An Ultrasound Image Segmentation Method for Thyroid Nodules Based on Dual-Path Attention Mechanism-Enhanced UNet++

An Ultrasound Image Segmentation Method for Thyroid Nodules Based on Dual-Path Attention Mechanism-Enhanced UNet++ | 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 An Ultrasound Image Segmentation Method for Thyroid Nodules Based on Dual-Path Attention Mechanism-Enhanced UNet++ Peizhen Dong, Ronghua Zhang, Jun Li, Changzheng Liu, Wen Liu, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4791835/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 18 Dec, 2024 Read the published version in BMC Medical Imaging → Version 1 posted 16 You are reading this latest preprint version Abstract Purpose: This study aims to design an auxiliary segmentation model for thyroid nodules to increase diagnostic accuracy and efficiency, thereby reducing the workload of medical personnel. Methods: This study proposes a Dual-Path Attention Mechanism (DPAM)-UNet++ model, which can automatically segment thyroid nodules in ultrasound images. Specifically, the model incorporates dual-path attention modules into the skip connections of the UNet++ network to capture global contextual information in feature maps. The model's performance was evaluated using Intersection over Union (IoU), F1_score, accuracy, etc. Additionally, a new integrated loss function was designed for the DPAM-UNet++ network. Results: Comparative experiments with classical segmentation models revealed that the DPAM-UNet++ model achieved an IoU of 0.7451, an F1_score of 0.8310, an accuracy of 0.9718, a precision of 0.8443, a recall of 0.8702, an Area Under Curve (AUC) of 0.9213, and an HD95 of 35.31. Except for the precision metric, this model outperformed the other models on all the indicators and achieved a segmentation effect that was more similar to that of the ground truth labels. Additionally, ablation experiments verified the effectiveness and necessity of the dual-path attention mechanism and the integrated loss function. Conclusion: The segmentation model proposed in this study can effectively capture global contextual information in ultrasound images and accurately identify the locations of nodule areas. The model yields excellent segmentation results, especially for small and multiple nodules. Additionally, the integrated loss function improves the segmentation of nodule edges, enhancing the model’s accuracy in segmenting edge details. Thyroid nodules deep learning auxiliary diagnosis ultrasound Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 18 Dec, 2024 Read the published version in BMC Medical Imaging → Version 1 posted Editorial decision: Revision requested 16 Sep, 2024 Reviews received at journal 08 Sep, 2024 Reviews received at journal 08 Sep, 2024 Reviews received at journal 08 Sep, 2024 Reviewers agreed at journal 08 Sep, 2024 Reviewers agreed at journal 08 Sep, 2024 Reviewers agreed at journal 08 Sep, 2024 Reviews received at journal 10 Aug, 2024 Reviews received at journal 31 Jul, 2024 Reviewers agreed at journal 31 Jul, 2024 Reviewers agreed at journal 30 Jul, 2024 Reviewers invited by journal 30 Jul, 2024 Editor invited by journal 30 Jul, 2024 Editor assigned by journal 30 Jul, 2024 Submission checks completed at journal 30 Jul, 2024 First submitted to journal 23 Jul, 2024 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-4791835","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":344535007,"identity":"fcfe20e7-e05c-44cd-9ae9-26a1a9c526fd","order_by":0,"name":"Peizhen Dong","email":"","orcid":"","institution":"College of Information Science and Technology,Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Peizhen","middleName":"","lastName":"Dong","suffix":""},{"id":344535008,"identity":"32eda353-5131-4fbe-881b-a82331d7028c","order_by":1,"name":"Ronghua Zhang","email":"","orcid":"","institution":"College of Information Science and Technology,Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Ronghua","middleName":"","lastName":"Zhang","suffix":""},{"id":344535009,"identity":"a280c514-41c9-47fe-bf94-9d4883197317","order_by":2,"name":"Jun Li","email":"","orcid":"","institution":"Department of Medical Ultrasound, The First Affiliated Hospital of Medical College, Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Jun","middleName":"","lastName":"Li","suffix":""},{"id":344535010,"identity":"79288bba-dd7b-48dc-908d-db3c7497875b","order_by":3,"name":"Changzheng Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAt0lEQVRIiWNgGAWjYBACPmYQWcGQAObxEKOFDazlDElaQARjG0la2HkMP/6cV5cnPyOB8cHbNgZ5c8IO4zGWkNx2uJhxRgKz4dw2BsOdDYS1mDEYbjuQ2CyRwCbNC3ShwQFitCTOqUtsk0hg/028loMNzIk9QFuYidTCVizZcOxw4gyeh82Sc85JGG4gpIWf//DGjz9q6hLntycf/PCmzEaeoC1IgLEBSEgQr34UjIJRMApGAW4AAMKLNKm8gXYxAAAAAElFTkSuQmCC","orcid":"","institution":"College of Information Science and Technology,Shihezi University","correspondingAuthor":true,"prefix":"","firstName":"Changzheng","middleName":"","lastName":"Liu","suffix":""},{"id":344535011,"identity":"3e8ea622-3191-4920-8ad0-57ec48945d20","order_by":4,"name":"Wen Liu","email":"","orcid":"","institution":"Department of Medical Ultrasound, The First Affiliated Hospital of Medical College, Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Wen","middleName":"","lastName":"Liu","suffix":""},{"id":344535012,"identity":"f48f8d3a-770f-416c-88ca-ff1ba8673ff9","order_by":5,"name":"Jiale Hu","email":"","orcid":"","institution":"College of Information Science and Technology,Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Jiale","middleName":"","lastName":"Hu","suffix":""},{"id":344535013,"identity":"a5138b9f-745e-4954-b8fe-8dfc9836197d","order_by":6,"name":"Yongqiang Yang","email":"","orcid":"","institution":"College of Information Science and Technology,Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Yongqiang","middleName":"","lastName":"Yang","suffix":""},{"id":344535014,"identity":"2cd310fa-609b-43ba-9255-fff99d3c88da","order_by":7,"name":"Xiang Li","email":"","orcid":"","institution":"College of Information Science and Technology,Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Xiang","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2024-07-24 02:38:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4791835/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4791835/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12880-024-01521-z","type":"published","date":"2024-12-18T15:57:33+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":72201828,"identity":"290bb5cf-f5c2-4fe3-8e41-b1071e1029e8","added_by":"auto","created_at":"2024-12-23 16:10:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1360974,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4791835/v1_covered_24109325-bb6a-4d5a-8208-edbc365b38e3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An Ultrasound Image Segmentation Method for Thyroid Nodules Based on Dual-Path Attention Mechanism-Enhanced UNet++","fulltext":[],"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":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-imaging","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmim","sideBox":"Learn more about [BMC Medical Imaging](http://bmcmedimaging.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bmim/default.aspx","title":"BMC Medical Imaging","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Thyroid nodules, deep learning, auxiliary diagnosis, ultrasound","lastPublishedDoi":"10.21203/rs.3.rs-4791835/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4791835/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Purpose: This study aims to design an auxiliary segmentation model for thyroid nodules to increase diagnostic accuracy and efficiency, thereby reducing the workload of medical personnel.\nMethods: This study proposes a Dual-Path Attention Mechanism (DPAM)-UNet++ model, which can automatically segment thyroid nodules in ultrasound images. Specifically, the model incorporates dual-path attention modules into the skip connections of the UNet++ network to capture global contextual information in feature maps. The model's performance was evaluated using Intersection over Union (IoU), F1_score, accuracy, etc. Additionally, a new integrated loss function was designed for the DPAM-UNet++ network.\nResults: Comparative experiments with classical segmentation models revealed that the DPAM-UNet++ model achieved an IoU of 0.7451, an F1_score of 0.8310, an accuracy of 0.9718, a precision of 0.8443, a recall of 0.8702, an Area Under Curve (AUC) of 0.9213, and an HD95 of 35.31. Except for the precision metric, this model outperformed the other models on all the indicators and achieved a segmentation effect that was more similar to that of the ground truth labels. Additionally, ablation experiments verified the effectiveness and necessity of the dual-path attention mechanism and the integrated loss function.\nConclusion: The segmentation model proposed in this study can effectively capture global contextual information in ultrasound images and accurately identify the locations of nodule areas. The model yields excellent segmentation results, especially for small and multiple nodules. Additionally, the integrated loss function improves the segmentation of nodule edges, enhancing the model’s accuracy in segmenting edge details.","manuscriptTitle":"An Ultrasound Image Segmentation Method for Thyroid Nodules Based on Dual-Path Attention Mechanism-Enhanced UNet++","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-26 06:09:17","doi":"10.21203/rs.3.rs-4791835/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-09-16T04:25:55+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-09-08T17:19:00+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-09-08T14:05:14+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-09-08T14:03:11+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"172530438799785431053879777574658858622","date":"2024-09-08T11:19:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"9379781761312130037486949535059025394","date":"2024-09-08T09:15:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"118141364099904689796083681826835162721","date":"2024-09-08T08:45:56+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-08-10T16:32:54+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-07-31T16:45:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"304681114974015089368133479373746445813","date":"2024-07-31T08:59:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"8610041782708566225731873927907031310","date":"2024-07-30T10:12:04+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-07-30T09:59:16+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-07-30T09:33:25+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-07-30T09:29:08+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-07-30T09:28:37+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Imaging","date":"2024-07-24T02:37:15+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-imaging","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmim","sideBox":"Learn more about [BMC Medical Imaging](http://bmcmedimaging.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bmim/default.aspx","title":"BMC Medical Imaging","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"8544373c-e124-4370-85d0-20e21170b0eb","owner":[],"postedDate":"August 26th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-12-23T16:02:22+00:00","versionOfRecord":{"articleIdentity":"rs-4791835","link":"https://doi.org/10.1186/s12880-024-01521-z","journal":{"identity":"bmc-medical-imaging","isVorOnly":false,"title":"BMC Medical Imaging"},"publishedOn":"2024-12-18 15:57:33","publishedOnDateReadable":"December 18th, 2024"},"versionCreatedAt":"2024-08-26 06:09:17","video":"","vorDoi":"10.1186/s12880-024-01521-z","vorDoiUrl":"https://doi.org/10.1186/s12880-024-01521-z","workflowStages":[]},"version":"v1","identity":"rs-4791835","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4791835","identity":"rs-4791835","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}