WITHDRAWN: Hybrid Attention U-Net++ with EfficientNet-B3 Encoder for Automatic Polyp Segmentation in Colonoscopy Images

preprint OA: closed
Full text JSON View at publisher

Abstract

Abstract CRC is ranked among the most common and deadly cancer in all parts of the globe and early identification of colorectal polyps is an essential stage in the prevention of malignant transformation. Yet, there are cases that the human eye in colonoscopy is subjective and prone to error, and thus missed areas of polyps are diagnosed. In this effort, I introduce a hybrid deep learning model, which combines EfficientNet-B3 encoder with U-Net+ decoder, efficiently scaled by spatial and channel squeeze-and-excitation (SCSE) attention that is effective in polyp segmentation. A custom hybrid Dice loss based on the binary Cross-Entropy loss is used to train the model and maximize the pixel-level accuracy as well as overlap between regions. The publicly available Kvasir-SEG data (1,000 colonoscopy images with expert-represented masks) was experimented with. It was demonstrated that the proposed model attained a Dice coefficient of 0.90 and Intersection over union (IoU) of 0.84, which is better than traditional U-Net variants. Such findings suggest that EfficientNet-B3 U-Net++ hybrid is a promising model to improve the boundaries of polyp and has the strong potential to be applied in practice in real-time in computer-aided diagnostic systems to assist clinicians in detecting a case of colorectal cancer in its initial stages.
Full text 9,023 characters · extracted from preprint-html · click to expand
WITHDRAWN: Hybrid Attention U-Net++ with EfficientNet-B3 Encoder for Automatic Polyp Segmentation in Colonoscopy Images | Research Square window.SnipcartSettings = {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 WITHDRAWN: Hybrid Attention U-Net++ with EfficientNet-B3 Encoder for Automatic Polyp Segmentation in Colonoscopy Images Aliya Tabassum Mohammad, Parish Venkata Kumar K This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8420839/v2 This work is licensed under a CC BY 4.0 License Status: Posted Version 2 posted You are reading this latest preprint version Show more versions Editorial Note The full text of this preprint has been withdrawn by the authors as it was submitted and made public without the full consent of all the authors. Therefore, the authors do not wish this work to be cited as a reference. Questions should be directed to the corresponding author. Editorial notes are used to provide important context regarding the topic of a preprint or to alert readers to potential issues concerning that preprint or a downstream publication associated with it. For more information on editorial notes, see our Editorial Policies . Abstract The full text of this preprint has been withdrawn by the authors as it was submitted and made public without the full consent of all the authors. Therefore, the authors do not wish this work to be cited as a reference. Questions should be directed to the corresponding author. Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 2 posted You are reading this latest preprint version Show more versions 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-8420839","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":575788452,"identity":"2c959dae-3ddf-44dc-80f0-c7df4a869e7d","order_by":0,"name":"Aliya Tabassum Mohammad","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEUlEQVRIiWNgGAWjYDACdsYGEJUA5TLLgcgDD/BpYQZpSUBoMQZrScClHKwGYgdcSyKKpdgAfzNzm8TPH3Z5/P3Hn0ndzLFOnx92+CHQFjs53QbsWiQOM7ZJ9iQkF0vcyDGTzt2WnrvxdpoBUEuysdkBHNYAtUjwJADdc4OHDajlcO7G2QkgLQcSt+HQIg+y5U9CfeL888efgbSkG85O/4BXiwFQizRPwuHEDQcSQA47nCAvnYPfFsPDjM3WMmnHiw1v5BhbA/1iuEE6p+BAggFuv8gdb394841NdZ7c+eMPb+dus5aXn52++cOHCjs5nN5nYGCRQHUqWKUBTuUgwPwBhSvfgFf1KBgFo2AUjEAAAHYlZKmN0o1sAAAAAElFTkSuQmCC","orcid":"","institution":"Siddhartha Academy Of Higher Education (Deemed to be University)","correspondingAuthor":true,"prefix":"","firstName":"Aliya","middleName":"Tabassum","lastName":"Mohammad","suffix":""},{"id":575788453,"identity":"6843b492-e229-4552-ad38-8fac1c1848c4","order_by":1,"name":"Parish Venkata Kumar K","email":"","orcid":"","institution":"Siddhartha Academy Of Higher Education (Deemed to be University)","correspondingAuthor":false,"prefix":"","firstName":"Parish","middleName":"Venkata Kumar","lastName":"K","suffix":""}],"badges":[],"createdAt":"2025-12-22 04:38:11","currentVersionCode":2,"declarations":"","doi":"10.21203/rs.3.rs-8420839/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-8420839/v2","draftVersion":[],"editorialEvents":[],"editorialNote":"The full text of this preprint has been withdrawn by the authors as it was submitted and made public without the full consent of all the authors. Therefore, the authors do not wish this work to be cited as a reference. Questions should be directed to the corresponding author.","failedWorkflow":false,"files":[],"financialInterests":"No competing interests reported.","formattedTitle":"WITHDRAWN: Hybrid Attention U-Net++ with EfficientNet-B3 Encoder for Automatic Polyp Segmentation in Colonoscopy Images","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":true,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":false,"isWithdrawnOrRetracted":true,"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":"","lastPublishedDoi":"10.21203/rs.3.rs-8420839/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8420839/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The full text of this preprint has been withdrawn by the authors as it was submitted and made public without the full consent of all the authors. Therefore, the authors do not wish this work to be cited as a reference. Questions should be directed to the corresponding author.","manuscriptTitle":"WITHDRAWN: Hybrid Attention U-Net++ with EfficientNet-B3 Encoder for Automatic Polyp Segmentation in Colonoscopy Images","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2026-01-16 18:30:21","doi":"10.21203/rs.3.rs-8420839/v2","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}},{"code":1,"date":"2025-12-30 06:02:06","doi":"10.21203/rs.3.rs-8420839/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":"09bca0d0-0315-4667-8981-078925579e3c","owner":[],"postedDate":"January 16th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-16T18:30:21+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-16 18:30:21","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v2","identity":"rs-8420839","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8420839","identity":"rs-8420839","version":["v2"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00