Deep transfer learning for Multiple Sclerosis Detection and classification using pre-trained model

Deep transfer learning for Multiple Sclerosis Detection and classification using pre-trained model | 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 Deep transfer learning for Multiple Sclerosis Detection and classification using pre-trained model Dhyey Desai, Jayesh Gangrade, Yadvendra Singh, Shweta Gangrade, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3393656/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 Multiple sclerosis (MS) is a neurological condition that damages the central nervous system and is characterized by demyelination, inflammation , and axonal destruction. Early and correct MS diagnosis is essential for prompt treatment and better patient outcomes. With the help of total 3427 MRI images in the form of four different types of classes — Control Axial, Control Sagittal, MS-Axial, and MS-Sagittal. We Proposed a unique method for MS detection in this study. The pre-processing of the MRI data is the initial step of the proposed methodology. This research paper presents a comprehensive study aimed at enhancing MS classification through the augmentation of MRI data. By expanding the initial dataset of 3427 images to a robust collection of 10000 images using advanced techniques, the study offers an invaluable resource for training and evaluating MS detection algorithms, thereby fostering improved diagnostic outcomes. The VGG-16, VGG-19 and xception model are trained on the hybrid dataset, consisting of both axial and sagittal images, allowing it to capture the intricate patterns associated with MS lesions. We have obtained the highest accuracy, out of the 3 models used here, of 97%, by using the VGG-16 model. Multiple sclerosis MRI Images Image Classification Deep learning model Full Text Additional Declarations No competing interests reported. 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-3393656","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":236854558,"identity":"2afbcfa6-dd6b-4ae5-91a1-ecd57e22570f","order_by":0,"name":"Dhyey Desai","email":"","orcid":"","institution":"Manipal University Jaipur","correspondingAuthor":false,"prefix":"","firstName":"Dhyey","middleName":"","lastName":"Desai","suffix":""},{"id":236854559,"identity":"eaebae53-9ff2-44ac-838b-f6a826726d39","order_by":1,"name":"Jayesh Gangrade","email":"","orcid":"","institution":"Manipal University Jaipur","correspondingAuthor":false,"prefix":"","firstName":"Jayesh","middleName":"","lastName":"Gangrade","suffix":""},{"id":236854560,"identity":"f44e38e9-0071-4f4c-8ebb-3d8f4ddc521c","order_by":2,"name":"Yadvendra Singh","email":"","orcid":"","institution":"Manipal University Jaipur","correspondingAuthor":false,"prefix":"","firstName":"Yadvendra","middleName":"","lastName":"Singh","suffix":""},{"id":236854561,"identity":"358850fe-d7ac-444c-ba63-ba9bc85a04c8","order_by":3,"name":"Shweta Gangrade","email":"","orcid":"","institution":"Manipal University Jaipur","correspondingAuthor":false,"prefix":"","firstName":"Shweta","middleName":"","lastName":"Gangrade","suffix":""},{"id":236854562,"identity":"0bbabfa6-b537-4eba-88be-d28dbb283ffd","order_by":4,"name":"Gaurav Gupta","email":"","orcid":"","institution":"Shoolini’s University","correspondingAuthor":false,"prefix":"","firstName":"Gaurav","middleName":"","lastName":"Gupta","suffix":""},{"id":236854563,"identity":"b377edfe-4803-4497-abde-4e01567f83ff","order_by":5,"name":"Ahmad Waleed Salehi","email":"data:image/png;base64,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","orcid":"","institution":"Rana University Kabul","correspondingAuthor":true,"prefix":"","firstName":"Ahmad","middleName":"Waleed","lastName":"Salehi","suffix":""}],"badges":[],"createdAt":"2023-09-28 00:44:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3393656/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3393656/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":51154707,"identity":"74c91839-cae6-4b82-92ab-4159f516e0c5","added_by":"auto","created_at":"2024-02-15 05:38:30","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":665266,"visible":true,"origin":"","legend":"","description":"","filename":"MultipleSclerosis4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3393656/v1_covered_78372c1b-b83a-494b-8051-800a6b9dad3b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Deep transfer learning for Multiple Sclerosis Detection and classification using pre-trained model","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"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":"Multiple sclerosis, MRI Images, Image Classification, Deep learning model","lastPublishedDoi":"10.21203/rs.3.rs-3393656/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3393656/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Multiple sclerosis (MS) is a neurological condition that damages the central nervous system and is characterized by demyelination, inflammation , and axonal destruction. Early and correct MS diagnosis is essential for prompt treatment and better patient outcomes. With the help of total 3427 MRI images in the form of four different types of classes — Control Axial, Control Sagittal, MS-Axial, and MS-Sagittal. We Proposed a unique method for MS detection in this study. The pre-processing of the MRI data is the initial step of the proposed methodology. This research paper presents a comprehensive study aimed at enhancing MS classification through the augmentation of MRI data. By expanding the initial dataset of 3427 images to a robust collection of 10000 images using advanced techniques, the study offers an invaluable resource for training and evaluating MS detection algorithms, thereby fostering improved diagnostic outcomes. The VGG-16, VGG-19 and xception model are trained on the hybrid dataset, consisting of both axial and sagittal images, allowing it to capture the intricate patterns associated with MS lesions. We have obtained the highest accuracy, out of the 3 models used here, of 97%, by using the VGG-16 model.","manuscriptTitle":"Deep transfer learning for Multiple Sclerosis Detection and classification using pre-trained model","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-10-05 06:02:19","doi":"10.21203/rs.3.rs-3393656/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":"1b41b2da-9c6c-4d06-b41f-aa5739dab3dd","owner":[],"postedDate":"October 5th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-03-25T12:23:15+00:00","versionOfRecord":[],"versionCreatedAt":"2023-10-05 06:02:19","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3393656","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3393656","identity":"rs-3393656","version":["v1"]},"buildId":"_2-kVJe1T_tPrBINL-cwx","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}