Enhanced 3D Dose Prediction for Hypofractionated SRS (Gamma Knife Radiosurgery) in Brain Tumor Using Cascaded-Deep-Supervised Convolutional Neural Network

Enhanced 3D Dose Prediction for Hypofractionated SRS (Gamma Knife Radiosurgery) in Brain Tumor Using Cascaded-Deep-Supervised Convolutional Neural Network | 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 Enhanced 3D Dose Prediction for Hypofractionated SRS (Gamma Knife Radiosurgery) in Brain Tumor Using Cascaded-Deep-Supervised Convolutional Neural Network Nan Li, Jinyuan Wang, Chunfeng Fang, Dongxue Zhou, Yaoying Liu, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3866145/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 30 Jul, 2024 Read the published version in Physical and Engineering Sciences in Medicine → Version 1 posted 5 You are reading this latest preprint version Abstract Gamma Knife radiosurgery (GKRS) is a well-established radiation therapy (RT) technique for treating brain tumors. However, the planning process for GKRS is complex and time-consuming, heavily reliant on the expertise of medical physicists. Incorporating deep learning approaches for GKRS dose prediction can reduce this dependency, improving planning efficiency and homogeneity, streamlining clinical workflows, and reducing patient lagging times. Despite this, precise Gamma Knife plan dose distribution prediction using existing models remains a significant challenge. The complexity stems from the intricate nature of dose distributions, subtle contrasts in CT scans, and the interdependence of dosimetric metrics. In an effort to overcome these challenges, we have developed a "Cascaded-Deep-Supervised" Convolutional Neural Network (CDS-CNN) that employs a hybrid-weighted optimization scheme. Our innovative method incorporates multi-level deep supervision along with a strategic sequential multi-network training approach. It enables the extraction of intra-slice and inter-slice features, leading to more realistic dose predictions with additional contextual information. CDS-CNN was trained and evaluated using data from 105 brain cancer patients who underwent GKRS treatment, with 85 cases used for training and 20 for testing. Quantitative evaluations and statistical analyses demonstrated high consistency between the predicted dose distributions and the reference doses from the treatment planning system (TPS). The 3D overall gamma passing rates (GPRs) reached 97.15%±1.36% (3mm/3%, 10% threshold). When evaluated using the more stringent criteria of 2mm/3%, 10% threshold, the overall GPRs still achieved 96.33%±1.08%. Furthermore, the average target coverage (TC) was 98.33%±1.16%, dose selectivity (DS) was 0.57±0.10, gradient index (GI) was 2.69±0.30, and homogeneity index (HI) was 1.79±0.09. The experimental results showed that the proposed CDS-CNN outperformed other models in predicting GKRS dose distributions, with the prediction being the closest to the TPS dose. Gamma Knife radiosurgery Brain cancer Convolutional Neural Network Dose prediction Contextual information Full Text Supplementary Files 3.Highlights.pdf Cite Share Download PDF Status: Published Journal Publication published 30 Jul, 2024 Read the published version in Physical and Engineering Sciences in Medicine → Version 1 posted Reviewers agreed at journal 27 Jan, 2024 Reviewers invited by journal 24 Jan, 2024 Editor invited by journal 15 Jan, 2024 Editor assigned by journal 15 Jan, 2024 First submitted to journal 14 Jan, 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-3866145","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":269342525,"identity":"36faf00f-3534-488f-a9ac-041c558a8c42","order_by":0,"name":"Nan Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwElEQVRIiWNgGAWjYBACfvb2gw8+VNjI8bM3EKlFsudMsuGMM2nGkj0HiNRicMPBTJqz5XDihhsJxLrsBkOaNGPDYWPJmY833mCosYkmqINxduNh68Id6XL80mnFFgzH0nIbCGlhljmQeHvmGWtjydk5ZhJA6whrYZNIMJDmbWNO3HDzDJFaeCQSjIBanIHe5yFSiwQPPJCBfkkgxi/2x+FReXjjjQ81NoS1IAMDiQRSlEO0kKpjFIyCUTAKRgYAACdIRBGxm8kuAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0001-6068-0667","institution":"Beihang University","correspondingAuthor":true,"prefix":"","firstName":"Nan","middleName":"","lastName":"Li","suffix":""},{"id":269342526,"identity":"9925b4af-cd3c-4814-887e-270b5ef3088f","order_by":1,"name":"Jinyuan Wang","email":"","orcid":"","institution":"301 Military Hospital: Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Jinyuan","middleName":"","lastName":"Wang","suffix":""},{"id":269342527,"identity":"06239f33-b0c9-450b-9c0f-ed8e1cedd765","order_by":2,"name":"Chunfeng Fang","email":"","orcid":"","institution":"Tsinghua University","correspondingAuthor":false,"prefix":"","firstName":"Chunfeng","middleName":"","lastName":"Fang","suffix":""},{"id":269342528,"identity":"80a21daf-4997-4aea-993a-25da7cb6a336","order_by":3,"name":"Dongxue Zhou","email":"","orcid":"","institution":"HeBei YiZhou Proton Center","correspondingAuthor":false,"prefix":"","firstName":"Dongxue","middleName":"","lastName":"Zhou","suffix":""},{"id":269342529,"identity":"25adf1b7-3bfa-4dc0-9cac-b1cf1af872d0","order_by":4,"name":"Yaoying Liu","email":"","orcid":"","institution":"Beihang University","correspondingAuthor":false,"prefix":"","firstName":"Yaoying","middleName":"","lastName":"Liu","suffix":""},{"id":269342530,"identity":"8062c967-b014-4986-a54c-244a1a5cb4da","order_by":5,"name":"Yanping Wang","email":"","orcid":"","institution":"HeiBei YiZhou Proton Center","correspondingAuthor":false,"prefix":"","firstName":"Yanping","middleName":"","lastName":"Wang","suffix":""},{"id":269342531,"identity":"5350c571-f3a1-4372-964f-0d18ed4b1c80","order_by":6,"name":"Chunsu Zhang","email":"","orcid":"","institution":"HeBei YiZhou Proton Center","correspondingAuthor":false,"prefix":"","firstName":"Chunsu","middleName":"","lastName":"Zhang","suffix":""},{"id":269342532,"identity":"5cd3aaac-4498-43d0-a219-0cc36b7e8a20","order_by":7,"name":"Lin Cao","email":"","orcid":"","institution":"HeBei YiZHou Proton Center","correspondingAuthor":false,"prefix":"","firstName":"Lin","middleName":"","lastName":"Cao","suffix":""},{"id":269342533,"identity":"5d0a7751-1a20-4baa-bf6b-9d844664ab01","order_by":8,"name":"Gaolong Zhang","email":"","orcid":"","institution":"Beihang University","correspondingAuthor":false,"prefix":"","firstName":"Gaolong","middleName":"","lastName":"Zhang","suffix":""},{"id":269342534,"identity":"4de46dd3-539a-4f99-83d7-8b62356650dd","order_by":9,"name":"Shouping Xu","email":"","orcid":"https://orcid.org/0000-0003-3189-9680","institution":"Chinese Academy of Medical Sciences and Peking Union Medical College","correspondingAuthor":false,"prefix":"","firstName":"Shouping","middleName":"","lastName":"Xu","suffix":""}],"badges":[],"createdAt":"2024-01-15 10:21:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3866145/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3866145/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s13246-024-01457-2","type":"published","date":"2024-07-30T15:56:56+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":61793299,"identity":"13fb4286-78ec-44de-b30c-2924743cadf9","added_by":"auto","created_at":"2024-08-05 16:09:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1324693,"visible":true,"origin":"","legend":"","description":"","filename":"01Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3866145/v1_covered_6619adc0-75b6-4b75-a6b2-e681a04df4cb.pdf"},{"id":50367682,"identity":"4e2ca16e-f4b1-4e03-a720-6213c68d48d8","added_by":"auto","created_at":"2024-01-30 12:15:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":12786,"visible":true,"origin":"","legend":"","description":"","filename":"3.Highlights.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3866145/v1/4819e4a380a749b146abf352.pdf"}],"financialInterests":"","formattedTitle":"Enhanced 3D Dose Prediction for Hypofractionated SRS (Gamma Knife Radiosurgery) in Brain Tumor Using Cascaded-Deep-Supervised Convolutional Neural Network","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":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"physical-and-engineering-sciences-in-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"apes","sideBox":"Learn more about [Physical and Engineering Sciences in Medicine](http://link.springer.com/journal/13246)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/apes/default.aspx","title":"Physical and Engineering Sciences in Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Gamma Knife radiosurgery, Brain cancer, Convolutional Neural Network, Dose prediction, Contextual information","lastPublishedDoi":"10.21203/rs.3.rs-3866145/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3866145/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eGamma Knife radiosurgery (GKRS) is a well-established radiation therapy (RT) technique for treating brain tumors. However, the planning process for GKRS is complex and time-consuming, heavily reliant on the expertise of medical physicists. Incorporating deep learning approaches for GKRS dose prediction can reduce this dependency, improving planning efficiency and homogeneity, streamlining clinical workflows, and reducing patient lagging times. Despite this, precise Gamma Knife plan dose distribution prediction using existing models remains a significant challenge. The complexity stems from the intricate nature of dose distributions, subtle contrasts in CT scans, and the interdependence of dosimetric metrics. In an effort to overcome these challenges, we have developed a \"Cascaded-Deep-Supervised\" Convolutional Neural Network (CDS-CNN) that employs a hybrid-weighted optimization scheme. Our innovative method incorporates multi-level deep supervision along with a strategic sequential multi-network training approach. It enables the extraction of intra-slice and inter-slice features, leading to more realistic dose predictions with additional contextual information. CDS-CNN was trained and evaluated using data from 105 brain cancer patients who underwent GKRS treatment, with 85 cases used for training and 20 for testing. Quantitative evaluations and statistical analyses demonstrated high consistency between the predicted dose distributions and the reference doses from the treatment planning system (TPS). The 3D overall gamma passing rates (GPRs) reached 97.15%\u0026plusmn;1.36% (3mm/3%, 10% threshold). When evaluated using the more stringent criteria of 2mm/3%, 10% threshold, the overall GPRs still achieved 96.33%\u0026plusmn;1.08%. Furthermore, the average target coverage (TC) was 98.33%\u0026plusmn;1.16%, dose selectivity (DS) was 0.57\u0026plusmn;0.10, gradient index (GI) was 2.69\u0026plusmn;0.30, and homogeneity index (HI) was 1.79\u0026plusmn;0.09. The experimental results showed that the proposed CDS-CNN outperformed other models in predicting GKRS dose distributions, with the prediction being the closest to the TPS dose.\u003c/p\u003e","manuscriptTitle":"Enhanced 3D Dose Prediction for Hypofractionated SRS (Gamma Knife Radiosurgery) in Brain Tumor Using Cascaded-Deep-Supervised Convolutional Neural Network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-30 12:10:25","doi":"10.21203/rs.3.rs-3866145/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"","date":"2024-01-27T23:19:33+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-01-24T22:48:34+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"Physical and Engineering Sciences in Medicine","date":"2024-01-16T01:27:31+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-01-15T20:32:43+00:00","index":"","fulltext":""},{"type":"submitted","content":"Physical and Engineering Sciences in Medicine","date":"2024-01-15T00:27:53+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"physical-and-engineering-sciences-in-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"apes","sideBox":"Learn more about [Physical and Engineering Sciences in Medicine](http://link.springer.com/journal/13246)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/apes/default.aspx","title":"Physical and Engineering Sciences in Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"78812a26-5777-4a31-a12f-243edc4a1dc4","owner":[],"postedDate":"January 30th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-08-05T15:59:13+00:00","versionOfRecord":{"articleIdentity":"rs-3866145","link":"https://doi.org/10.1007/s13246-024-01457-2","journal":{"identity":"physical-and-engineering-sciences-in-medicine","isVorOnly":false,"title":"Physical and Engineering Sciences in Medicine"},"publishedOn":"2024-07-30 15:56:56","publishedOnDateReadable":"July 30th, 2024"},"versionCreatedAt":"2024-01-30 12:10:25","video":"","vorDoi":"10.1007/s13246-024-01457-2","vorDoiUrl":"https://doi.org/10.1007/s13246-024-01457-2","workflowStages":[]},"version":"v1","identity":"rs-3866145","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3866145","identity":"rs-3866145","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}