HAHNet: A convolutional neural network for HER2 status classification of breast cancer

HAHNet: A convolutional neural network for HER2 status classification of breast cancer | 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 Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article HAHNet: A convolutional neural network for HER2 status classification of breast cancer Jiahao Wang, Xiaodong Zhu, Kai Chen, Lei Hao, Yuanning Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2841300/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 20 Sep, 2023 Read the published version in BMC Bioinformatics → Version 1 posted 8 You are reading this latest preprint version Abstract Background : Breast cancer is a major health problem for women. Human epidermal growth factor receptor-2 (HER2) is a very important diagnostic and prognostic factor for breast cancer, and HER2 status classification is essential for the development of treatment plans for breast cancer. Generally speaking, pathologists will adopt immunohistochemistry (IHC) to assess HER2 status, which requires additional economic costs. Furthermore, the manual assessment of HER2 status is time-consuming and error-prone. In recent years, deep learning has been widely used in medical field and has attained great achievements. However, the existing deep learning methods for HER2 status classification of conventional hematoxylin and eosin (H&E) stained images are not accurate enough. Results : To address these problems, a neural network model named HAHNet is proposed in this paper. HAHNet combines multi-scale features with attention mechanisms, which is able to directly classify HER2 status of H&E stained histological images of breast cancer. Typically, the HAHNet network mainly includes convolution preprocessing, attention mechanism, downsampling, and multi-scale feature extraction. The experimental results show that HAHNet outperforms other existing methods with regard to six metrics of Accuracy, Sensitivity, Precision, F-score, MCC, and AUC. Conclusions : Collectively, the above experiments demonstrate that our proposed HAHNet achieves high performance in classifying the HER2 status of breast cancer using only H&E stained samples, which can be used in case classification and helps to reduce the cost required for diagnosis. Breast cancer HER2 Deep learning HAHNet Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 20 Sep, 2023 Read the published version in BMC Bioinformatics → Version 1 posted Editorial decision: Major revision 15 Jun, 2023 Reviews received at journal 02 Jun, 2023 Reviewers agreed at journal 17 May, 2023 Reviewers invited by journal 17 May, 2023 Editor assigned by journal 16 May, 2023 Editor invited by journal 16 May, 2023 Submission checks completed at journal 16 May, 2023 First submitted to journal 20 Apr, 2023 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 In Review Editorial Policies 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-2841300","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":200846979,"identity":"8ca81e66-58ce-4b6b-9097-bdbb72dc9d9b","order_by":0,"name":"Jiahao Wang","email":"","orcid":"","institution":"Jilin University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jiahao","middleName":"","lastName":"Wang","suffix":""},{"id":200846983,"identity":"c49d1737-20da-4600-aa31-00b6d8da40c1","order_by":1,"name":"Xiaodong Zhu","email":"","orcid":"","institution":"Jilin University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Xiaodong","middleName":"","lastName":"Zhu","suffix":""},{"id":200846986,"identity":"641132fa-c282-4651-b653-20889bf5aaa7","order_by":2,"name":"Kai Chen","email":"","orcid":"","institution":"Jilin University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Kai","middleName":"","lastName":"Chen","suffix":""},{"id":200846989,"identity":"0ae715fb-8069-408d-a2ac-dd9c92aa4226","order_by":3,"name":"Lei Hao","email":"","orcid":"","institution":"Jilin University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Lei","middleName":"","lastName":"Hao","suffix":""},{"id":200846992,"identity":"9fc21eb4-91b7-4379-975a-5dc4215849ec","order_by":4,"name":"Yuanning Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAr0lEQVRIiWNgGAWjYBACPmYQWcEmA6IkiNLCBtZyho2HBC0ggrGNgRQt7Dxm0oXz+HgMDjAfvM3DYJdHhMOAWmZuYwNqYUu25mFILiZOCy9YC5DBw3AgsYE4LXNAWvi/kaKlAWwLG7Fa2IqteY6x8UgeZjO2nGOQTFgLP//hjbd5ao7J8R1vfnjjTYUdYS1AwAKMjmMMDOA4NSBCPRAwf2BgqCFO6SgYBaNgFIxMAADHTSldD942EgAAAABJRU5ErkJggg==","orcid":"","institution":"Jilin University","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Yuanning","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2023-04-20 12:44:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-2841300/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-2841300/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12859-023-05474-y","type":"published","date":"2023-09-20T15:00:34+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":43640288,"identity":"8183ef6f-5daa-430e-8e6a-09ba8f426f12","added_by":"auto","created_at":"2023-09-25 15:03:23","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2143518,"visible":true,"origin":"","legend":"","description":"","filename":"HAHNetAconvolutionalneuralnetworkforHER2statusclassificationofbreastcancer.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2841300/v1_covered_8f7ce925-32ed-42a3-ba33-4c1cfa759605.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"HAHNet: A convolutional neural network for HER2 status classification of breast cancer","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-bioinformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"binf","sideBox":"Learn more about [BMC Bioinformatics](http://bmcbioinformatics.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/binf","title":"BMC Bioinformatics","twitterHandle":"@BMC_Bioinformatics","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Breast cancer, HER2, Deep learning, HAHNet","lastPublishedDoi":"10.21203/rs.3.rs-2841300/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2841300/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground\u003c/strong\u003e: Breast cancer is a major health problem for women. Human\u0026nbsp;epidermal growth factor receptor-2 (HER2) is a very important diagnostic and prognostic factor for breast cancer, and HER2 status classification is essential for the development of\u0026nbsp;treatment plans for breast cancer. Generally speaking,\u0026nbsp;pathologists will adopt\u0026nbsp;immunohistochemistry (IHC) to assess HER2 status, which requires additional economic costs. Furthermore, the manual assessment of HER2 status is time-consuming and error-prone. In recent years, deep learning has been widely used in medical field and has attained\u0026nbsp;great\u0026nbsp;achievements. However,\u0026nbsp;the\u0026nbsp;existing deep learning methods for HER2 status classification of conventional hematoxylin and eosin (H\u0026amp;E) stained images are not accurate enough.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults\u003c/strong\u003e: To address these problems, a neural network model named HAHNet is\u0026nbsp;proposed in this paper. HAHNet combines\u0026nbsp;multi-scale features with\u0026nbsp;attention mechanisms, which is able to\u0026nbsp;directly classify HER2 status of H\u0026amp;E stained histological images of breast cancer. Typically, the HAHNet network mainly includes\u0026nbsp;convolution preprocessing, attention mechanism, downsampling, and multi-scale feature extraction. The experimental results show\u0026nbsp;that HAHNet outperforms\u0026nbsp;other existing methods with regard to\u0026nbsp;six metrics of Accuracy, Sensitivity, Precision, F-score, MCC, and AUC.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusions\u003c/strong\u003e: Collectively, the\u0026nbsp;above\u0026nbsp;experiments demonstrate that our\u0026nbsp;proposed HAHNet achieves\u0026nbsp;high performance in classifying the HER2 status of breast cancer using only H\u0026amp;E stained samples, which can be used in\u0026nbsp;case classification and helps to reduce the cost required for diagnosis.\u003c/p\u003e","manuscriptTitle":"HAHNet: A convolutional neural network for HER2 status classification of breast cancer","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-05-18 07:12:48","doi":"10.21203/rs.3.rs-2841300/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revision","date":"2023-06-15T04:55:41+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2023-06-02T11:23:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"e863fa8d-c98f-4fc3-a0ab-e70368dff5c4","date":"2023-05-18T01:31:11+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2023-05-18T01:00:40+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2023-05-16T06:26:47+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2023-05-16T06:24:35+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2023-05-16T06:22:02+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Bioinformatics","date":"2023-04-20T12:33:36+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-bioinformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"binf","sideBox":"Learn more about [BMC Bioinformatics](http://bmcbioinformatics.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/binf","title":"BMC Bioinformatics","twitterHandle":"@BMC_Bioinformatics","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"49f81aad-2c45-4b41-9d2b-8e795ecaf4e9","owner":[],"postedDate":"May 18th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2023-09-25T15:02:15+00:00","versionOfRecord":{"articleIdentity":"rs-2841300","link":"https://doi.org/10.1186/s12859-023-05474-y","journal":{"identity":"bmc-bioinformatics","isVorOnly":false,"title":"BMC Bioinformatics"},"publishedOn":"2023-09-20 15:00:34","publishedOnDateReadable":"September 20th, 2023"},"versionCreatedAt":"2023-05-18 07:12:48","video":"","vorDoi":"10.1186/s12859-023-05474-y","vorDoiUrl":"https://doi.org/10.1186/s12859-023-05474-y","workflowStages":[]},"version":"v1","identity":"rs-2841300","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2841300","identity":"rs-2841300","version":["v1"]},"buildId":"pf3fE39SIOqb-0xH_OWvX","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}