A Multimodal Brain Tumor Segmentation Network Using Deep Learning Approach

A Multimodal Brain Tumor Segmentation Network Using Deep Learning Approach | 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 Multimodal Brain Tumor Segmentation Network Using Deep Learning Approach Yassine Aribi, Abdulmajid AlJunaid, Mohamed Ali Rekik, Brahim Kammoun, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9302809/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 12 You are reading this latest preprint version Abstract Over the last decade, several studies have been conducted to improve the efficiency and robustness of brain tumor detection and segmentation based on different parameters. Accurate volume segmentation of brain tumors and tissues facilitates quantitative brain analysis and disease identification in multimodal magnetic resonance (MR) images. However, three-dimensional fully convolutional networks (3D FCNs) using simple multimodal fusion strategies have difficulty learning complex non-linear complementary information between modalities due to the complex relationships between the modalities. At the same time, indiscriminate feature aggregation between low-level and high-level features can easily cause volumetric feature misalignment in 3D FCNs. To address these issues, we propose a network for segmenting brain tumor and tissue regions from MR images. In this network, a multimodal feature interaction module is firstly designed to adapt to effectively fuse and refine multimodal features. Secondly, a feature alignment module was developed to dynamically align low-level and high-level features by resampling the features with learnable weights. We have conducted extensive experiments on BraTS 2018 and BraTS 2020. The experimental results show that our network has superior performance over typical conventional brain tumor segmentation methods. Biological sciences/Cancer Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Physical sciences/Mathematics and computing brain tumor segmentation multimodal feature alignment MR images Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 29 Apr, 2026 Reviews received at journal 29 Apr, 2026 Reviewers agreed at journal 19 Apr, 2026 Reviewers agreed at journal 18 Apr, 2026 Reviewers agreed at journal 18 Apr, 2026 Reviewers agreed at journal 18 Apr, 2026 Reviewers agreed at journal 18 Apr, 2026 Reviewers invited by journal 18 Apr, 2026 Editor assigned by journal 18 Apr, 2026 Editor invited by journal 17 Apr, 2026 Submission checks completed at journal 11 Apr, 2026 First submitted to journal 11 Apr, 2026 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-9302809","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":628626735,"identity":"2a4bc31c-5fe6-47a9-83e9-f8186aa18b57","order_by":0,"name":"Yassine Aribi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA80lEQVRIiWNgGAWjYLCCBDDJ2MaQUCFBspYzxGqBAjaQLsLA4Pjxxx8e7rBh4J99uO3Bw3kWcvzsDYyPK37h0XImx0wi8Uwag8S5xHaDxG0SxpI9B5gNz/bh0XIgh40hse0wA8MZxjYJoJbEDTcS2CQbe/BoOf/88YfEtv8M8mAtcyTq999/QEDLjQQDicS2A0AXgrQ0SAC5DGySDT9wa5G88Qbol7ZkHsMzjO0GCcckDGecSWw2bGzArYXvfPrjjz/b7OTkzrA/e/ijpk6ev/3wwYcNf3BrUTgAoXmQxBgb8EaQPA4X4LFlFIyCUTAKRhwAAIPeVLTrFueGAAAAAElFTkSuQmCC","orcid":"","institution":"University of Sfax","correspondingAuthor":true,"prefix":"","firstName":"Yassine","middleName":"","lastName":"Aribi","suffix":""},{"id":628626738,"identity":"40ab3a09-966b-4263-bee0-dd1327796ccd","order_by":1,"name":"Abdulmajid AlJunaid","email":"","orcid":"","institution":"King Khalid University","correspondingAuthor":false,"prefix":"","firstName":"Abdulmajid","middleName":"","lastName":"AlJunaid","suffix":""},{"id":628626742,"identity":"70274f0e-848a-4ea6-9f9f-a0ad8a678f30","order_by":2,"name":"Mohamed Ali Rekik","email":"","orcid":"","institution":"CHU Hospital of Sfax University of Sfax","correspondingAuthor":false,"prefix":"","firstName":"Mohamed","middleName":"Ali","lastName":"Rekik","suffix":""},{"id":628626746,"identity":"4fc6291c-1f08-4d84-9368-9fa459273bc8","order_by":3,"name":"Brahim Kammoun","email":"","orcid":"","institution":"CHU Hospital of Sfax University of Sfax","correspondingAuthor":false,"prefix":"","firstName":"Brahim","middleName":"","lastName":"Kammoun","suffix":""},{"id":628626749,"identity":"1e379cac-35b7-4bbe-bf4a-ee6b53880d89","order_by":4,"name":"Ahmed AlMokhtar Ben Hmida","email":"","orcid":"","institution":"King Khalid University","correspondingAuthor":false,"prefix":"","firstName":"Ahmed","middleName":"AlMokhtar Ben","lastName":"Hmida","suffix":""},{"id":628626755,"identity":"03d2da90-cbfb-4893-a676-3ed9466a43b4","order_by":5,"name":"Turke Althobaiti","email":"","orcid":"","institution":"Northern Border University","correspondingAuthor":false,"prefix":"","firstName":"Turke","middleName":"","lastName":"Althobaiti","suffix":""}],"badges":[],"createdAt":"2026-04-02 11:53:46","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9302809/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9302809/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108006707,"identity":"568aa9c0-7018-4e0a-bafb-df795529500d","added_by":"auto","created_at":"2026-04-28 12:56:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":770973,"visible":true,"origin":"","legend":"","description":"","filename":"Papier3ScRupdated.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9302809/v1_covered_ef1beffd-1268-4c71-94e2-786aca9e2453.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Multimodal Brain Tumor Segmentation Network Using Deep Learning Approach","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"brain tumor, segmentation, multimodal, feature alignment, MR images","lastPublishedDoi":"10.21203/rs.3.rs-9302809/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9302809/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eOver the last decade, several studies have been conducted to improve the efficiency and robustness of brain tumor detection and segmentation based on different parameters. Accurate volume segmentation of brain tumors and tissues facilitates quantitative brain analysis and disease identification in multimodal magnetic resonance (MR) images. However, three-dimensional fully convolutional networks (3D FCNs) using simple multimodal fusion strategies have difficulty learning complex non-linear complementary information between modalities due to the complex relationships between the modalities. At the same time, indiscriminate feature aggregation between low-level and high-level features can easily cause volumetric feature misalignment in 3D FCNs. To address these issues, we propose a network for segmenting brain tumor and tissue regions from MR images. In this network, a multimodal feature interaction module is firstly designed to adapt to effectively fuse and refine multimodal features. Secondly, a feature alignment module was developed to dynamically align low-level and high-level features by resampling the features with learnable weights. We have conducted extensive experiments on BraTS 2018 and BraTS 2020. The experimental results show that our network has superior performance over typical conventional brain tumor segmentation methods.\u003c/p\u003e","manuscriptTitle":"A Multimodal Brain Tumor Segmentation Network Using Deep Learning Approach","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-27 14:04:04","doi":"10.21203/rs.3.rs-9302809/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-04-29T19:11:29+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-29T13:43:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"99793922261400830156651029784013285248","date":"2026-04-20T01:05:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"14461457135168045246477989274450791783","date":"2026-04-18T15:17:28+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"115605871254409157163110477124072819883","date":"2026-04-18T14:56:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"227290244231511092544187833752782892023","date":"2026-04-18T14:14:44+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"174228501540563203366399365165316344462","date":"2026-04-18T13:49:45+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-18T12:43:10+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-18T12:34:26+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-04-17T06:23:04+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-11T12:34:53+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-04-11T12:30:49+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"e3a606ef-61fb-4e2a-8ec9-16e11a400559","owner":[],"postedDate":"April 27th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":66909941,"name":"Biological sciences/Cancer"},{"id":66909942,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":66909943,"name":"Physical sciences/Engineering"},{"id":66909945,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-04-27T14:04:04+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-27 14:04:04","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9302809","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9302809","identity":"rs-9302809","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}