Efficient Real-Time 3D Scene Reconstruction of Brain Tumors Using Convolutional Neural Networks and Image Processing Pipelines

Efficient Real-Time 3D Scene Reconstruction of Brain Tumors Using Convolutional Neural Networks and Image Processing Pipelines | 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 Efficient Real-Time 3D Scene Reconstruction of Brain Tumors Using Convolutional Neural Networks and Image Processing Pipelines DevendraBabu Pidatala, Dr. Preeti Jha This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8249379/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 3D scene reconstruction becomes more tedious to reconstruct the image accurately without losing pixels. This process mainly used to improve the accuracy of disease detection rate, surgical intervention, and neuro-navigation. In this paper, the proposed approach is an integrated model that combines various models such as novel Deformable Attention Transformers (DAT) and Hierarchical Latent Space (HTS), combined with hybrid image processing pipelines. In this work, preprocessing plays a significant role in improving algorithm performance. Various preprocessing techniques, such as Median Filtering, Cropping, ROBEX (Robust Brain Extraction), and Multi-Scale Edge Detection (Marr-Hildreth), are used to increase the data quality. In the next step, the Swin Transformer (Shifted Window Transformer) architecture is used to fine-tune the segmented tumor regions, which helps reconstruct 3D images. To ensure real-time performance, we integrate optimized data handling mechanisms and parallel processing strategies. Finally, the proposed approach improves the 3D reconstruction brain tumor images by using Pre-trained Fine-Tuned 3D U-Net model to obtained the missed patterns from the input images and transmit to the proposed DAT-HTS using transfer learning. The constructed 3D models are validated with ground-truth data by measuring Dice Similarity Coefficient (DSC), and Intersection over Union (IoU), and computational efficiency-based standard metrics. Experimental results show that the proposed method can provide high segmentation accuracy and fast reconstruction time, which can be used for clinical purpose. This will allow for more efficient surgical intervention planning, as well as better analysis of surgery results by visualization of deep brain tumor structures. Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Physical sciences/Mathematics and computing Deformable Attention Transformers (DAT) Hierarchical Latent Space (HTS) Median Filtering Cropping ROBEX (Robust Brain Extraction) and Multi-Scale Edge Detection (Marr-Hildreth) 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-8249379","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":557972728,"identity":"3aee7c5f-69ce-4788-9e4f-6f049d9b3f7d","order_by":0,"name":"DevendraBabu Pidatala","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABO0lEQVRIiWNgGAWjYDACZgYDIGnBwHAAxGNjAHJ5GBg+gNjseLQcYJBA1cI4A8RmxmkPFi3MPBDTsAJzduaNnz/USMjzHe8xfFxQdk/enP3sMWmbX9vk+ZgZGD98zMHQYtnMVixx4JiE4cwzZ4yNZ5wrNtzZk5cmndt327CNmYFZcuY2TFcd5jGQOMAmwbjhRlqaNG9bAuOGAzlm0rk9txmBWtiYebFqMf5x4J+E/Yb7z9J/A7XYbzj/xkzasue2PR4tZhIH2yQSN9xgPsYM1AJkAG1h+HE7EZcWoF/KLM72SSTPPJN8WJrnXELyzhnvki17G24ntzEzNmPzizn/4c03Kr7Z2PYdP9j4macswXY7f+7BGz/+3Lad39588MNHLA7DHvaMbWCyAZscDi0Mf3CIj4JRMApGwUgEAIQab3gnGRPAAAAAAElFTkSuQmCC","orcid":"","institution":"Koneru Lakshmaiah Education Foundation","correspondingAuthor":true,"prefix":"","firstName":"DevendraBabu","middleName":"","lastName":"Pidatala","suffix":""},{"id":557972730,"identity":"7573d8ad-d58e-47e2-b7a6-c2a91dad074d","order_by":1,"name":"Dr. Preeti Jha","email":"","orcid":"","institution":"Koneru Lakshmaiah Education Foundation","correspondingAuthor":false,"prefix":"Dr.","firstName":"Preeti","middleName":"","lastName":"Jha","suffix":""}],"badges":[],"createdAt":"2025-12-01 10:53:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8249379/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8249379/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98198416,"identity":"a3b3cf6b-4ccc-471b-8367-7467a3eb6b80","added_by":"auto","created_at":"2025-12-15 07:11:19","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1129948,"visible":true,"origin":"","legend":"","description":"","filename":"EfficientRealTime3DSceneReconstruction.docx","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/19ea71d8b24aa3bc849954d2.docx"},{"id":98431065,"identity":"45e930b6-9500-4c29-b91f-2d221001e5bf","added_by":"auto","created_at":"2025-12-17 16:46:55","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4944,"visible":true,"origin":"","legend":"","description":"","filename":"fd065c13e0f147f1a1b3941375c657cc.json","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/9ecd3c2d9f8bd09205dece96.json"},{"id":98430957,"identity":"7e056960-6b47-41cf-bb38-567fbc27e87b","added_by":"auto","created_at":"2025-12-17 16:46:32","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":105478,"visible":true,"origin":"","legend":"","description":"","filename":"fd065c13e0f147f1a1b3941375c657cc1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/ed858cabe1b745c57037ab3c.xml"},{"id":98432254,"identity":"68546a60-e097-4b73-b542-891bedbd109c","added_by":"auto","created_at":"2025-12-17 16:49:18","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":210201,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/b005297514db7fff08bd05eb.png"},{"id":98198410,"identity":"a947f32f-0d9a-4311-9da4-0deaf93dec90","added_by":"auto","created_at":"2025-12-15 07:11:19","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":93591,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/aaf9f969dc745b70b910a9c9.png"},{"id":98433044,"identity":"2b7ad56d-0260-4b95-ac9d-636fba88f91d","added_by":"auto","created_at":"2025-12-17 16:50:12","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":108564,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/719d1b856db49043a385a8a1.png"},{"id":98198400,"identity":"e118f5f8-bddb-48ae-bf5e-45bf58dc6333","added_by":"auto","created_at":"2025-12-15 07:11:19","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":114799,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/a826332e43a5511b034a81e8.png"},{"id":98432746,"identity":"3917e473-b17c-489e-9756-caae3025a09e","added_by":"auto","created_at":"2025-12-17 16:49:54","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":102127,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/1f09157ba9bb39a645d235c1.png"},{"id":98198412,"identity":"c50c5be4-67a6-43db-a3f9-89e6979fd17d","added_by":"auto","created_at":"2025-12-15 07:11:19","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":322714,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/387c25781119e60114e9e024.png"},{"id":98198413,"identity":"f2130db2-8c4a-4dbd-8974-b96a86ff6152","added_by":"auto","created_at":"2025-12-15 07:11:19","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":142010,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/d40f48f108cafedde478de5e.png"},{"id":98198414,"identity":"5488b1eb-a15e-4796-ac0d-d0b4ae419f8c","added_by":"auto","created_at":"2025-12-15 07:11:19","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55404,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/f0f88d3b7fe26adff8a83aeb.png"},{"id":98432580,"identity":"f7ddc338-5f9d-46bf-b732-7184139c264f","added_by":"auto","created_at":"2025-12-17 16:49:43","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":26433,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/1103d06f5740090112b8980c.png"},{"id":98431164,"identity":"0fede57b-daba-4b1f-a21c-3890095bcc6a","added_by":"auto","created_at":"2025-12-17 16:47:10","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":26276,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/2b2b022f255b1ba0a0a58735.png"},{"id":98198417,"identity":"933e8f9f-41c6-45d9-a242-5db63cbf28ea","added_by":"auto","created_at":"2025-12-15 07:11:20","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21774,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/71fdd8967ee968a96cdcb5de.png"},{"id":98433028,"identity":"abed75fd-03a8-4202-8c76-3dcbaf5d33dd","added_by":"auto","created_at":"2025-12-17 16:50:12","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28730,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/e518da60a12b06f804630675.png"},{"id":98431576,"identity":"a37dc083-732e-4c47-844c-4b95a0ab8aac","added_by":"auto","created_at":"2025-12-17 16:47:58","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":63659,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/5f0e57f4456f87aaf01ef4d9.png"},{"id":98432291,"identity":"c81d3dbb-d76d-4df2-a0b9-7531e7249a8c","added_by":"auto","created_at":"2025-12-17 16:49:20","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":47211,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/32aac8dc43c428f7ae036814.png"},{"id":98432893,"identity":"bfb45d0f-3adf-41b3-8ea9-eb220c492b19","added_by":"auto","created_at":"2025-12-17 16:50:05","extension":"xml","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":103724,"visible":true,"origin":"","legend":"","description":"","filename":"fd065c13e0f147f1a1b3941375c657cc1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/afbe35ee1b0fa9571c19e816.xml"},{"id":98431641,"identity":"bbe9cc6c-76cb-420b-be07-e93c806a3995","added_by":"auto","created_at":"2025-12-17 16:48:05","extension":"html","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":114732,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1/6113522fb0de98b04491c046.html"},{"id":108942853,"identity":"fd96916a-887b-4eb5-b9e5-95f06be002cc","added_by":"auto","created_at":"2026-05-11 05:42:58","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":768300,"visible":true,"origin":"","legend":"","description":"","filename":"EfficientRealTime3DSceneReconstruction.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8249379/v1_covered_484c136c-0b5c-4e1f-b7e9-904bdaaf32b0.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Efficient Real-Time 3D Scene Reconstruction of Brain Tumors Using Convolutional Neural Networks and Image Processing Pipelines","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":"Deformable Attention Transformers (DAT), Hierarchical Latent Space (HTS), Median Filtering, Cropping, ROBEX (Robust Brain Extraction), and Multi-Scale Edge Detection (Marr-Hildreth)","lastPublishedDoi":"10.21203/rs.3.rs-8249379/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8249379/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e3D scene reconstruction becomes more tedious to reconstruct the image accurately without losing pixels. This process mainly used to improve the accuracy of disease detection rate, surgical intervention, and neuro-navigation. In this paper, the proposed approach is an integrated model that combines various models such as novel Deformable Attention Transformers (DAT) and Hierarchical Latent Space (HTS), combined with hybrid image processing pipelines. In this work, preprocessing plays a significant role in improving algorithm performance. Various preprocessing techniques, such as Median Filtering, Cropping, ROBEX (Robust Brain Extraction), and Multi-Scale Edge Detection (Marr-Hildreth), are used to increase the data quality. In the next step, the Swin Transformer (Shifted Window Transformer) architecture is used to fine-tune the segmented tumor regions, which helps reconstruct 3D images. To ensure real-time performance, we integrate optimized data handling mechanisms and parallel processing strategies. Finally, the proposed approach improves the 3D reconstruction brain tumor images by using Pre-trained Fine-Tuned 3D U-Net model to obtained the missed patterns from the input images and transmit to the proposed DAT-HTS using transfer learning. The constructed 3D\u0026ensp;models are validated with ground-truth data by measuring Dice Similarity Coefficient (DSC), and Intersection over Union (IoU), and computational efficiency-based standard metrics. Experimental results show that the proposed method can provide high segmentation\u0026ensp;accuracy and fast reconstruction time, which can be used for clinical purpose. This will allow for more efficient surgical intervention\u0026ensp;planning, as well as better analysis of surgery results by visualization of deep brain tumor structures.\u003c/p\u003e","manuscriptTitle":"Efficient Real-Time 3D Scene Reconstruction of Brain Tumors Using Convolutional Neural Networks and Image Processing Pipelines","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-15 07:11:13","doi":"10.21203/rs.3.rs-8249379/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":"98c605d1-d32d-4cd5-b459-44ba0d80ae63","owner":[],"postedDate":"December 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":59389816,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":59389819,"name":"Physical sciences/Engineering"},{"id":59389823,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-05-11T05:41:12+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-15 07:11:13","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8249379","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8249379","identity":"rs-8249379","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}