Prostate MR Image Segmentation Using a Multi-Stage Network Approach

Prostate MR Image Segmentation Using a Multi-Stage Network Approach | 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 Prostate MR Image Segmentation Using a Multi-Stage Network Approach Lars Erik Olof Jacobson, Mohamed Bader-El-Den, Lalit Maurya, Adrian Hopgood, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6808322/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 05 Sep, 2025 Read the published version in International Urology and Nephrology → Version 1 posted You are reading this latest preprint version Abstract Prostate cancer (PCa) remains one of the most prevalent cancers among men, with over 1.4 million new cases and 375,304 deaths reported globally in 2020. Current diagnostic approaches, such as prostate specific antigen (PSA) testing and trans-rectal ultrasound (TRUS)-guided biopsies, are often limited by low specificity and accuracy. This study addresses these limitations by leveraging deep learning-based image segmentation techniques on a dataset comprising 61,119 T2-weighted MR images from 1,151 patients to enhance PCa detection and characterisation. A multi-stage segmentation approach, including One-Stage, Sequential Two-Stage, and End-to-End Two-Stage methods, was evaluated using various deep learning architectures. The MultiResUNet model, integrated into a multi-stage segmentation framework, demonstrated significant improvements in delineating prostate boundaries. The study utilised a dataset of over 61,000 T2-weighted magnetic resonance (MR) images from more than 1,100 patients, employing three distinct segmentation strategies: One-Stage, Sequential Two-Stage, and End-to-End Two-Stage methods. The end-to-end approach, leveraging shared feature representations, consistently outperformed other methods, underscoring its effectiveness in enhancing diagnostic accuracy. These findings highlight the potential of advanced deep learning architectures in streamlining prostate cancer detection and treatment planning. Future work will focus on further optimisation of the models and assessing their generalisability to diverse medical imaging contexts. Image segmentation prostate magnetic resonance imaging u-net end-to-end Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 05 Sep, 2025 Read the published version in International Urology and Nephrology → 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-6808322","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":467691167,"identity":"a22a667c-803f-4e48-9d20-a1558cc1652b","order_by":0,"name":"Lars Erik Olof Jacobson","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBUlEQVRIiWNgGAWjYBACPjDJA8QSIEYFAwNjAwEtbKhazhCthQGqhbGNCIexsZ99/IFBxk6eX7r94ePCeTZyzP1rHz7m3cEgzy92ALsWnnQzCQaeZMOZc84YG8/clmbMOOO5sTHvGQbDmbMTcDgsDeg2HuYEgxs5bNK82w4nNs44BmS0MSQY3Mahhf8Z8wcGnnqglvRn0rxz/hOhRSIN6HGew0AtCWbSvA0HEhv72whpecYmkcBzHOIXnmPJQL+wMRvOPSOB0y/8/GnMHz72VENCjKfGTs6w/xjjg7c7bIAi2LWAQWIPEsdwRgIoPiVwKweDH0hsef4DRCSBUTAKRsEoGEkAAN1GUmAIW0avAAAAAElFTkSuQmCC","orcid":"","institution":"University of Portsmouth","correspondingAuthor":true,"prefix":"","firstName":"Lars","middleName":"Erik Olof","lastName":"Jacobson","suffix":""},{"id":467691168,"identity":"cccf79ad-1624-43d6-a373-48663282c88b","order_by":1,"name":"Mohamed Bader-El-Den","email":"","orcid":"","institution":"University of Portsmouth","correspondingAuthor":false,"prefix":"","firstName":"Mohamed","middleName":"","lastName":"Bader-El-Den","suffix":""},{"id":467691169,"identity":"72233e8f-ced8-48ce-8e56-db61fbc74247","order_by":2,"name":"Lalit Maurya","email":"","orcid":"","institution":"University of Portsmouth","correspondingAuthor":false,"prefix":"","firstName":"Lalit","middleName":"","lastName":"Maurya","suffix":""},{"id":467691171,"identity":"6d191336-a93f-4e55-8bc5-ec7a01207b82","order_by":3,"name":"Adrian Hopgood","email":"","orcid":"","institution":"University of Portsmouth","correspondingAuthor":false,"prefix":"","firstName":"Adrian","middleName":"","lastName":"Hopgood","suffix":""},{"id":467691173,"identity":"9665f3f9-36c3-4ab1-802e-ba13ec571486","order_by":4,"name":"Vincenzo Tamma","email":"","orcid":"","institution":"University of Portsmouth","correspondingAuthor":false,"prefix":"","firstName":"Vincenzo","middleName":"","lastName":"Tamma","suffix":""},{"id":467691175,"identity":"515ff7c4-450b-46bf-98a3-0da8781c8e70","order_by":5,"name":"Shamsul Masum","email":"","orcid":"","institution":"University of Portsmouth","correspondingAuthor":false,"prefix":"","firstName":"Shamsul","middleName":"","lastName":"Masum","suffix":""},{"id":467691176,"identity":"4f31c0cf-c548-4bbc-9700-8c910211e993","order_by":6,"name":"David Prendergast","email":"","orcid":"","institution":"Innovative Physics Ltd","correspondingAuthor":false,"prefix":"","firstName":"David","middleName":"","lastName":"Prendergast","suffix":""},{"id":467691177,"identity":"a0ab89b7-81d6-4128-81d2-14ba9c6ffb81","order_by":7,"name":"Peter Osborn","email":"","orcid":"","institution":"University NHS Trust","correspondingAuthor":false,"prefix":"","firstName":"Peter","middleName":"","lastName":"Osborn","suffix":""}],"badges":[],"createdAt":"2025-06-03 07:38:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6808322/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6808322/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11255-025-04763-0","type":"published","date":"2025-09-05T15:57:32+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":90828101,"identity":"ae3461eb-9f92-4a18-bac3-e5d52f1e1f81","added_by":"auto","created_at":"2025-09-08 16:05:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":9643997,"visible":true,"origin":"","legend":"","description":"","filename":"MRIImageSegmentation2025JournalPaperSpringerversion.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6808322/v1_covered_62775612-ca4a-463f-9523-915623b4feb7.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Prostate MR Image Segmentation Using a Multi-Stage Network Approach","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"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":"Image segmentation, prostate, magnetic resonance imaging, u-net, end-to-end","lastPublishedDoi":"10.21203/rs.3.rs-6808322/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6808322/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Prostate cancer (PCa) remains one of the most prevalent cancers among men, with over 1.4 million new cases and 375,304 deaths reported globally in 2020. Current diagnostic approaches, such as prostate specific antigen (PSA) testing and trans-rectal ultrasound (TRUS)-guided biopsies, are often limited by low specificity and accuracy. This study addresses these limitations by leveraging deep learning-based image segmentation techniques on a dataset comprising 61,119 T2-weighted MR images from 1,151 patients to enhance PCa detection and characterisation. A multi-stage segmentation approach, including One-Stage, Sequential Two-Stage, and End-to-End Two-Stage methods, was evaluated using various deep learning architectures. The MultiResUNet model, integrated into a multi-stage segmentation framework, demonstrated significant improvements in delineating prostate boundaries. The study utilised a dataset of over 61,000 T2-weighted magnetic resonance (MR) images from more than 1,100 patients, employing three distinct segmentation strategies: One-Stage, Sequential Two-Stage, and End-to-End Two-Stage methods. The end-to-end approach, leveraging shared feature representations, consistently outperformed other methods, underscoring its effectiveness in enhancing diagnostic accuracy. These findings highlight the potential of advanced deep learning architectures in streamlining prostate cancer detection and treatment planning. Future work will focus on further optimisation of the models and assessing their generalisability to diverse medical imaging contexts.","manuscriptTitle":"Prostate MR Image Segmentation Using a Multi-Stage Network Approach","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-09 03:31:07","doi":"10.21203/rs.3.rs-6808322/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":"57743844-43f9-44a4-aa44-9942b7933258","owner":[],"postedDate":"June 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-09-08T16:03:49+00:00","versionOfRecord":{"articleIdentity":"rs-6808322","link":"https://doi.org/10.1007/s11255-025-04763-0","journal":{"identity":"international-urology-and-nephrology","isVorOnly":false,"title":"International Urology and Nephrology"},"publishedOn":"2025-09-05 15:57:32","publishedOnDateReadable":"September 5th, 2025"},"versionCreatedAt":"2025-06-09 03:31:07","video":"","vorDoi":"10.1007/s11255-025-04763-0","vorDoiUrl":"https://doi.org/10.1007/s11255-025-04763-0","workflowStages":[]},"version":"v1","identity":"rs-6808322","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6808322","identity":"rs-6808322","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}