A Self-Attention Mechanism Neural Network for Detection and Diagnosis of COVID-19 from Chest X-Ray Images

A Self-Attention Mechanism Neural Network for Detection and Diagnosis of COVID-19 from Chest X-Ray 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 A Self-Attention Mechanism Neural Network for Detection and Diagnosis of COVID-19 from Chest X-Ray Images Bo Cheng, Wei Xiang, Ruhui Xue, Hang Yang, Laili Zhu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-577494/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 The new type of coronavirus is called COVID-19. The virus can cause respiratory diseases, accompanied by cough, fever, difficulty breathing, and in severe cases, it can also cause symptoms such as pneumonia. It began to spread at the end of 2019 and has now spread to all parts of the world. The limited test kits and increasing number of cases encourage us to propose a deep learning model that can help radiologists and clinicians use chest X-rays to detect COVID-19 cases and show the diagnostic features of pneumonia. In this study, our methods are: 1) Propose a data enhancement method to increase the diversity of the data set, thereby improving the generalization performance of the network. 2) Using the deep convolutional neural network model DPN-SE, an attention mechanism is added on the basis of the DPN network, which greatly improves the performance of the network. 3) Use the lime interpretable library to mark the X-ray, the characteristic area on the medical image that is helpful for the doctor to make a diagnosis. The model we proposed can obtain better results with the least amount of data preprocessing given limited data. In general, the proposed method and model can effectively become a very useful tool for clinical practitioners and radiologists. Artificial Intelligence and Machine Learning Computational Biology coronavirus respiratory diseases radiologists medical image Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 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-577494","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":32493525,"identity":"0cb1a849-930a-4695-a5d4-f3b205736517","order_by":0,"name":"Bo Cheng","email":"","orcid":"","institution":"Southwest Minzu University","correspondingAuthor":false,"prefix":"","firstName":"Bo","middleName":"","lastName":"Cheng","suffix":""},{"id":32493526,"identity":"da2e2338-3a11-4118-aaa2-7fd9b172392b","order_by":1,"name":"Wei Xiang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4UlEQVRIiWNgGAWjYBACfmb+BwcSDGzk+KECjA2EtEi28zA++FCRZizZQKwWg/M8zIYzzhxK3HCAWC0Mh3mPSfO2HTA2Pn/GTLqAwUZ2wwHmZw/w6WBs5ksDarkjZ3Yjx0x6BkOa8YYDbOYG+LQwMzOYAbU8Mza7wbtNmofhMNCFPGwS+LSwQbQcTtzcfxak5T9hLTzMPMZA7wMNZ8gFaTlAWIsEM1siOJAlbuR/tuYxSDaeeZjNDK8W+/OHD0Cisv9Y4m2eCjvZvuPNz/BqQQOgoGImQf0oGAWjYBSMAuwAAB6cSA2aYKMWAAAAAElFTkSuQmCC","orcid":"","institution":"Southwest Minzu University","correspondingAuthor":true,"prefix":"","firstName":"Wei","middleName":"","lastName":"Xiang","suffix":""},{"id":32493527,"identity":"b891d356-bbee-4bf9-ac70-91e197d1c8f8","order_by":2,"name":"Ruhui Xue","email":"","orcid":"","institution":"Southwest Minzu University","correspondingAuthor":false,"prefix":"","firstName":"Ruhui","middleName":"","lastName":"Xue","suffix":""},{"id":32493528,"identity":"781ac759-372b-4dd4-b2d7-6d7bb585c97a","order_by":3,"name":"Hang Yang","email":"","orcid":"","institution":"Southwest Minzu University","correspondingAuthor":false,"prefix":"","firstName":"Hang","middleName":"","lastName":"Yang","suffix":""},{"id":32493529,"identity":"46d2fb58-527a-4a7f-af3b-97ce39fa3e20","order_by":4,"name":"Laili Zhu","email":"","orcid":"","institution":"Southwest Minzu University","correspondingAuthor":false,"prefix":"","firstName":"Laili","middleName":"","lastName":"Zhu","suffix":""}],"badges":[],"createdAt":"2021-05-31 15:14:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-577494/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-577494/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":10360431,"identity":"e37229cd-286f-4d7d-93e0-977c36ca0d76","added_by":"auto","created_at":"2021-06-14 22:11:19","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":565343,"visible":true,"origin":"","legend":"Overview of the Data Augmentation. Step1: Scale the narrow side of the image to size 224; Step2: Randomly\ntailoring a picture of size [224, 224] from an image of [224, n] or [n,224]; Setp3: The [224, 224] size picture is processed by\naffine transformation: flip, rotate, scale.","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-577494/v1/f8352bd41ef5c6913c6e7ba1.png"},{"id":10360434,"identity":"bffabdf6-7da3-4500-98fe-0b165aa64f11","added_by":"auto","created_at":"2021-06-14 22:11:19","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":225117,"visible":true,"origin":"","legend":"Network overall framework diagram","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-577494/v1/d6a6c5aa5db37531864b6325.png"},{"id":10360430,"identity":"7844bbae-738f-411e-bcc2-9db7af52192d","added_by":"auto","created_at":"2021-06-14 22:11:19","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":438933,"visible":true,"origin":"","legend":"Network overall framework diagram","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-577494/v1/47345a4ef3f13bd7455bb852.png"},{"id":10360382,"identity":"cc903017-7aa4-49c5-a0b1-d48f6f53ec79","added_by":"auto","created_at":"2021-06-14 22:08:19","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":239163,"visible":true,"origin":"","legend":"Schematic diagram of a four-level tripod-type atomic system driven by three coherent laser fields.","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-577494/v1/921f9ec1b764e9a9321a0ce1.png"},{"id":10360432,"identity":"295e285b-0451-4dae-8bb4-4f18c55f856f","added_by":"auto","created_at":"2021-06-14 22:11:19","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":933384,"visible":true,"origin":"","legend":"Types of lung X-ray images","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-577494/v1/9edac61b5a50a266aeae6e89.png"},{"id":10360387,"identity":"2d3bc8fd-bf6e-4347-af36-cce6201fd412","added_by":"auto","created_at":"2021-06-14 22:08:19","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":210889,"visible":true,"origin":"","legend":"(a) the results of DPNNet network model training (b) the results of DPNN-SE network model training.","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-577494/v1/cea87ff782e8b5372fc80c6a.png"},{"id":10360433,"identity":"66213969-e599-42df-acd5-6f72f66e9027","added_by":"auto","created_at":"2021-06-14 22:11:19","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":768806,"visible":true,"origin":"","legend":"Examples of COVID-19 model activation maps.","description":"","filename":"7.png","url":"https://assets-eu.researchsquare.com/files/rs-577494/v1/dea90ecd5904b93e99dd985b.png"},{"id":13646039,"identity":"0b225e97-82c4-4ece-8510-625f76055a65","added_by":"auto","created_at":"2021-09-17 09:22:20","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1017183,"visible":true,"origin":"","legend":"","description":"","filename":"mymain.pdf","url":"https://assets-eu.researchsquare.com/files/rs-577494/v1_covered.pdf"},{"id":10360943,"identity":"ec9a14a3-f30b-422f-a9df-cbca3b7c3790","added_by":"auto","created_at":"2021-06-14 22:14:27","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1013527,"visible":true,"origin":"","legend":"","description":"","filename":"mymain.pdf","url":"https://assets-eu.researchsquare.com/files/rs-577494/v1_covered.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eA Self-Attention Mechanism Neural Network for Detection and Diagnosis of COVID-19 from Chest X-Ray Images\u003c/p\u003e","fulltext":[{"header":"Full Text","content":"This preprint is available for \u003ca href='/article/rs-577494/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e."}],"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":false,"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":"coronavirus, respiratory diseases, radiologists, medical image","lastPublishedDoi":"10.21203/rs.3.rs-577494/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-577494/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The new type of coronavirus is called COVID-19. The virus can cause respiratory diseases, accompanied by cough, fever, difficulty breathing, and in severe cases, it can also cause symptoms such as pneumonia. It began to spread at the end of 2019 and has now spread to all parts of the world. The limited test kits and increasing number of cases encourage us to propose a deep learning model that can help radiologists and clinicians use chest X-rays to detect COVID-19 cases and show the diagnostic features of pneumonia. In this study, our methods are: 1) Propose a data enhancement method to increase the diversity of the data set, thereby improving the generalization performance of the network. 2) Using the deep convolutional neural network model DPN-SE, an attention mechanism is added on the basis of the DPN network, which greatly improves the performance of the network. 3) Use the lime interpretable library to mark the X-ray, the characteristic area on the medical image that is helpful for the doctor to make a diagnosis. The model we proposed can obtain better results with the least amount of data preprocessing given limited data. In general, the proposed method and model can effectively become a very useful tool for clinical practitioners and radiologists.","manuscriptTitle":"A Self-Attention Mechanism Neural Network for Detection and Diagnosis of COVID-19 from Chest X-Ray Images","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2021-06-14 22:08:17","doi":"10.21203/rs.3.rs-577494/v1","editorialEvents":[{"type":"communityComments","content":1}],"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":"69f0e533-4aeb-4792-9afd-2fd22dbfeaf0","owner":[],"postedDate":"June 14th, 2021","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":5023276,"name":"Artificial Intelligence and Machine Learning"},{"id":5023277,"name":"Computational Biology"}],"tags":[],"updatedAt":"2021-09-02T05:14:10+00:00","versionOfRecord":[],"versionCreatedAt":"2021-06-14 22:08:17","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-577494","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-577494","identity":"rs-577494","version":["v1"]},"buildId":"_2-kVJe1T_tPrBINL-cwx","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}