Explainable Deep Learning Framework for Brain Tumor Segmentation Using Vision Transformer and Conditional Random Fields

Explainable Deep Learning Framework for Brain Tumor Segmentation Using Vision Transformer and Conditional Random Fields | 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 Explainable Deep Learning Framework for Brain Tumor Segmentation Using Vision Transformer and Conditional Random Fields Homayoun Safarpour, Soroush Sadeghi, Payam Zarbakhsh, Mohammadreza Kamsari, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6404734/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 04 Dec, 2025 Read the published version in Multimedia Systems → Version 1 posted 11 You are reading this latest preprint version Abstract Background/Objectives: Brain tumor segmentation is critical for accurate identification and treatment planning. However, delineating intricate tumor areas like Edema, Tumor Core, and Enhancing Tumor remains challenging owing to diversity in dimensions, morphology, and delineation. Methods: This introduces an innovative a novel deep learning model integrating a Pretrained Vision Transformer (ViT) for global context representation, Atrous Spatial Pyramid Pooling (ASPP) in both encoder and merging stages, and ReLU6. Additionally, attention mechanisms and Conditional Random Fields (CRF) were incorporated for refining feature emphasis and segmentation boundaries. Results: The model was trained and tested on the BraTS 2020 dataset and compared with state-of-the-art methods. The suggested model obtained the highest Dice coefficients across all tumor regions, with improvements of up to 4% for Enhancing Tumor and Edema. Grad-CAM heatmaps illustrated the model's proficiency in precisely identifying tumor areas, hence enhancing the interpretability of predictions. Conclusions: The incorporation of multi-scale feature extraction, attention mechanism, and global context representation markedly improved segmentation accuracy and interpretability. The findings underscore the proposed model's capacity to enhance clinical processes and establish a standard for brain tumor segmentation tasks. Future endeavors involve testing on varied datasets and investigating lightweight structures for real-time applications. Brain Tumor Segmentation Vision Transformer Grad-CAM Conditional Random Fields Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 04 Dec, 2025 Read the published version in Multimedia Systems → Version 1 posted Editorial decision: Revision requested 22 Sep, 2025 Reviews received at journal 23 Jun, 2025 Reviews received at journal 13 Jun, 2025 Reviews received at journal 13 Jun, 2025 Reviewers agreed at journal 04 Jun, 2025 Reviewers agreed at journal 03 Jun, 2025 Reviewers agreed at journal 03 Jun, 2025 Reviewers invited by journal 03 Jun, 2025 Editor assigned by journal 02 May, 2025 Submission checks completed at journal 10 Apr, 2025 First submitted to journal 08 Apr, 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-6404734","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":466229830,"identity":"04de815e-4bd1-466d-bc13-baaec7c283de","order_by":0,"name":"Homayoun Safarpour","email":"","orcid":"","institution":"University of Szeged","correspondingAuthor":false,"prefix":"","firstName":"Homayoun","middleName":"","lastName":"Safarpour","suffix":""},{"id":466229831,"identity":"c319b0d4-3e5e-42b2-80b0-f43e27204533","order_by":1,"name":"Soroush Sadeghi","email":"","orcid":"","institution":"University of Tehran","correspondingAuthor":false,"prefix":"","firstName":"Soroush","middleName":"","lastName":"Sadeghi","suffix":""},{"id":466229836,"identity":"191322f1-07bd-43ef-af35-ded28b845598","order_by":2,"name":"Payam Zarbakhsh","email":"","orcid":"","institution":"Ada kent University","correspondingAuthor":false,"prefix":"","firstName":"Payam","middleName":"","lastName":"Zarbakhsh","suffix":""},{"id":466229838,"identity":"ad7a6dff-86c1-4284-8358-cfab78207c3e","order_by":3,"name":"Mohammadreza Kamsari","email":"","orcid":"","institution":"Malek-Ashtar University of Technology(MUT)","correspondingAuthor":false,"prefix":"","firstName":"Mohammadreza","middleName":"","lastName":"Kamsari","suffix":""},{"id":466229839,"identity":"e8793e11-e8c4-45c9-bcac-a5cefe200e10","order_by":4,"name":"Marjan Kia","email":"","orcid":"","institution":"Park University","correspondingAuthor":false,"prefix":"","firstName":"Marjan","middleName":"","lastName":"Kia","suffix":""},{"id":466229841,"identity":"4f8adb5f-d413-4707-b462-5beb6ce80774","order_by":5,"name":"Ramin Ranjbarzadeh","email":"data:image/png;base64,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","orcid":"","institution":"University of Galway","correspondingAuthor":true,"prefix":"","firstName":"Ramin","middleName":"","lastName":"Ranjbarzadeh","suffix":""}],"badges":[],"createdAt":"2025-04-08 15:23:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6404734/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6404734/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00530-025-02075-y","type":"published","date":"2025-12-04T15:57:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":97723809,"identity":"44ff53b3-76bc-49d9-be00-1b3c717ea65e","added_by":"auto","created_at":"2025-12-08 16:07:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2105152,"visible":true,"origin":"","legend":"","description":"","filename":"BrainViTCRF.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6404734/v1_covered_e025bf52-c7a7-4324-8b52-ce4abd9fc2dd.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Explainable Deep Learning Framework for Brain Tumor Segmentation Using Vision Transformer and Conditional Random Fields","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Brain Tumor Segmentation; Vision Transformer; Grad-CAM; Conditional Random Fields","lastPublishedDoi":"10.21203/rs.3.rs-6404734/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6404734/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBackground/Objectives: Brain tumor segmentation is critical for accurate identification and treatment planning. However, delineating intricate tumor areas like Edema, Tumor Core, and Enhancing Tumor remains challenging owing to diversity in dimensions, morphology, and delineation.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eMethods: This introduces an innovative a novel deep learning model integrating a Pretrained Vision Transformer (ViT) for global context representation, Atrous Spatial Pyramid Pooling (ASPP) in both encoder and merging stages, and ReLU6. Additionally, attention mechanisms and Conditional Random Fields (CRF) were incorporated for refining feature emphasis and segmentation boundaries.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eResults: The model was trained and tested on the BraTS 2020 dataset and compared with state-of-the-art methods. The suggested model obtained the highest Dice coefficients across all tumor regions, with improvements of up to 4% for Enhancing Tumor and Edema. Grad-CAM heatmaps illustrated the model's proficiency in precisely identifying tumor areas, hence enhancing the interpretability of predictions.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eConclusions: The incorporation of multi-scale feature extraction, attention mechanism, and global context representation markedly improved segmentation accuracy and interpretability. The findings underscore the proposed model's capacity to enhance clinical processes and establish a standard for brain tumor segmentation tasks. Future endeavors involve testing on varied datasets and investigating lightweight structures for real-time applications.\u003c/p\u003e","manuscriptTitle":"Explainable Deep Learning Framework for Brain Tumor Segmentation Using Vision Transformer and Conditional Random Fields","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-09 07:28:34","doi":"10.21203/rs.3.rs-6404734/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-22T09:54:51+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-23T16:33:32+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-13T11:15:57+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-13T05:57:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"227487692604742919675529102741260983262","date":"2025-06-04T06:09:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"53792586964982675995187836242698695706","date":"2025-06-04T02:03:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"146799412909647911860695728120510078070","date":"2025-06-03T11:36:36+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-03T11:29:50+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-02T07:27:55+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-10T10:14:46+00:00","index":"","fulltext":""},{"type":"submitted","content":"Multimedia Systems","date":"2025-04-08T15:20:24+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"56b80e9d-a14e-44ae-b1f0-16af872ddfca","owner":[],"postedDate":"June 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-12-08T16:00:15+00:00","versionOfRecord":{"articleIdentity":"rs-6404734","link":"https://doi.org/10.1007/s00530-025-02075-y","journal":{"identity":"multimedia-systems","isVorOnly":false,"title":"Multimedia Systems"},"publishedOn":"2025-12-04 15:57:00","publishedOnDateReadable":"December 4th, 2025"},"versionCreatedAt":"2025-06-09 07:28:34","video":"","vorDoi":"10.1007/s00530-025-02075-y","vorDoiUrl":"https://doi.org/10.1007/s00530-025-02075-y","workflowStages":[]},"version":"v1","identity":"rs-6404734","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6404734","identity":"rs-6404734","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}