ODNN: Augmented Brain Tumor Boundary Detection and Localization in MRI Images using Optimization Guided Hybrid Deep Neural Networks

ODNN: Augmented Brain Tumor Boundary Detection and Localization in MRI Images using Optimization Guided Hybrid Deep Neural Networks | 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 ODNN: Augmented Brain Tumor Boundary Detection and Localization in MRI Images using Optimization Guided Hybrid Deep Neural Networks Mohammed Razia Alangir Banu, Arpita Gupta, Athur Shaik Ali Gousia Banu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4622762/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 Accurate tumor segmentation and localization in MRI images are critical for diagnosis, treatment planning, and monitoring in oncology. However, manual delineation of tumor boundaries is time-consuming and subject to inter-observer variability. Deep learning techniques have shown promise in automating this process, yet achieving precise localization remains challenging. In this work, we propose an Optimization-Guided Hybrid Deep Neural Network (ODNN) framework for augmented tumor boundary detection and localization in MRI images. The ODNN model integrates optimization techniques practical swam optimization (PSO) within Inception-v3 and ResNet-50 to enhance the accuracy of tumor localization. Specifically, we employ a combination of convolutional neural networks (CNNs) for feature extraction and optimization algorithms to refine tumor boundary predictions. The optimization technique, PSO process iteratively adjusts model parameters to minimize a predefined tumor function, optimizing the network for improved localization performance. We evaluate the proposed ODNN framework on a dataset of MRI images containing various tumor types and complexities. Comparative experiments demonstrate that our approach achieves superior performance in tumor boundary detection and localization compared to baseline deep learning models. Quantitative evaluation metrics such as precision of 97.8%, dice similarity coefficient of 94.5%, recall of 95.5%, f1-score of 96.2% and hausdorff distance of 7.12 which confirm the effectiveness of the ODNN framework in accurately delineating tumor boundaries. By integrating optimization techniques with deep learning, we effectively address the challenges of precise tumor localization. The proposed ODNN framework holds promise for improving diagnostic accuracy, treatment planning, and patient outcomes in oncology, paving the way for advancements in computer-aided diagnosis systems for medical imaging. Deep Neural Network Brain MRI Images Tumor Segmentation ResNet50 Inception-v3 Optimization Algorithm 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-4622762","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":322267375,"identity":"51449870-9629-4d2b-a63a-d8877b10613e","order_by":0,"name":"Mohammed Razia Alangir Banu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA50lEQVRIiWNgGAWjYJCCA4wNQJKZ+eADIMXDR7wWdrZkA5AWNqKsAWvh5zGTAHEIajFvP/7wwM8ddnkGh9nSKr/m2MmwMTA/fHQDjxaZMwkJB3vPJBcbHGY+dlt2WzLQYWzGxjl4tEgwJBw4wNvGnLgBaMttyW3MQC08bNJ4tfA/bDj4t60eqIXHrFhyWz0RWiSSGQ7zth0Ga2H8uO0wMVqeMRyWPXM8ceZhtmRpxm3HediYCfmFP/3xx7c7qhP7zh8++PHntmp7fvbmh4/xaUEBzDxgkljlIMD4gxTVo2AUjIJRMGIAAB6ESeGz+PHOAAAAAElFTkSuQmCC","orcid":"","institution":"Koneru Lakshmiah Education Foundation","correspondingAuthor":true,"prefix":"","firstName":"Mohammed","middleName":"Razia Alangir","lastName":"Banu","suffix":""},{"id":322267376,"identity":"9d9c3e57-5965-4e79-91d9-f16224a197f8","order_by":1,"name":"Arpita Gupta","email":"","orcid":"","institution":"Koneru Lakshmiah Education Foundation","correspondingAuthor":false,"prefix":"","firstName":"Arpita","middleName":"","lastName":"Gupta","suffix":""},{"id":322267377,"identity":"f0e597eb-4645-4bd9-a15c-4be4c0d962b0","order_by":2,"name":"Athur Shaik Ali Gousia Banu","email":"","orcid":"","institution":"Koneru Lakshmiah Education Foundation","correspondingAuthor":false,"prefix":"","firstName":"Athur","middleName":"Shaik Ali Gousia","lastName":"Banu","suffix":""}],"badges":[],"createdAt":"2024-06-22 17:03:05","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4622762/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4622762/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100364407,"identity":"b58c64eb-59d0-4c18-98db-c2ae5ce88e08","added_by":"auto","created_at":"2026-01-16 07:53:38","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2552842,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4622762/v1_covered_88d0e524-e1f3-4ba6-acc1-3a88dfcffd46.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"ODNN: Augmented Brain Tumor Boundary Detection and Localization in MRI Images using Optimization Guided Hybrid Deep Neural Networks","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":"Deep Neural Network, Brain MRI Images, Tumor Segmentation, ResNet50, Inception-v3, Optimization Algorithm","lastPublishedDoi":"10.21203/rs.3.rs-4622762/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4622762/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate tumor segmentation and localization in MRI images are critical for diagnosis, treatment planning, and monitoring in oncology. However, manual delineation of tumor boundaries is time-consuming and subject to inter-observer variability. Deep learning techniques have shown promise in automating this process, yet achieving precise localization remains challenging. In this work, we propose an Optimization-Guided Hybrid Deep Neural Network (ODNN) framework for augmented tumor boundary detection and localization in MRI images. The ODNN model integrates optimization techniques practical swam optimization (PSO) within Inception-v3 and ResNet-50 to enhance the accuracy of tumor localization. Specifically, we employ a combination of convolutional neural networks (CNNs) for feature extraction and optimization algorithms to refine tumor boundary predictions. The optimization technique, PSO process iteratively adjusts model parameters to minimize a predefined tumor function, optimizing the network for improved localization performance. We evaluate the proposed ODNN framework on a dataset of MRI images containing various tumor types and complexities. Comparative experiments demonstrate that our approach achieves superior performance in tumor boundary detection and localization compared to baseline deep learning models. Quantitative evaluation metrics such as precision of 97.8%, dice similarity coefficient of 94.5%, recall of 95.5%, f1-score of 96.2% and hausdorff distance of 7.12 which confirm the effectiveness of the ODNN framework in accurately delineating tumor boundaries. By integrating optimization techniques with deep learning, we effectively address the challenges of precise tumor localization. The proposed ODNN framework holds promise for improving diagnostic accuracy, treatment planning, and patient outcomes in oncology, paving the way for advancements in computer-aided diagnosis systems for medical imaging.","manuscriptTitle":"ODNN: Augmented Brain Tumor Boundary Detection and Localization in MRI Images using Optimization Guided Hybrid Deep Neural Networks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-06 09:39:55","doi":"10.21203/rs.3.rs-4622762/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":"e6c78265-4e54-43a4-92c9-cba103b90a4d","owner":[],"postedDate":"January 6th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-12T21:53:30+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-06 09:39:55","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4622762","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4622762","identity":"rs-4622762","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}