Enhancing Semantic Segmentation Accuracy for Small Tumors Integrating Structural Properties

Enhancing Semantic Segmentation Accuracy for Small Tumors Integrating Structural Properties | 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 Enhancing Semantic Segmentation Accuracy for Small Tumors Integrating Structural Properties Md Rakibul Islam, Riad Hassan, Abdullah Nazib, Feroza Naznin, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8651167/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Deep learning has achieved remarkable accuracy in medical image segmentation, particularly for larger structures with well-defined boundaries. However, its effectiveness can be challenged by factors such as irregular object shapes and edges, non-smooth surfaces, small target areas, etc. which complicate the ability of networks to grasp the intricate and diverse nature of anatomical regions. In response to these challenges, we propose an to integrate object boundary smoothness and size into account, with the goal to improve segmentation performance in intricate anatomical regions. In this regard, we introduce two parameters derived from surface smoothness and volume information and integrate them into focal loss. Our proposed loss function dynamically adjusts itself based on an object's surface smoothness, and size, based on the ratio of targeted area and background. We evaluated the performance of the proposed loss function on the PICAI 2022 and BraTS 2018 datasets. In the PICAI 2022 dataset, the it achieved an Intersection over Union (IoU) score of 0.696 and a Dice Similarity Coefficient (DSC) of 0.769, outperforming the regular focal Loss (FL) by 5.5% and 5.4% respectively. It also surpassed the best baseline by 2.0% and 1.2%. In the BraTS 2018 dataset, it achieved an IoU score of 0.883 and a DSC score of 0.931. Our ablation experiments also show that the proposed integration strategy surpasses conventional losses (this includes Dice Loss, Focal Loss, and their hybrid variants) by large margin in IoU, DSC, and other metrics. Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Physical sciences/Mathematics and computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 11 May, 2026 Reviewers agreed at journal 14 Apr, 2026 Reviewers invited by journal 14 Apr, 2026 Editor invited by journal 17 Feb, 2026 Editor assigned by journal 23 Jan, 2026 Submission checks completed at journal 23 Jan, 2026 First submitted to journal 20 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-8651167","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":625890603,"identity":"4dd136a9-05d2-4c06-a917-a09d5ba77c9b","order_by":0,"name":"Md Rakibul Islam","email":"","orcid":"","institution":"Islamic University","correspondingAuthor":false,"prefix":"","firstName":"Md","middleName":"Rakibul","lastName":"Islam","suffix":""},{"id":625890604,"identity":"cd8b1246-9c60-422e-b9de-55575d0671f6","order_by":1,"name":"Riad Hassan","email":"","orcid":"","institution":"Green University of Bangladesh","correspondingAuthor":false,"prefix":"","firstName":"Riad","middleName":"","lastName":"Hassan","suffix":""},{"id":625890606,"identity":"ff61a5bb-140c-4ddb-966c-9c2d8c733a61","order_by":2,"name":"Abdullah Nazib","email":"","orcid":"","institution":"Queensland University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Abdullah","middleName":"","lastName":"Nazib","suffix":""},{"id":625890608,"identity":"aac8ca94-65e4-49fd-a8c3-d77f916d8ac1","order_by":3,"name":"Feroza Naznin","email":"","orcid":"","institution":"Green University of Bangladesh","correspondingAuthor":false,"prefix":"","firstName":"Feroza","middleName":"","lastName":"Naznin","suffix":""},{"id":625890611,"identity":"6f28bc72-0097-4bff-b31a-aa6400a23820","order_by":4,"name":"MD ZAHIDUL ISLAM","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4klEQVRIiWNgGAWjYFACHoYDPAYgBvMBICEhQ4oWtgSQFh6itDBAlEE0EtYi33724IE3Bdvk5d17Pr+6UWPBw8B++OgGfFoYe/ISDs4xuG248czZbdY5x4AO40lLu4FPCzNDjsFhHoPbjBtn5G4zzmEDapHgMcOrhY3/DViL/cb5b54Z5/wjQguPBMSWxPkSPMyPc9uI0CIh8cYA5JfkDTxpZsy5fRI8bIT8It+fY/zhzZ/btvPbDz/+nPOtTo6f/fAxvFrgwOAAA5sE2HdEKQdb18DA/IFo1aNgFIyCUTCiAAD15El96nAUHQAAAABJRU5ErkJggg==","orcid":"","institution":"Islamic University","correspondingAuthor":true,"prefix":"","firstName":"MD","middleName":"ZAHIDUL","lastName":"ISLAM","suffix":""},{"id":625890616,"identity":"c4abf577-dc5d-4eae-b0d1-122b9cbcb979","order_by":5,"name":"Clinton Fookes","email":"","orcid":"","institution":"Queensland University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Clinton","middleName":"","lastName":"Fookes","suffix":""}],"badges":[],"createdAt":"2026-01-20 16:27:35","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8651167/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8651167/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107415395,"identity":"01e1bcdd-3b59-4aa9-ba92-71ffdf5c36f8","added_by":"auto","created_at":"2026-04-21 09:43:10","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":661744,"visible":true,"origin":"","legend":"","description":"","filename":"RevisedScientificReportsSubmissionV1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8651167/v1_covered_21e6718d-5f38-4e04-a7ec-d2b175aa1450.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eEnhancing Semantic Segmentation Accuracy for Small Tumors Integrating Structural Properties\u003c/p\u003e","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":"","lastPublishedDoi":"10.21203/rs.3.rs-8651167/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8651167/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Deep learning has achieved remarkable accuracy in medical image segmentation, particularly for larger structures with well-defined boundaries. However, its effectiveness can be challenged by factors such as irregular object shapes and edges, non-smooth surfaces, small target areas, etc. which complicate the ability of networks to grasp the intricate and diverse nature of anatomical regions. In response to these challenges, we propose an to integrate object boundary smoothness and size into account, with the goal to improve segmentation performance in intricate anatomical regions. In this regard, we introduce two parameters derived from surface smoothness and volume information and integrate them into focal loss. Our proposed loss function dynamically adjusts itself based on an object's surface smoothness, and size, based on the ratio of targeted area and background. We evaluated the performance of the proposed loss function on the PICAI 2022 and BraTS 2018 datasets. In the PICAI 2022 dataset, the it achieved an Intersection over Union (IoU) score of 0.696 and a Dice Similarity Coefficient (DSC) of 0.769, outperforming the regular focal Loss (FL) by 5.5\\% and 5.4\\% respectively. It also surpassed the best baseline by 2.0\\% and 1.2\\%. In the BraTS 2018 dataset, it achieved an IoU score of 0.883 and a DSC score of 0.931. Our ablation experiments also show that the proposed integration strategy surpasses conventional losses (this includes Dice Loss, Focal Loss, and their hybrid variants) by large margin in IoU, DSC, and other metrics. ","manuscriptTitle":"Enhancing Semantic Segmentation Accuracy for Small Tumors Integrating Structural Properties","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-21 09:41:16","doi":"10.21203/rs.3.rs-8651167/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"16883544358800880186336300265029836","date":"2026-05-11T13:38:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"27258329816761940382018848690369545847","date":"2026-04-14T18:29:19+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-14T17:54:50+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-02-18T03:59:47+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-24T04:36:12+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-24T04:36:04+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-01-20T14:27:05+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":"c85bf500-3bdc-4b42-bc80-8353011ea27f","owner":[],"postedDate":"April 21st, 2026","published":true,"recentEditorialEvents":[{"type":"reviewerAgreed","content":"16883544358800880186336300265029836","date":"2026-05-11T13:38:01+00:00","index":119,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":66719123,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":66719124,"name":"Physical sciences/Engineering"},{"id":66719125,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-04-21T09:41:17+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-21 09:41:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8651167","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8651167","identity":"rs-8651167","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}