Fovea-UNet: Detection and Segmentation of Lymph Node Metastases in Colorectal Cancers with Deep Learning

Fovea-UNet: Detection and Segmentation of Lymph Node Metastases in Colorectal Cancers with Deep Learning | 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 Fovea-UNet: Detection and Segmentation of Lymph Node Metastases in Colorectal Cancers with Deep Learning Yajiao Liu, Jiang Wang, Chenpeng Wu, Liyun Liu, Zhiyong Zhang, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2813343/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 Objective: Colorectal cancer is one of the most serious malignant tumors, and lymph node metastasis (LNM) from colorectal cancer is a major factor for patient management and prognosis. Accurate image detection of LNM is an important task to help pathologists diagnose cancer. However, effective image detection with the whole slide image (WSI) can only be performed by patch-based classification method, which are far from enough for cancer region segmentation and location due to a small patch image has less non-local contextual information. Recently, the U-Net architecture has been widely used to segment image to accomplish more precise cancer diagnosis. In this work, we aggregate the detailed and non-local contextual information into a U-Net baseline to segment the important region with high diagnostic value. Method: Inspired by the working principle of Fovea in visual neuroscience, a novel network framework based on U-Net for cancer segmentation named Fovea-UNet is proposed to adaptively adjust the resolution according to the importance-aware of information and selectively focuses on the region most relevant to colorectal LNM. Specifically, we design an effective adaptively optimized pooling operation called Fovea Pooling (FP), which dynamically aggregate the detailed and non-local contextual information according to pixel-level feature importance. In addition, the improved lightweight backbone network based on GhostNet is adopted to reduce the computational cost caused by FP pooling. Results & Conclusions: Experimental results show that our proposed framework can achieve higher performance than other state-of-the-art segmentation networks with 92.82% sensitivity and 88.51% F1 score on the LNM dataset. Clinical impact: The proposed framework can provide a valid tool for cancer diagnosis, especially for LNM of colorectal cancer. medical image segmentation colorectal cancer fovea in human retina adaptive resolution feature importance-aware attention mechanism lightweight backbone network 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-2813343","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":192457821,"identity":"1e422034-38ae-45f4-9ee9-db7c38dc58ef","order_by":0,"name":"Yajiao Liu","email":"","orcid":"","institution":"Tianjin University","correspondingAuthor":false,"prefix":"","firstName":"Yajiao","middleName":"","lastName":"Liu","suffix":""},{"id":192457822,"identity":"72185e19-6f31-491e-b4a3-936d049ec409","order_by":1,"name":"Jiang Wang","email":"","orcid":"","institution":"Tianjin University","correspondingAuthor":false,"prefix":"","firstName":"Jiang","middleName":"","lastName":"Wang","suffix":""},{"id":192457823,"identity":"0d5d76d6-f43d-4ce8-bf65-d94863bd2cdb","order_by":2,"name":"Chenpeng Wu","email":"","orcid":"","institution":"Tangshan Gongren Hospital","correspondingAuthor":false,"prefix":"","firstName":"Chenpeng","middleName":"","lastName":"Wu","suffix":""},{"id":192457824,"identity":"86ead076-8ae1-4ec1-9558-582cdad52012","order_by":3,"name":"Liyun Liu","email":"","orcid":"","institution":"Tangshan Gongren Hospital","correspondingAuthor":false,"prefix":"","firstName":"Liyun","middleName":"","lastName":"Liu","suffix":""},{"id":192457825,"identity":"f51c1550-5e3e-4fcd-af6f-abc65df9bda6","order_by":4,"name":"Zhiyong Zhang","email":"","orcid":"","institution":"Tangshan Gongren Hospital","correspondingAuthor":false,"prefix":"","firstName":"Zhiyong","middleName":"","lastName":"Zhang","suffix":""},{"id":192457826,"identity":"a19dadc0-8781-4555-93b5-4d5458b4454a","order_by":5,"name":"Haitao Yu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAqUlEQVRIiWNgGAWjYBACAxDxgYENziZCC1Ax44wEUrUw8yQgbCQMzOV7zKRtf/AlNrA3b5NgqLlDWItlG4+ZdE4CW2IDz7EyCYZjz4hw2DGYFokcMwnGhsNEarEAaZF/Q4oWBrAtPERrSSu27EljM27jSSu2SDhGjJbDhzfe+GFzTLafHcj4UEOEFgYGDlB0HIPEfwIxGhgY2B8AiRri1I6CUTAKRsHIBACfcDI7S7ohWAAAAABJRU5ErkJggg==","orcid":"","institution":"Tianjin University","correspondingAuthor":true,"prefix":"","firstName":"Haitao","middleName":"","lastName":"Yu","suffix":""}],"badges":[],"createdAt":"2023-04-13 14:14:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-2813343/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-2813343/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":36012127,"identity":"7cb774a7-b323-49de-ac8f-1bee3807b37a","added_by":"auto","created_at":"2023-04-19 15:37:30","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1047189,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2813343/v1_covered.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Fovea-UNet: Detection and Segmentation of Lymph Node Metastases in Colorectal Cancers with Deep Learning","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":"medical image segmentation, colorectal cancer, fovea in human retina, adaptive resolution, feature importance-aware, attention mechanism, lightweight backbone network","lastPublishedDoi":"10.21203/rs.3.rs-2813343/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2813343/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eObjective:\u003c/strong\u003e Colorectal cancer is one of the most serious malignant tumors, and lymph node metastasis (LNM) from colorectal cancer is a major factor for patient management and prognosis. Accurate image detection of LNM is an important task to help pathologists diagnose cancer. However, effective image detection with the whole slide image (WSI) can only be performed by patch-based classification method, which are far from enough for cancer region segmentation and location due to a small patch image has less non-local contextual information. Recently, the U-Net architecture has been widely used to segment image to accomplish more precise cancer diagnosis. In this work, we aggregate the detailed and non-local contextual information into a U-Net baseline to segment the important region with high diagnostic value.\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethod: \u003c/strong\u003eInspired by the working principle of Fovea in visual neuroscience, a novel network framework based on U-Net for cancer segmentation named Fovea-UNet is proposed to adaptively adjust the resolution according to the importance-aware of information and selectively focuses on the region most relevant to colorectal LNM. Specifically, we design an effective adaptively optimized pooling operation called Fovea Pooling (FP), which dynamically aggregate the detailed and non-local contextual information according to pixel-level feature importance. In addition, the improved lightweight backbone network based on GhostNet is adopted to reduce the computational cost caused by FP pooling.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults \u0026amp; Conclusions:\u003c/strong\u003e Experimental results show that our proposed framework can achieve higher performance than other state-of-the-art segmentation networks with 92.82% sensitivity and 88.51% F1 score on the LNM dataset.\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eClinical impact:\u003c/strong\u003e The proposed framework can provide a valid tool for cancer diagnosis, especially for LNM of colorectal cancer.\u003c/p\u003e","manuscriptTitle":"Fovea-UNet: Detection and Segmentation of Lymph Node Metastases in Colorectal Cancers with Deep Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-04-19 15:37:12","doi":"10.21203/rs.3.rs-2813343/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":"0c40ff83-eb25-4e83-82f7-29d2bc3a9e68","owner":[],"postedDate":"April 19th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2023-04-19T15:37:15+00:00","versionOfRecord":[],"versionCreatedAt":"2023-04-19 15:37:12","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-2813343","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2813343","identity":"rs-2813343","version":["v1"]},"buildId":"J0_U0BvcaRcwD8yVFaRlm","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}