Deep Learning-Based Dose Prediction for Low-Energy Electron Superficial Radiotherapy

Deep Learning-Based Dose Prediction for Low-Energy Electron Superficial Radiotherapy | 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 Deep Learning-Based Dose Prediction for Low-Energy Electron Superficial Radiotherapy Jialin Huang, Zhitao Dai, Shuai Hu, Yuanchun Ye, Yuling Chen, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4959016/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 Background: Accurate and rapid surface dose calculation is critical in superficiallow-energy electron radiotherapy due to the shallow treatment depth and the riskof radiation-induced skin toxicity. Traditional Monte Carlo (MC) simulations,while precise, can be computationally expensive and time-consuming. Methods: To improve both the accuracy and speed of dose calculations, thisstudy combined MC simulations with deep learning techniques. Low-energy electron beams were simulated for six body sites using DOSXYZnrc, producing CTphantoms and corresponding dose distributions. A cascaded 3D-UNet (C3D) model was trained on these MC simulation datasets to predict dose distributionsrapidly. Results: The C3D model demonstrated a mean absolute percentage error(MAPE) of less than 8% for one-dimensional dose curves, with no significantdifferences found in t-tests. The maximum dose difference observed across different body sites in 2D slices was 0.0421 ± 0.0340. The model achieved an overallGamma pass rate of over 92.09 ± 0.51% within 1%/1mm tolerance, and fordose distribution (DD) analysis under the 1% tolerance, the pass rate was 93.58± 0.21%. Additionally, the C3D model completed dose predictions in just 0.42seconds, making it approximately 140,000 times faster than MC simulations. Conclusion: The integration of deep learning with MC simulations significantlyenhances the efficiency of surface dose calculations in superficial electron radiotherapy. The C3D model provides rapid and accurate dose predictions, facilitatingmore efficient treatment planning while maintaining high accuracy compared totraditional MC methods. Dose prediction Deep learning Monte Carlo simulation Low-energy electron Superficial treatment Radiotherapy 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-4959016","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":356020646,"identity":"d33b35b1-fd4c-4e6e-ae22-232940b1b4b4","order_by":0,"name":"Jialin Huang","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Jialin","middleName":"","lastName":"Huang","suffix":""},{"id":356020647,"identity":"067040aa-0f33-4338-be3a-266b2c71c6a1","order_by":1,"name":"Zhitao Dai","email":"","orcid":"","institution":"Cancer Hospital of Chinese Academy of Medical Sciences","correspondingAuthor":false,"prefix":"","firstName":"Zhitao","middleName":"","lastName":"Dai","suffix":""},{"id":356020648,"identity":"c2390093-8fe0-460e-a098-1b93b35b4fa1","order_by":2,"name":"Shuai Hu","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Shuai","middleName":"","lastName":"Hu","suffix":""},{"id":356020649,"identity":"46ccb973-593f-47eb-b4e9-eba584907904","order_by":3,"name":"Yuanchun Ye","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Yuanchun","middleName":"","lastName":"Ye","suffix":""},{"id":356020650,"identity":"bccc5b0e-e61c-4d1b-b230-74b5b6f75340","order_by":4,"name":"Yuling Chen","email":"","orcid":"","institution":"The Seventh Affiliated Hospital of Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Yuling","middleName":"","lastName":"Chen","suffix":""},{"id":356020651,"identity":"b5323655-d0f5-4fdd-8c8c-26e8c8713764","order_by":5,"name":"Ming Li","email":"","orcid":"","institution":"Incubation Center of Guangdong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Ming","middleName":"","lastName":"Li","suffix":""},{"id":356020652,"identity":"4497a2ef-666d-49ab-b7ab-f430334d64b4","order_by":6,"name":"Tianye Niu","email":"","orcid":"","institution":"Shenzhen Bay Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Tianye","middleName":"","lastName":"Niu","suffix":""},{"id":356020653,"identity":"5c7ac4fc-bf90-4f26-ba73-f937d62d7990","order_by":7,"name":"Jinfen Zheng","email":"","orcid":"","institution":"Center for Chronic Disease Prevention of Shenzhen","correspondingAuthor":false,"prefix":"","firstName":"Jinfen","middleName":"","lastName":"Zheng","suffix":""},{"id":356020654,"identity":"29344936-2b99-4012-978b-2e099204af50","order_by":8,"name":"Yongsheng Huang","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Yongsheng","middleName":"","lastName":"Huang","suffix":""},{"id":356020655,"identity":"cf6cd16e-3e6e-4a16-9fb9-61917b8f07a4","order_by":9,"name":"Yuanjie Bi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6UlEQVRIiWNgGAWjYBACA2Yg/sDAwMMHFzpAhBbDGUAtbMRrAWJmHiBBvBZzdh6DYtscOxk2BvZnkj/bGOT4biQwfi7Ao8WymcfAOHdbMtBhPGbSvG0MxpI3EpilZ+Bz2GGwFmaQFjZpxjaGxA03EtjATsWrxXJbPQ/MYfXEaWHcdhgUYmYSQIclGBDSYtnMVmDYu+04D1CZsTXPOQnDmWceNkvj02LOf3ibwc9t1fb87O0Pb/4os5HnO5588DM+LQwMHGYGYJqZgUWCgQGIGBgb8GpgYGB//ADKYv5AQOkoGAWjYBSMUAAAnTw8zkG2P5UAAAAASUVORK5CYII=","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":true,"prefix":"","firstName":"Yuanjie","middleName":"","lastName":"Bi","suffix":""}],"badges":[],"createdAt":"2024-08-22 15:06:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4959016/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4959016/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":68865263,"identity":"845823aa-0eaa-4fe3-b470-9d9784bc246e","added_by":"auto","created_at":"2024-11-13 01:08:41","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5901254,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4959016/v1_covered_20755107-a094-45dd-b4b2-f7773989df50.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eDeep Learning-Based Dose Prediction for Low-Energy Electron Superficial Radiotherapy\u003c/p\u003e","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":"Dose prediction, Deep learning, Monte Carlo simulation, Low-energy electron, Superficial treatment, Radiotherapy","lastPublishedDoi":"10.21203/rs.3.rs-4959016/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4959016/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground: \u003c/strong\u003eAccurate and rapid surface dose calculation is critical in superficiallow-energy electron radiotherapy due to the shallow treatment depth and the riskof radiation-induced skin toxicity. Traditional Monte Carlo (MC) simulations,while precise, can be computationally expensive and time-consuming.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods: \u003c/strong\u003eTo improve both the accuracy and speed of dose calculations, thisstudy combined MC simulations with deep learning techniques. Low-energy electron beams were simulated for six body sites using DOSXYZnrc, producing CTphantoms and corresponding dose distributions. A cascaded 3D-UNet (C3D) model was trained on these MC simulation datasets to predict dose distributionsrapidly.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults:\u003c/strong\u003e The C3D model demonstrated a mean absolute percentage error(MAPE) of less than 8% for one-dimensional dose curves, with no significantdifferences found in t-tests. The maximum dose difference observed across different body sites in 2D slices was 0.0421 ± 0.0340. The model achieved an overallGamma pass rate of over 92.09 ± 0.51% within 1%/1mm tolerance, and fordose distribution (DD) analysis under the 1% tolerance, the pass rate was 93.58± 0.21%. Additionally, the C3D model completed dose predictions in just 0.42seconds, making it approximately 140,000 times faster than MC simulations.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusion:\u003c/strong\u003e The integration of deep learning with MC simulations significantlyenhances the efficiency of surface dose calculations in superficial electron radiotherapy. The C3D model provides rapid and accurate dose predictions, facilitatingmore efficient treatment planning while maintaining high accuracy compared totraditional MC methods.\u003c/p\u003e","manuscriptTitle":"Deep Learning-Based Dose Prediction for Low-Energy Electron Superficial Radiotherapy","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-09-24 03:24:12","doi":"10.21203/rs.3.rs-4959016/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":"3c8111a3-85c0-43c2-a6f5-815d69a795f3","owner":[],"postedDate":"September 24th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-11-13T01:08:12+00:00","versionOfRecord":[],"versionCreatedAt":"2024-09-24 03:24:12","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4959016","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4959016","identity":"rs-4959016","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}