Cancer Survival Analysis

MRAN: A Reconstructive Attention Network for Handling Modality Sparsity in Multimodal Cancer Survival Analysis | 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 MRAN: A Reconstructive Attention Network for Handling Modality Sparsity in Multimodal Cancer Survival Analysis Djaafer GHERBI, Mohammed Lamine BENOMAR, Mohammed Said KADDOUR This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8887611/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 Survival prediction in clear cell renal cell carcinoma (ccRCC) is challenging due to severe class imbalance and pervasive radiological data sparsity in real-world cohorts. Standard multimodal fusion techniques often degrade when modalities are missing, typically overfitting to the majority survival class (∼88%) and failing to reliably flag high-risk patients. We introduce the Multimodal Reconstructive Attention Network (MRAN), which integrates whole-slide images (WSI), CT, and clinical/genomic variables via attention-based fusion coupled with an auxiliary feature-level reconstruction branch. This branch learns to generate CT embeddings from histopathology, enabling the model to exploit radiological signals even for patients without acquired scans. Ablation studies confirm that a tri-modal configuration (WSI + CT + clinical), which explicitly excludes sparse MRI data, provides the optimal signal-to-noise ratio. Evaluated on the MMISTccRCC dataset with 5-fold cross-validation and an independent holdout test set, MRAN achieves a C-index of 0.835 and a Balanced Accuracy of 83.5%. At a clinically calibrated operating point, the model attains a Sensitivity of 81.3% (identifying mortality) and a Specificity of 85.7% (identifying survivors), thereby overcoming the accuracy paradox and demonstrating robust utility for 12-month risk stratification in ccRCC. Bioinformatics Biomedical Engineering Multimodal Learning Survival Analysis Missing Data Imputation Deep Learning Medical Image Diagnosis Kidney Cancer Full Text Additional Declarations The authors declare no competing interests. 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-8887611","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":591704713,"identity":"e8734c2d-9133-4f2c-b4bd-901d17b43513","order_by":0,"name":"Djaafer GHERBI","email":"data:image/png;base64,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","orcid":"","institution":"University of Ain Temouchent","correspondingAuthor":true,"prefix":"","firstName":"Djaafer","middleName":"","lastName":"GHERBI","suffix":""},{"id":591704714,"identity":"00c3029b-275c-4447-b210-2896c2712c67","order_by":1,"name":"Mohammed Lamine BENOMAR","email":"","orcid":"","institution":"University of Ain Temouchent","correspondingAuthor":false,"prefix":"","firstName":"Mohammed","middleName":"Lamine","lastName":"BENOMAR","suffix":""},{"id":591704715,"identity":"8ed908fc-bb80-4995-a796-1c4fefe0a9e1","order_by":2,"name":"Mohammed Said KADDOUR","email":"","orcid":"","institution":"University of Ain Temouchent","correspondingAuthor":false,"prefix":"","firstName":"Mohammed","middleName":"Said","lastName":"KADDOUR","suffix":""}],"badges":[],"createdAt":"2026-02-15 17:28:07","currentVersionCode":1,"declarations":{"humanSubjects":true,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":true,"humanSubjectConsent":true,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8887611/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8887611/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102963602,"identity":"8d9413b7-8f44-4141-ae1f-a6cb21273c92","added_by":"auto","created_at":"2026-02-19 04:19:17","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":974132,"visible":true,"origin":"","legend":"","description":"","filename":"MRANAReconstructiveAttentionNetwork.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8887611/v1_covered_892d4375-9100-4c1a-b3de-78b4669f43e2.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eMRAN: A Reconstructive Attention Network for Handling Modality Sparsity in Multimodal Cancer Survival Analysis\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"University of Ain Temouchent","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":"Multimodal Learning, Survival Analysis, Missing Data Imputation, Deep Learning, Medical Image Diagnosis, Kidney Cancer","lastPublishedDoi":"10.21203/rs.3.rs-8887611/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8887611/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSurvival prediction in clear cell renal cell carcinoma (ccRCC) is challenging due to severe class imbalance and pervasive radiological data sparsity in real-world cohorts. Standard multimodal fusion techniques often degrade when modalities are missing, typically overfitting to the majority survival class (∼88%) and failing to reliably flag high-risk patients. We introduce the Multimodal Reconstructive Attention Network (MRAN), which integrates whole-slide images (WSI), CT, and clinical/genomic variables via attention-based fusion coupled with an auxiliary feature-level reconstruction branch. This branch learns to generate CT embeddings from histopathology, enabling the model to exploit radiological signals even for patients without acquired scans. Ablation studies confirm that a tri-modal configuration (WSI + CT + clinical), which explicitly excludes sparse MRI data, provides the optimal signal-to-noise ratio. Evaluated on the MMISTccRCC dataset with 5-fold cross-validation and an independent holdout test set, MRAN achieves a C-index of 0.835 and a Balanced Accuracy of 83.5%. At a clinically calibrated operating point, the model attains a Sensitivity of 81.3% (identifying mortality) and a Specificity of 85.7% (identifying survivors), thereby overcoming the accuracy paradox and demonstrating robust utility for 12-month risk stratification in ccRCC.\u003c/p\u003e","manuscriptTitle":"MRAN: A Reconstructive Attention Network for Handling Modality Sparsity in Multimodal Cancer Survival Analysis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-18 02:44:40","doi":"10.21203/rs.3.rs-8887611/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":"6fe278b1-54eb-4e11-a934-5a002c706dd4","owner":[],"postedDate":"February 18th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":62962719,"name":"Bioinformatics"},{"id":62962720,"name":"Biomedical Engineering"}],"tags":[],"updatedAt":"2026-02-18T02:44:40+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-18 02:44:40","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8887611","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8887611","identity":"rs-8887611","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}