Clinically Applicable System For 3D Teeth Segmentation in Intraoral Scans using Deep Learning

Clinically Applicable System For 3D Teeth Segmentation in Intraoral Scans using Deep Learning | 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 Article Clinically Applicable System For 3D Teeth Segmentation in Intraoral Scans using Deep Learning Jin Hao, Wen Liao, Yueling Zhang, Peilin Li, Jianru Yi, Jerry Peng, and 12 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-103285/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 Digital dentistry plays a pivotal role in dental healthcare. A critical step in many digital dental systems is to accurately delineate individual teeth and the gingiva in the three-dimension (3D) intraoral scanned (IOS) mesh data. However, previous state-of-the-art methods are either time-consuming or error-prone, hence hinder their clinical applicability. In this paper, we present an accurate, efficient, and fully-automated deep learning model, trained on a dataset of 4,000 IOS data annotated by experienced human experts. On a hold-out dataset of 200 scans, our model achieves a per-face accuracy, average-area accuracy and area under the receiver operating characteristic curve (AUC) of 96.94%, 98.26%, and 0.9991, respectively, significantly outperforming the state-of-the-art baseline. In addition, our model only takes about 24 seconds to generate segmentation outputs, as compared to over 5 minutes by the baseline and 15 minutes by human experts. A clinical performance test of 500 patients with malocclusion or/and abnormal teeth shows that 96.9% of the segmentations are satisfactory for clinical applications, 2.9% automatically trigger alarms for human improvement, and only 0.2% of them need rework. Our research demonstrates the potential for deep learning to improve the efficacy and efficiency of dental treatment and digital dentistry. Dentistry Theoretical Computer Science Nuclear Medicine & Medical Imaging 3D Teeth Segmentation Intraoral Scans Deep Learning Digital Dentistry Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Full Text Tables Due to technical limitations, Tables 1-5 are only available as downloads in the Supplemental Files section. Additional Declarations Yes there is potential Competing Interest. X.F.P., Z.Z., and Z.C. are employed in DeepAlign. B.W.Z. and Y.F. are employed in Angel Align. J.H. and Z.Z.L. are consultants to DeepAlign. Supplementary Files SupplementaryMaterials.docx Supplementary Materials FigureS1.pdf Figure S1 FigureS2.pdf Figure S2 FigureS3.pdf Figure S3 TABLE1.docx Table 1 TABLE2.docx Table 2 TABLE3.docx Table 3 TABLE4.docx Table 4 TABLE5.docx Table 5 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-103285","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":4383893,"identity":"7ce1d9fb-4d91-446d-974b-3573bbd8ae0f","order_by":0,"name":"Jin Hao","email":"","orcid":"","institution":"Harvard University","correspondingAuthor":false,"prefix":"","firstName":"Jin","middleName":"","lastName":"Hao","suffix":""},{"id":4383894,"identity":"f84f155c-4aa8-483b-9e5b-14f5b6023414","order_by":1,"name":"Wen Liao","email":"","orcid":"","institution":"Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Wen","middleName":"","lastName":"Liao","suffix":""},{"id":4383895,"identity":"5f44e251-eea2-4b25-8d4f-454382346500","order_by":2,"name":"Yueling Zhang","email":"","orcid":"","institution":"Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Yueling","middleName":"","lastName":"Zhang","suffix":""},{"id":4383896,"identity":"31709512-65c6-4f27-97fc-9afee1ea9a68","order_by":3,"name":"Peilin Li","email":"","orcid":"","institution":"Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Peilin","middleName":"","lastName":"Li","suffix":""},{"id":4383897,"identity":"4a3becc0-0ed6-4bb8-973b-bce532831f8b","order_by":4,"name":"Jianru Yi","email":"","orcid":"","institution":"Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Jianru","middleName":"","lastName":"Yi","suffix":""},{"id":4383898,"identity":"189d7454-dbd8-474a-8c8b-b1792dfc0129","order_by":5,"name":"Jerry Peng","email":"","orcid":"","institution":"DeepAlign Tech Inc.","correspondingAuthor":false,"prefix":"","firstName":"Jerry","middleName":"","lastName":"Peng","suffix":""},{"id":4383899,"identity":"a7b45de7-083c-4d0d-811e-3e8460cf7d51","order_by":6,"name":"Zeu Zhao","email":"","orcid":"","institution":"DeepAlign Tech Inc.","correspondingAuthor":false,"prefix":"","firstName":"Zeu","middleName":"","lastName":"Zhao","suffix":""},{"id":4383900,"identity":"43ba694a-577d-4439-b56b-446f70fd2481","order_by":7,"name":"Zhang Chen","email":"","orcid":"","institution":"DeepAlign Tech Inc.","correspondingAuthor":false,"prefix":"","firstName":"Zhang","middleName":"","lastName":"Chen","suffix":""},{"id":4383901,"identity":"19ed8f54-baf1-4b23-b6b6-7c8695c3da92","order_by":8,"name":"Wenxuan Shi","email":"","orcid":"","institution":"DeepAlign Tech Inc.","correspondingAuthor":false,"prefix":"","firstName":"Wenxuan","middleName":"","lastName":"Shi","suffix":""},{"id":4383902,"identity":"b8eddda8-f017-4da1-865b-506de1729578","order_by":9,"name":"Tingyu Chen","email":"","orcid":"","institution":"DeepAlign Tech Inc.","correspondingAuthor":false,"prefix":"","firstName":"Tingyu","middleName":"","lastName":"Chen","suffix":""},{"id":4383903,"identity":"6432460a-ab38-461b-bc82-f360a7bde61f","order_by":10,"name":"Bowen Zhou","email":"","orcid":"","institution":"Angel Align Inc.","correspondingAuthor":false,"prefix":"","firstName":"Bowen","middleName":"","lastName":"Zhou","suffix":""},{"id":4383904,"identity":"23ee118b-f0d3-41fb-b68f-27e344d09946","order_by":11,"name":"Yang Feng","email":"","orcid":"","institution":"Angel Align Inc.","correspondingAuthor":false,"prefix":"","firstName":"Yang","middleName":"","lastName":"Feng","suffix":""},{"id":4383905,"identity":"0eab9804-1acf-40b7-a1a2-9d6a192f49e0","order_by":12,"name":"Bing Fang","email":"","orcid":"","institution":"Department of Orthodontics, Shanghai Ninth People’s Hospital, Collage of Stomatology, Shanghai Jiao Tong University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Bing","middleName":"","lastName":"Fang","suffix":""},{"id":4383906,"identity":"69c425b6-1fec-4d42-86ad-d0810c7389ec","order_by":13,"name":"Haoji Hu","email":"","orcid":"","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Haoji","middleName":"","lastName":"Hu","suffix":""},{"id":4383907,"identity":"60dafc9d-defa-49a4-a6ba-d963b39cdf81","order_by":14,"name":"Howard Yang","email":"","orcid":"","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Howard","middleName":"","lastName":"Yang","suffix":""},{"id":4383908,"identity":"f2e37bb9-c013-4fb5-a0f4-10f17966561c","order_by":15,"name":"Erping Li","email":"","orcid":"https://orcid.org/0000-0002-5006-7399","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Erping","middleName":"","lastName":"Li","suffix":""},{"id":4383909,"identity":"bde64e79-5a23-4019-9089-459426fcecd2","order_by":16,"name":"Zuozhu Liu","email":"","orcid":"","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Zuozhu","middleName":"","lastName":"Liu","suffix":""},{"id":4383910,"identity":"9bcabedc-7eff-4180-9dbd-77aa37f6d888","order_by":17,"name":"Zhihe Zhao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwElEQVRIiWNgGAWjYDACCQY2IGkD4fCQoCWNdC2HSdAiP7v92YMfFeft+WckMD5428Ygb05IC+OcA+mGPWduJ864kcBsOLeNwXBnAwEtzBIJxyR4224nGEgksEnztjEkGBwgoIVNIrFN8m/bOXugFvbfRGnhkUgGGX6AcQPQFmaitEhIpLFJy5xJTpxx5mGz5JxzEoYbCGmRn5H+TPJNhZ09f3vywQ9vymzkCdqCBBgbQLYSr34UjIJRMApGAW4AABA9OKcZ8nU3AAAAAElFTkSuQmCC","orcid":"","institution":"Sichuan University","correspondingAuthor":true,"prefix":"","firstName":"Zhihe","middleName":"","lastName":"Zhao","suffix":""}],"badges":[],"createdAt":"2020-11-05 07:45:40","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-103285/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-103285/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":3489983,"identity":"6be7eed8-4ba0-4bc9-9809-5192200776ef","added_by":"auto","created_at":"2020-11-10 15:16:50","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":144302,"visible":true,"origin":"","legend":"The DC-Net system is composed of two main modules to generate clinically applicable segmentation outputs. The deep learning segmentation module includes data preprocessing, deep learning segmentation and boundary smoothing. The canary module includes confidence evaluation, auto-correction, and fault-alarm for potential human improvement.","description":"","filename":"1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-103285/v1/edf06d0e0fb684224e9bfff6.jpg"},{"id":3489985,"identity":"7f05fe27-f9a4-403f-a163-160afda5e8ac","added_by":"auto","created_at":"2020-11-10 15:16:51","extension":"jpg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":90118,"visible":true,"origin":"","legend":"ROC curves for (A): ROC curves for the gingiva in maxillary and mandible. (B-C): ROC curves for three teeth in mandible and maxillary, respectively. We selected the worst-performed teeth (teeth 18 and 48); 2 randomly chosen canine teeth (teeth 11 and 32) and 2 randomly chosen molar teeth (teeth 25 and 36). The horizontal axis is zoomed for better visualization in (A-B).","description":"","filename":"figure2.jpg","url":"https://assets-eu.researchsquare.com/files/rs-103285/v1/f9bca2e8d509e2836997768f.jpg"},{"id":3489987,"identity":"de92eec7-05d7-401f-ac69-b389ff756142","added_by":"auto","created_at":"2020-11-10 15:17:10","extension":"jpg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":138418,"visible":true,"origin":"","legend":"The confusion matrix for the predictions by DLBS versus the ground-truth from human experts for the mandible (A) and maxillary (B), respectively. The percentage of all mesh faces in each category is displayed on a color gradient scale.","description":"","filename":"figure3.jpg","url":"https://assets-eu.researchsquare.com/files/rs-103285/v1/fe516f4b7349e81f9ebc279d.jpg"},{"id":3489989,"identity":"f85d1839-fe93-4bb3-8563-89d7683b4b88","added_by":"auto","created_at":"2020-11-10 15:17:11","extension":"jpg","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":162648,"visible":true,"origin":"","legend":"Details of the selected boxes are displayed in the corresponding zoom-in boxes on the right. The teeth and gingiva are labeled with 17 different predefined colors, with a reference shown in the Supplementary.","description":"","filename":"4.jpg","url":"https://assets-eu.researchsquare.com/files/rs-103285/v1/f14a11ba351eb58988e2b24c.jpg"},{"id":3489991,"identity":"6934c8cb-cfbb-42cf-8da5-e84cc7f2b332","added_by":"auto","created_at":"2020-11-10 15:17:12","extension":"jpg","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":58151,"visible":true,"origin":"","legend":"The deep learning architecture takes the point clouds as inputs and outputs the segmentation results which could be mapped back to meshes easily using kNN. The network first transforms the set of points to a canonical space with the Transformation Net. Then, the EdgeConv blocks will compute edge features for each point, and aggregate features using 2D convolutional layers. We stack both mean- and max-pooling layers after the first two EdgeConv blocks, and the pooled outputs will be concatenated as the input for the next block. The outputs from all EdgeConv blocks are concatenated together to form a global feature descriptor before the one-hot encoded categorical vector (maxilla or mandible) is fed into the network. Finally, we stack four 2D convolutional layers, which aggregate the concatenation of the outputs from all intermediate EdgeConv blocks and the global feature descriptor, to generate point-wise classification scores for 33 semantic labels. \u0026oplus; in the diagram stands for concatenation. The detailed settings of the architecture are listed in Methods and Supplementary.","description":"","filename":"5.jpg","url":"https://assets-eu.researchsquare.com/files/rs-103285/v1/bab3e1fb7983c719fbf1d6eb.jpg"},{"id":13554915,"identity":"c09b8446-b935-4ec1-af61-b9edcdb0f9df","added_by":"auto","created_at":"2021-09-17 02:43:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":617418,"visible":true,"origin":"","legend":"","description":"","filename":"NatureComm110320.pdf","url":"https://assets-eu.researchsquare.com/files/rs-103285/v1_covered.pdf"},{"id":3489982,"identity":"4e9ff9dd-f1f8-41fd-8a8d-bc5421803ea5","added_by":"auto","created_at":"2020-11-10 15:17:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":295317,"visible":true,"origin":"","legend":"","description":"","filename":"NatureComm110320.pdf","url":"https://assets-eu.researchsquare.com/files/rs-103285/v1_stamped.pdf"},{"id":3489984,"identity":"bb680159-cf60-4abd-8a5b-989f91254984","added_by":"auto","created_at":"2020-11-10 15:16:51","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":30555,"visible":true,"origin":"","legend":"Supplementary Materials","description":"","filename":"SupplementaryMaterials.docx","url":"https://assets-eu.researchsquare.com/files/rs-103285/v1/07048fb65ec42a8f348b30f5.docx"},{"id":3489986,"identity":"d3be87c2-3bff-4ddf-a23b-d96251f82a09","added_by":"auto","created_at":"2020-11-10 15:17:09","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":25072569,"visible":true,"origin":"","legend":"Figure S1","description":"","filename":"FigureS1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-103285/v1/439e533d6ec220c1e0c8f873.pdf"},{"id":3489988,"identity":"1bf3db62-0200-4e39-a78e-0c9c77d1590d","added_by":"auto","created_at":"2020-11-10 15:17:11","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":23464075,"visible":true,"origin":"","legend":"Figure S2","description":"","filename":"FigureS2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-103285/v1/8e3cd42ac58d1c4efa59f4fa.pdf"},{"id":3489990,"identity":"802cc6d6-8ed9-426b-bfdb-b7bdb5d32c94","added_by":"auto","created_at":"2020-11-10 15:17:12","extension":"pdf","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":26229722,"visible":true,"origin":"","legend":"Figure S3","description":"","filename":"FigureS3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-103285/v1/e778e367600d83fe17b2f39c.pdf"},{"id":3489992,"identity":"0e27fb16-7934-40d2-b9d5-be3b3c5eb52b","added_by":"auto","created_at":"2020-11-10 15:17:12","extension":"docx","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":14319,"visible":true,"origin":"","legend":"Table 1","description":"","filename":"TABLE1.docx","url":"https://assets-eu.researchsquare.com/files/rs-103285/v1/8726835fef265a00004948e0.docx"},{"id":3489993,"identity":"1f1777c4-bf7f-4505-bb7a-541fa7387cd6","added_by":"auto","created_at":"2020-11-10 15:17:12","extension":"docx","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":13598,"visible":true,"origin":"","legend":"Table 2","description":"","filename":"TABLE2.docx","url":"https://assets-eu.researchsquare.com/files/rs-103285/v1/a55dfc911063555f44ed5be1.docx"},{"id":3489994,"identity":"8ca5b80e-2cb1-43b7-9ed7-1d53075b4c85","added_by":"auto","created_at":"2020-11-10 15:17:12","extension":"docx","order_by":7,"title":"","display":"","copyAsset":false,"role":"supplement","size":16881,"visible":true,"origin":"","legend":"Table 3","description":"","filename":"TABLE3.docx","url":"https://assets-eu.researchsquare.com/files/rs-103285/v1/9dd853514f05ad336a03f4b0.docx"},{"id":3489995,"identity":"ef76eab5-b0ca-461e-bdaf-6092e606b023","added_by":"auto","created_at":"2020-11-10 15:17:12","extension":"docx","order_by":8,"title":"","display":"","copyAsset":false,"role":"supplement","size":16683,"visible":true,"origin":"","legend":"Table 4","description":"","filename":"TABLE4.docx","url":"https://assets-eu.researchsquare.com/files/rs-103285/v1/2856eb20670acf38255a7b5c.docx"},{"id":3489996,"identity":"c9eb1590-c4e9-4030-bc99-6c2a1a50983c","added_by":"auto","created_at":"2020-11-10 15:17:13","extension":"docx","order_by":9,"title":"","display":"","copyAsset":false,"role":"supplement","size":13907,"visible":true,"origin":"","legend":"Table 5","description":"","filename":"TABLE5.docx","url":"https://assets-eu.researchsquare.com/files/rs-103285/v1/7657a91715a17852336bfdcc.docx"}],"financialInterests":"\u003cb\u003eYes\u003c/b\u003e there is potential Competing Interest.\nX.F.P., Z.Z., and Z.C. are employed in DeepAlign. B.W.Z. and Y.F. are employed in Angel Align. J.H. and Z.Z.L. are consultants to DeepAlign.","formattedTitle":"Clinically Applicable System For 3D Teeth Segmentation in Intraoral Scans using Deep Learning","fulltext":[{"header":"Full Text","content":"\u003cp\u003eThis preprint is available for \u003ca href='/article/rs-103285/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e.\u003c/p\u003e"},{"header":"Tables","content":"\u003cp\u003eDue to technical limitations, Tables 1-5 are only available as downloads in the Supplemental Files section.\u0026nbsp;\u003c/p\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":"3D Teeth Segmentation, Intraoral Scans, Deep Learning, Digital Dentistry","lastPublishedDoi":"10.21203/rs.3.rs-103285/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-103285/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDigital dentistry plays a pivotal role in dental healthcare. A critical step in many digital dental systems is to accurately delineate individual teeth and the gingiva in the three-dimension (3D) intraoral scanned (IOS) mesh data. However, previous state-of-the-art methods are either time-consuming or error-prone, hence hinder their clinical applicability. In this paper, we present an accurate, efficient, and fully-automated deep learning model, trained on a dataset of 4,000 IOS data annotated by experienced human experts. On a hold-out dataset of 200 scans, our model achieves a per-face accuracy, average-area accuracy and area under the receiver operating characteristic curve (AUC) of 96.94%, 98.26%, and 0.9991, respectively, significantly outperforming the state-of-the-art baseline. In addition, our model only takes about 24 seconds to generate segmentation outputs, as compared to over 5 minutes by the baseline and 15 minutes by human experts. A clinical performance test of 500 patients with malocclusion or/and abnormal teeth shows that 96.9% of the segmentations are satisfactory for clinical applications, 2.9% automatically trigger alarms for human improvement, and only 0.2% of them need rework. Our research demonstrates the potential for deep learning to improve the efficacy and efficiency of dental treatment and digital dentistry.\u003c/p\u003e","manuscriptTitle":"Clinically Applicable System For 3D Teeth Segmentation in Intraoral Scans using Deep Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2020-11-10 15:16:49","doi":"10.21203/rs.3.rs-103285/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":"9d867ecb-704c-4dab-a420-d0916d7b7ecf","owner":[],"postedDate":"November 10th, 2020","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":1005118,"name":"Dentistry"},{"id":1005119,"name":"Theoretical Computer Science"},{"id":1005120,"name":"Nuclear Medicine \u0026 Medical Imaging"}],"tags":[],"updatedAt":"2021-05-10T09:47:43+00:00","versionOfRecord":[],"versionCreatedAt":"2020-11-10 15:16:49","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-103285","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-103285","identity":"rs-103285","version":["v1"]},"buildId":"_2-kVJe1T_tPrBINL-cwx","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}