DMA-UNet: A Dual-Branch Multi-Scale Attention U-Net for MRI Segmentation and Classification of Parotid Gland Tumours

DMA-UNet: A Dual-Branch Multi-Scale Attention U-Net for MRI Segmentation and Classification of Parotid Gland Tumours | 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 DMA-UNet: A Dual-Branch Multi-Scale Attention U-Net for MRI Segmentation and Classification of Parotid Gland Tumours Yousef Alswaiti, Ahmed Abed Mohammed, Lamyaa sabeeh Ashour Ashour, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9172585/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 The human salivary glands are classified as crucial components of the exocrine system, which are responsible for generating the saliva required for lubrication, digestion, and oral health, digestion, and maintaining oral health. The tumours of the parotid glands (PGTs) represent a significant clinical concern in head and neck oncology, and both benign versus malignant parotid gland tumours occur. The traditional methods of diagnosis, including the use of cytology with fine-needle aspiration (FNAC), are limited, and such limitations are the inconsistent sensitivity and the invasive nature of the method. This paper proposes a novel architecture built upon a multi-scale dual-branch U-Net to balance between the segmentation and classification of parotid gland tumours in parotid gland MRI. The model consists of a single encoder branch to obtain multi-scale features, while two distinct decoder branches facilitate simultaneous tumour segmentation and classification into normal, benign, and malignant classes. The attention mechanisms improve the model’s performance regarding emphasis on the most relevant imaging features. Preprocessing of a diverse dataset of 332 patients, which included different tumour types in MRI, was carried out and augmented to address class imbalance. The Dual Branch U-Net with Multi-Scale Attention was evaluated for segmentation and classification tasks using validation and unseen test datasets. The model demonstrates robust performance, with accuracy, precision, recall, and F1-score values steadily above 0.96 for both validation and testing datasets, while segmentation results showed perfect Dice coefficients of 0.9988 but extremely high IoU values of 0.9984, indicating effective region-level segmentation with some boundary limitations. This indicates that the model generalizes well and can classify tumour samples with high reliability. Category-wise, the model performs exceptionally well in identifying malignant tumours, achieving near-perfect precision and recall. Parotid Gland Tumour Classification MRI Dual-branch U-Net Attention Mechanism 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-9172585","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":611541715,"identity":"14bb6b0d-39b1-48ab-b232-9608ea2b09c4","order_by":0,"name":"Yousef Alswaiti","email":"","orcid":"","institution":"Department of oral and maxillofacial diagnoses and treatment centre, school and hospital of stomatology, China Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yousef","middleName":"","lastName":"Alswaiti","suffix":""},{"id":611541719,"identity":"034b00f4-eda8-4b9f-880a-c7a787154029","order_by":1,"name":"Ahmed Abed Mohammed","email":"","orcid":"","institution":"College of Computer Science and Information Technology, University of Al-Qadisiyah","correspondingAuthor":false,"prefix":"","firstName":"Ahmed","middleName":"Abed","lastName":"Mohammed","suffix":""},{"id":611541723,"identity":"431b568b-5974-4615-8de7-e7d1ea418ab1","order_by":2,"name":"Lamyaa sabeeh Ashour Ashour","email":"","orcid":"","institution":"Department of Mathematics, College of Basic Education, University of Misan","correspondingAuthor":false,"prefix":"","firstName":"Lamyaa","middleName":"sabeeh Ashour","lastName":"Ashour","suffix":""},{"id":611541725,"identity":"a2db4924-f19c-4e70-a117-9e8c4e73ff3f","order_by":3,"name":"Ahmed Kateb Jumaah Al-Nussairi","email":"","orcid":"","institution":"Department of Mathematics, College of Basic Education, University of Misan","correspondingAuthor":false,"prefix":"","firstName":"Ahmed","middleName":"Kateb Jumaah","lastName":"Al-Nussairi","suffix":""},{"id":611541726,"identity":"01368f96-ad65-4302-af0f-9c38aea0e815","order_by":4,"name":"Dhafer G. Honi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+ElEQVRIie3Lv0rDUBTH8d9dnGJdbyj0GW5xkEIfJmfKUorSxTHhwJ38s6bgQ+iWwSFdnPIAF9rBIDibzUIFjxq66A10c7jf5Rx+8AFCof+YA97kJIDKnxOM5FeZVtnX4iWq6AibBKcHERxpfBOglwzW3GTtI+YnQ7aXTWlg1py7tsTcVH+TePM0zotXLOK7lXVUC9mseLKssfAR45Kzl6gC3TsSYneykB0eW1m8JG1515FzsuaHfPSS2ZjREeyJ6iGxm13kV5WmZUGshUSxI55c17J4yMClD9l7NaVbnTbt1pqRLI3bllO68ZAuvf+iX0soFAqFDu8TrxNtIbLbB+cAAAAASUVORK5CYII=","orcid":"","institution":"Doctoral School of Informatics, University of Debrecen","correspondingAuthor":true,"prefix":"","firstName":"Dhafer","middleName":"G.","lastName":"Honi","suffix":""},{"id":611541728,"identity":"5b7710a1-147f-4185-b539-4c6123328ee0","order_by":5,"name":"Mohd Nadhir Ab Wahab","email":"","orcid":"","institution":"School of Computer Sciences, Universiti Sains Malaysia","correspondingAuthor":false,"prefix":"","firstName":"Mohd","middleName":"Nadhir Ab","lastName":"Wahab","suffix":""},{"id":611541730,"identity":"74f2e3cc-9a1b-49bf-af37-edfa87836086","order_by":6,"name":"Laszlo Szathmary","email":"","orcid":"","institution":"University of Debrecen, Department of IT","correspondingAuthor":false,"prefix":"","firstName":"Laszlo","middleName":"","lastName":"Szathmary","suffix":""}],"badges":[],"createdAt":"2026-03-19 19:38:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9172585/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9172585/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106402894,"identity":"d4298588-8335-46eb-80e6-3485c2eb0c30","added_by":"auto","created_at":"2026-04-08 09:13:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3561943,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9172585/v1_covered_3bcdf5ad-bc54-42ca-adb0-438753f60828.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"DMA-UNet: A Dual-Branch Multi-Scale Attention U-Net for MRI Segmentation and Classification of Parotid Gland Tumours","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":"Parotid Gland, Tumour Classification, MRI, Dual-branch U-Net, Attention Mechanism","lastPublishedDoi":"10.21203/rs.3.rs-9172585/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9172585/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The human salivary glands are classified as crucial components of the exocrine system, which are responsible for generating the saliva required for lubrication, digestion, and oral health, digestion, and maintaining oral health. The tumours of the parotid glands (PGTs) represent a significant clinical concern in head and neck oncology, and both benign versus malignant parotid gland tumours occur. The traditional methods of diagnosis, including the use of cytology with fine-needle aspiration (FNAC), are limited, and such limitations are the inconsistent sensitivity and the invasive nature of the method. This paper proposes a novel architecture built upon a multi-scale dual-branch U-Net to balance between the segmentation and classification of parotid gland tumours in parotid gland MRI. The model consists of a single encoder branch to obtain multi-scale features, while two distinct decoder branches facilitate simultaneous tumour segmentation and classification into normal, benign, and malignant classes. The attention mechanisms improve the model’s performance regarding emphasis on the most relevant imaging features. Preprocessing of a diverse dataset of 332 patients, which included different tumour types in MRI, was carried out and augmented to address class imbalance. The Dual Branch U-Net with Multi-Scale Attention was evaluated for segmentation and classification tasks using validation and unseen test datasets. The model demonstrates robust performance, with accuracy, precision, recall, and F1-score values steadily above 0.96 for both validation and testing datasets, while segmentation results showed perfect Dice coefficients of 0.9988 but extremely high IoU values of 0.9984, indicating effective region-level segmentation with some boundary limitations. This indicates that the model generalizes well and can classify tumour samples with high reliability. Category-wise, the model performs exceptionally well in identifying malignant tumours, achieving near-perfect precision and recall.","manuscriptTitle":"DMA-UNet: A Dual-Branch Multi-Scale Attention U-Net for MRI Segmentation and Classification of Parotid Gland Tumours","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-26 07:04:09","doi":"10.21203/rs.3.rs-9172585/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":"20a5b42b-2741-4566-8538-203295c2c115","owner":[],"postedDate":"March 26th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-06T06:10:37+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-26 07:04:09","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9172585","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9172585","identity":"rs-9172585","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}