Nucleus Image Segmentation Method Based on GAN Network and FCN Model

Nucleus Image Segmentation Method Based on GAN Network and FCN 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 Nucleus Image Segmentation Method Based on GAN Network and FCN Model Kai Zhang, Yang Shi, Chengquan Hu, Hang Yu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-858913/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract Aiming at the problems of rough edges and low accuracy in processing cell nucleus image segmentation in existing image segmentation methods. A cell nucleus image segmentation technology based on generative adversarial network (GAN) network and fully convolutional network (FCN) model is proposed. First, the FCN model is used to perform preliminary segmentation of the cell nucleus image, in which the fully connected layer convolution and skip connection are used to improve the accuracy of image segmentation. Then, improve the GAN network, introduce splitting branches into the discriminator structure, and combine the GAN network and the splitting network into one. At the same time, pixel loss is introduced in the generator to obtain a nucleus image that is visually more similar to the real image. Finally, the segmented image output by the FCN model is used as the input of the GAN network to achieve high-precision segmentation of the nucleus image. The proposed method is experimentally demonstrated based on the 2018 data science bowl dataset. The results show that it can achieve rapid convergence, and the mean intersection over union (MIoU) is 85.34%, which is better than other comparison methods. Geometry Topology Theoretical Computer Science Nucleus image Image segmentation technology GAN network FCN model Fully connected layer convolution Pixel loss Full Text Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 05 Sep, 2021 Reviewers invited by journal 04 Sep, 2021 Editor assigned by journal 30 Aug, 2021 First submitted to journal 29 Aug, 2021 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-858913","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":50196303,"identity":"427977b4-5ae3-4bf1-b181-abd0b48a8c85","order_by":0,"name":"Kai Zhang","email":"","orcid":"","institution":"Changchun University of Finance and Economics","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Kai","middleName":"","lastName":"Zhang","suffix":""},{"id":50196304,"identity":"094cc639-1837-4917-81d7-4a14d90ce320","order_by":1,"name":"Yang Shi","email":"","orcid":"","institution":"Changchun University of Finance and Economics","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Yang","middleName":"","lastName":"Shi","suffix":""},{"id":50196305,"identity":"bca9e727-53d4-4e4a-9f97-4d42cc169c79","order_by":2,"name":"Chengquan Hu","email":"","orcid":"","institution":"Jilin University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Chengquan","middleName":"","lastName":"Hu","suffix":""},{"id":50196306,"identity":"a217be0c-6696-42a1-84ae-77ea793fc688","order_by":3,"name":"Hang Yu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyElEQVRIiWNgGAWjYJCCDwwGEnLy7I2NDz8QqYNxBkOFhbFhz+FmYwnitZypSGy4kd4mwEOMev72M4YNH9skGBtnPmxjkGCwk9NtIKBF4kyOYePMNglmdunEtgcFDMnGZgcIaDGQ4DF/zNsmwcY4O7HdQILhQOI2IrQYNv9tk+BhuHkQRBKrheGMhATDDUYitUicSSts7KmQMDDsSQQGsgERfuFvP7yx4YdBXf189uMPH36osJMjqAXdnaQpHwWjYBSMglGAAwAAnwBBQeGkTg0AAAAASUVORK5CYII=","orcid":"","institution":"Jilin Agricultural University","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Hang","middleName":"","lastName":"Yu","suffix":""}],"badges":[],"createdAt":"2021-08-30 17:25:41","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-858913/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-858913/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":13676783,"identity":"63516cb2-aff3-4af9-92e0-f602331dae33","added_by":"auto","created_at":"2021-09-17 11:32:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":495978,"visible":true,"origin":"","legend":"","description":"","filename":"NucleusImageSegmentation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-858913/v1_covered.pdf"},{"id":13162568,"identity":"5547ffd5-8540-475b-98f3-80922a1c5147","added_by":"auto","created_at":"2021-09-07 20:58:21","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":492422,"visible":true,"origin":"","legend":"","description":"","filename":"NucleusImageSegmentation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-858913/v1_covered.pdf"}],"financialInterests":"","formattedTitle":"Nucleus Image Segmentation Method Based on GAN Network and FCN Model","fulltext":[{"header":"Full Text","content":"This preprint is available for \u003ca href='/article/rs-858913/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e."}],"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":true,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"soft-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"soco","sideBox":"Learn more about [Soft Computing](https://www.springer.com/journal/500)","snPcode":"500","submissionUrl":"https://submission.nature.com/new-submission/500/3","title":"Soft Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Nucleus image, Image segmentation technology, GAN network, FCN model, Fully connected layer convolution, Pixel loss","lastPublishedDoi":"10.21203/rs.3.rs-858913/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-858913/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAiming at the problems of rough edges and low accuracy in processing cell nucleus image segmentation in existing image segmentation methods. A cell nucleus image segmentation technology based on generative adversarial network (GAN) network and fully convolutional network (FCN) model is proposed. First, the FCN model is used to perform preliminary segmentation of the cell nucleus image, in which the fully connected layer convolution and skip connection are used to improve the accuracy of image segmentation. Then, improve the GAN network, introduce splitting branches into the discriminator structure, and combine the GAN network and the splitting network into one. At the same time, pixel loss is introduced in the generator to obtain a nucleus image that is visually more similar to the real image. Finally, the segmented image output by the FCN model is used as the input of the GAN network to achieve high-precision segmentation of the nucleus image. The proposed method is experimentally demonstrated based on the 2018 data science bowl dataset. The results show that it can achieve rapid convergence, and the mean intersection over union (MIoU) is 85.34%, which is better than other comparison methods.\u003c/p\u003e","manuscriptTitle":"Nucleus Image Segmentation Method Based on GAN Network and FCN Model","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2021-09-07 20:58:15","doi":"10.21203/rs.3.rs-858913/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2021-09-05T10:25:16+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2021-09-04T17:41:18+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2021-08-31T02:30:56+00:00","index":"","fulltext":""},{"type":"submitted","content":"Soft Computing","date":"2021-08-29T09:53:44+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"soft-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"soco","sideBox":"Learn more about [Soft Computing](https://www.springer.com/journal/500)","snPcode":"500","submissionUrl":"https://submission.nature.com/new-submission/500/3","title":"Soft Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"8a190d28-d686-4a3a-a220-e261a6ad3cb0","owner":[],"postedDate":"September 7th, 2021","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":7002959,"name":"Geometry"},{"id":7002960,"name":"Topology"},{"id":7002961,"name":"Theoretical Computer Science"}],"tags":[],"updatedAt":"2021-10-18T10:58:49+00:00","versionOfRecord":[],"versionCreatedAt":"2021-09-07 20:58:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-858913","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-858913","identity":"rs-858913","version":["v1"]},"buildId":"7rjqhiLT3MXkJMwkYKINL","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}