EMSA-Net: Enhancing Brain Tumor Segmentation with Equivalent Multi-Scale and Cross-Modality Attention under limited MRI Modalities

EMSA-Net: Enhancing Brain Tumor Segmentation with Equivalent Multi-Scale and Cross-Modality Attention under limited MRI Modalities | 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 EMSA-Net: Enhancing Brain Tumor Segmentation with Equivalent Multi-Scale and Cross-Modality Attention under limited MRI Modalities Beibei Hou, Yamin Wang, Zhaozhao Xu, Junding Sun, Lihong Zhang, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8701857/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 Multi-modality medical imaging is essential for disease diagnosis and clinical treatment as it can provide complementary information on the morphological features of tumors. Clinically, acquiring four complete modalities is difficult due to device limitations, scan time, and limited costs, such that getting high segmentation performance for brain tumors becomes more challenging. Scale Module (EMS) utilizes the available modalities to extract brain tumor regions fully and integrates features according to the contributions of available modalities. Cross-Modality Attention Mechanism (CMA) further fuses multi-modality features and mitigates the impact of limited modalities in medical image segmentation. In this way, EMSA-Net can effectively capture the relationship between different modalities and tumor regions, enhancing the robustness of the model. Additionally, this paper introduces a knowledge distillation method where the student network is trained on a subset of the teacher’s inputs. This approach allows the student model to learn from the teacher model’s knowledge, enabling effective segmentation even with limited modalities. The proposed method is evaluated on the BraTS2020 dataset, demonstrating its effectiveness in improving segmentation performance under limited modality conditions. The performance of the proposed model is superior to state-of-the-art methods. For all 15 multi-modality combinations, the proposed method achieves average Dice scores of 88.7% for WT, 82.7% for TC, and 68.8% for ET, outperforming other methods by 0.8%, 2.9%, and 2.1% respectively. More important, limited modalities, such as T1ce, also perform comparably to complete modalities. Limited modality brain tumor segmentation feature fusion cross-modality knowledge distillation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 05 Mar, 2026 Reviewers agreed at journal 20 Feb, 2026 Reviewers invited by journal 20 Feb, 2026 Editor assigned by journal 20 Feb, 2026 Submission checks completed at journal 27 Jan, 2026 First submitted to journal 26 Jan, 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-8701857","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":594822957,"identity":"2f7dc7cd-535c-4116-9927-27e093f02e1d","order_by":0,"name":"Beibei Hou","email":"","orcid":"","institution":"Henan Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Beibei","middleName":"","lastName":"Hou","suffix":""},{"id":594822959,"identity":"8ad013fa-8250-436f-858e-bc9cde34966d","order_by":1,"name":"Yamin Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCElEQVRIiWNgGAWjYBADHgb2HjAjAcolRgvPGRK1MDBI5BCpxeD42cOveWq2yZhLvj346EYFQ565RALjg7dtDPLmuLScyUuz5jl2m8dydl6ycc4ZhmLLGQnMhnPbGAx3NmDXYnYgx8yYh+02j8HtHDPp3DaGxA03EtikedsYEgwO4NBy/g1Qyz+glptngFr+gbWw/8ar5UaO8WPeNqCWGzxALQ0QW5jxabG/8caMcW4fUMuZHGPjnGMSiTt7HjZLzjknYbgBhxbJ/hzjD2++3bY3OH7G8HFOjU3idvbkgx/elNnI47IFCNikkGJBgsGAgbEBzMADmD/+QOYa4FM7CkbBKBgFIxIAACPGXJAETxYaAAAAAElFTkSuQmCC","orcid":"","institution":"Henan Polytechnic University","correspondingAuthor":true,"prefix":"","firstName":"Yamin","middleName":"","lastName":"Wang","suffix":""},{"id":594822961,"identity":"39a73063-080b-422a-9b4d-ee0899acc104","order_by":2,"name":"Zhaozhao Xu","email":"","orcid":"","institution":"Henan Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Zhaozhao","middleName":"","lastName":"Xu","suffix":""},{"id":594822963,"identity":"78e1c09c-5467-4c00-9ddf-34ccf9a1740f","order_by":3,"name":"Junding Sun","email":"","orcid":"","institution":"Henan Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Junding","middleName":"","lastName":"Sun","suffix":""},{"id":594822965,"identity":"b7da861a-dbed-4a52-9e60-400434e07bba","order_by":4,"name":"Lihong Zhang","email":"","orcid":"","institution":"Henan Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Lihong","middleName":"","lastName":"Zhang","suffix":""},{"id":594822967,"identity":"9ac59c39-2658-4fc0-8d76-8be726361e7f","order_by":5,"name":"Lei Zhao","email":"","orcid":"","institution":"Hunan University","correspondingAuthor":false,"prefix":"","firstName":"Lei","middleName":"","lastName":"Zhao","suffix":""},{"id":594822969,"identity":"422fbde8-d9b9-4e81-8fb0-14a51bbe2c20","order_by":6,"name":"Bin Pu","email":"","orcid":"","institution":"Hong Kong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Bin","middleName":"","lastName":"Pu","suffix":""},{"id":594822970,"identity":"5c7ac3a7-134e-458b-bcee-cd2177e3b494","order_by":7,"name":"Yudong Zhang","email":"","orcid":"","institution":"Henan Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Yudong","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2026-01-26 15:25:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8701857/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8701857/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":103507105,"identity":"9dbbe2e9-4c28-4d84-ab08-f129cb76de6c","added_by":"auto","created_at":"2026-02-26 13:40:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1192869,"visible":true,"origin":"","legend":"","description":"","filename":"EMSANet.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8701857/v1_covered_034beeb9-3328-4c46-9d89-73a34c02a17a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"EMSA-Net: Enhancing Brain Tumor Segmentation with Equivalent Multi-Scale and Cross-Modality Attention under limited MRI Modalities","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":"Limited modality, brain tumor segmentation, feature fusion, cross-modality, knowledge distillation","lastPublishedDoi":"10.21203/rs.3.rs-8701857/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8701857/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Multi-modality medical imaging is essential for disease diagnosis and clinical treatment as it can provide complementary information on the morphological features of tumors. Clinically, acquiring four complete modalities is difficult due to device limitations, scan time, and limited costs, such that getting high segmentation performance for brain tumors becomes more challenging. Scale Module (EMS) utilizes the available modalities to extract brain tumor regions fully and integrates features according to the contributions of available modalities. Cross-Modality Attention Mechanism (CMA) further fuses multi-modality features and mitigates the impact of limited modalities in medical image segmentation. In this way, EMSA-Net can effectively capture the relationship between different modalities and tumor regions, enhancing the robustness of the model. Additionally, this paper introduces a knowledge distillation method where the student network is trained on a subset of the teacher’s inputs. This approach allows the student model to learn from the teacher model’s knowledge, enabling effective segmentation even with limited modalities. The proposed method is evaluated on the BraTS2020 dataset, demonstrating its effectiveness in improving segmentation performance under limited modality conditions. The performance of the proposed model is superior to state-of-the-art methods. For all 15 multi-modality combinations, the proposed method achieves average Dice scores of 88.7% for WT, 82.7% for TC, and 68.8% for ET, outperforming other methods by 0.8%, 2.9%, and 2.1% respectively. More important, limited modalities, such as T1ce, also perform comparably to complete modalities.","manuscriptTitle":"EMSA-Net: Enhancing Brain Tumor Segmentation with Equivalent Multi-Scale and Cross-Modality Attention under limited MRI Modalities","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-25 09:00:18","doi":"10.21203/rs.3.rs-8701857/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-03-05T05:28:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"146799412909647911860695728120510078070","date":"2026-02-21T01:24:08+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-20T16:38:04+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-20T16:37:16+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-28T04:20:57+00:00","index":"","fulltext":""},{"type":"submitted","content":"Cluster Computing","date":"2026-01-26T15:22:01+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":"eb087379-d005-4d6d-8277-6beb185135e0","owner":[],"postedDate":"February 25th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-02-25T09:00:18+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-25 09:00:18","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8701857","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8701857","identity":"rs-8701857","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}