Segmentation of Brain Tumors Using a Generative AI-Enhanced U-Net Model | 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 Segmentation of Brain Tumors Using a Generative AI-Enhanced U-Net Model Nouran Reda Ragab, Rasha H.Sakr, Amal I.AboElenien This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7900791/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 Generative AI is significantly transforming medical imaging by helping to overcome major obstacles such as data scarcity, the high cost of image annotation, and privacy concerns. This research explores the utilization of Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) for tasks including image generation, denoising, scan reconstruction, and the segmentation of anatomical structures. Using the publicly available BRATS2020 dataset, we implemented models such as GANs, VAEs, and the U-Net architecture. Performance was evaluated using metrics including the Structural Similarity Index (SSIM), the Dice Coefficient, and the Fréchet Inception Distance (FID). The results demonstrated a significant improvement in image quality and segmentation accuracy. A primary application was the automation of brain tumor segmentation from MRI scans, a task that is traditionally time-consuming, labor-intensive, and subject to inter-observer variability. This research presents an automated method using a U-Net convolutional neural network, which is specifically designed for biomedical image segmentation. The process involved data preparation, implementation of the U-Net model, and a thorough training phase. The model's performance was assessed using the Dice Similarity Coefficient (DSC) and Intersection over Union (IoU). The U-Net model achieved promising results in accurately segmenting brain tumor regions, demonstrating high potential as an effective tool for automated tumor outlining. On the BRATS2020 test data, the model achieved an accuracy of 99.18%, indicating high efficiency and superior performance compared to current state-of-the-art research. This work contributes to the growing field of deep learning in medical imaging by providing a detailed framework and reproducible results for brain tumor segmentation. Biological sciences/Cancer Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Health sciences/Health care Physical sciences/Mathematics and computing Health sciences/Medical research Brain tumor generative AI deep learning U-Net architecture data segmentation 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-7900791","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":542616737,"identity":"65af3afa-5ef0-42de-b367-1c37205460dd","order_by":0,"name":"Nouran Reda Ragab","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABQklEQVRIie3QsWrCQBjA8e8I1eWiaxxqX+EkIB2keZULgU5SCl2crFD4XGLn+hYpXRwvHOhyrWskS7o4VRC6aDHSi6XQNkIdS8l/uOPu+N3BARQV/cGY2E1bAFFNxLLT0gv+ecj3ktMPIjWhJLxT50B/I60vxJAmygPIxG8u1yNZr0wehaBq6jhlfhSsR12oltsMlm850lTKHg7U1q6pCy6sTuz6NCnNBkpCzX9hZHibJ1HbBhNXbiA4E0zFnFq8FJkogEVtZph+jtiakBTVdTBNmHDxycnILMUuOBlJ86ShiWHimGd3ihAF8TWJTTSAWZrAKk/U+Mo4RtkYRnMe9pTn+uoZY71DLTW/DAe9HGGTmweyQHlSmXryddM5c8p9bzxbYLde7Xv3yWqz96N/RnY302wQBA8i3zrslaKioqJ/3TslJ4UZRM8fvgAAAABJRU5ErkJggg==","orcid":"","institution":"Mansoura University","correspondingAuthor":true,"prefix":"","firstName":"Nouran","middleName":"Reda","lastName":"Ragab","suffix":""},{"id":542616738,"identity":"e92ef48f-9183-4982-9480-6ab18f3251a2","order_by":1,"name":"Rasha H.Sakr","email":"","orcid":"","institution":"Mansoura University","correspondingAuthor":false,"prefix":"","firstName":"Rasha","middleName":"","lastName":"H.Sakr","suffix":""},{"id":542616739,"identity":"94cc5e22-635b-47a2-aee3-78969822ca87","order_by":2,"name":"Amal I.AboElenien","email":"","orcid":"","institution":"Mansoura University","correspondingAuthor":false,"prefix":"","firstName":"Amal","middleName":"","lastName":"I.AboElenien","suffix":""}],"badges":[],"createdAt":"2025-10-19 21:53:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7900791/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7900791/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95797109,"identity":"b0e2a07d-4094-4e78-b02f-d636499a60e5","added_by":"auto","created_at":"2025-11-13 08:01:01","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3006677,"visible":true,"origin":"","legend":"","description":"","filename":"SegmentationofBrainTumorsUsingaGenerativeAIEnhancedUNetModel..docx","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/6387fafbcfea18b978ae9a4d.docx"},{"id":95665453,"identity":"908da162-c52f-40db-b6a8-b7fc0c718c77","added_by":"auto","created_at":"2025-11-11 16:46:15","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5528,"visible":true,"origin":"","legend":"","description":"","filename":"ffe600033a8c4e41b82a560624c725b6.json","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/f61be1bd3466e0f4e1c4c8fe.json"},{"id":95797412,"identity":"d87579d2-83c7-44fb-9bbc-fe83a1888bad","added_by":"auto","created_at":"2025-11-13 08:04:46","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":107405,"visible":true,"origin":"","legend":"","description":"","filename":"ffe600033a8c4e41b82a560624c725b61enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/bd22b1d657e90f66057f7a5e.xml"},{"id":95665445,"identity":"a71ae84b-038a-4505-85d5-330f64f692b7","added_by":"auto","created_at":"2025-11-11 16:46:15","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":22574,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/f86b70c8e494e57c7c0b8b20.png"},{"id":95798475,"identity":"761aea28-8f8a-4499-a2ba-3c41844e4372","added_by":"auto","created_at":"2025-11-13 08:16:51","extension":"jpeg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":340203,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/c978f16abbd2cdcf06332555.jpeg"},{"id":95665446,"identity":"ee73ebe3-055e-41bd-bf1c-1c86a0799e7d","added_by":"auto","created_at":"2025-11-11 16:46:15","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":178754,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/0d53bc263327fe12a58e62d3.png"},{"id":95665451,"identity":"569af5a0-625b-4c6f-84bb-eeb1a86edc27","added_by":"auto","created_at":"2025-11-11 16:46:15","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":208442,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/b8879d6cfd3db90e060f593f.png"},{"id":95797824,"identity":"9dbd0c21-36eb-4eba-95a3-0c0af8367d75","added_by":"auto","created_at":"2025-11-13 08:11:52","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":200119,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/eacd9d5c4961c8f1a91c7f55.png"},{"id":95797530,"identity":"bcf6d672-c1b9-4a25-bca6-9554b0278748","added_by":"auto","created_at":"2025-11-13 08:06:22","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14438,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/af59bafbca0b61e9acd42e95.png"},{"id":95797625,"identity":"ae54c9e0-f0ad-4c66-834c-ebdbbfbee4af","added_by":"auto","created_at":"2025-11-13 08:08:12","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":87153,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage15.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/fc759cf25f7fd951bee402bf.png"},{"id":95665458,"identity":"11770981-472f-4527-9b46-15466434da72","added_by":"auto","created_at":"2025-11-11 16:46:15","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":126228,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage16.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/47d2b218aa5c60b4c551bffc.png"},{"id":95797777,"identity":"c2cf25c7-afed-4f34-a3bc-917ebd3c1ff7","added_by":"auto","created_at":"2025-11-13 08:10:37","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":110160,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage17.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/e88d62b91ee07d8221e01fa3.png"},{"id":95665457,"identity":"6c9efa96-477f-4cf1-b2e4-a44b423de562","added_by":"auto","created_at":"2025-11-11 16:46:15","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20693,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage18.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/a8076c78c58823eeb546d441.png"},{"id":95799018,"identity":"72e154ec-ec1f-47ec-a626-4df0698a97bc","added_by":"auto","created_at":"2025-11-13 08:18:24","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":94527,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage19.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/088d0f0cc927d3db4f48ea9b.png"},{"id":95797397,"identity":"8766f14a-9200-46bb-ac39-c8065b83783f","added_by":"auto","created_at":"2025-11-13 08:04:39","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":125664,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/a661969aea4ed43295e1849f.png"},{"id":95665464,"identity":"09e919c2-adca-4bef-af87-b6186e1d8075","added_by":"auto","created_at":"2025-11-11 16:46:15","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":108453,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage20.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/9697c1dee8947c5b98672a1c.png"},{"id":95665461,"identity":"0d2576d1-ab9b-4f6a-8fe8-0bb5eff38a0e","added_by":"auto","created_at":"2025-11-11 16:46:15","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":210768,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage21.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/7e82d7a597519f1a25d2a0b6.png"},{"id":95798738,"identity":"a2c35d80-498e-4df4-afa7-d55bd7e00576","added_by":"auto","created_at":"2025-11-13 08:17:43","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":234261,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage22.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/8f1e59d00026cba7a0d1a0ee.png"},{"id":95665470,"identity":"97e0d917-d2fe-43d4-86b8-bf59a30caedc","added_by":"auto","created_at":"2025-11-11 16:46:15","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":147877,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage23.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/542b3eedd7cd592113379551.png"},{"id":95798741,"identity":"dc25183d-37c6-4a7e-aab2-535f1dba2aea","added_by":"auto","created_at":"2025-11-13 08:17:43","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":51460,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage24.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/5ab41d6a2d1c65f0f1fe31ee.png"},{"id":95665463,"identity":"14baa39d-8477-465a-9bec-e2a0853d65ec","added_by":"auto","created_at":"2025-11-11 16:46:15","extension":"jpeg","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":484354,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage25.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/41fea8717c029e79835b87d8.jpeg"},{"id":95797775,"identity":"68e1214d-2515-48e7-9826-90491131dd14","added_by":"auto","created_at":"2025-11-13 08:10:35","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":25392,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/b4ada578e337eb868b6f7abb.png"},{"id":95665462,"identity":"0635b126-21f7-4582-a909-11629692b808","added_by":"auto","created_at":"2025-11-11 16:46:15","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":124239,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/bfa0db8e4ca0778327be45de.png"},{"id":95665477,"identity":"9c8457a0-4d7f-4870-8ad7-8dcafb223ccd","added_by":"auto","created_at":"2025-11-11 16:46:16","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":92414,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/018073d7e2da966b7b615ecb.png"},{"id":95665466,"identity":"aea7becc-188a-4f2b-bb4e-26c272a3541e","added_by":"auto","created_at":"2025-11-11 16:46:15","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":61560,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/976d5214fca790f1c8fd8e0d.png"},{"id":95665468,"identity":"c4515e38-dc4a-434b-9c00-c34a5e6a9c81","added_by":"auto","created_at":"2025-11-11 16:46:15","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":106560,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/dc1325dd1b9d023430860958.png"},{"id":95665465,"identity":"09912847-6a22-4ec1-bfa0-404a989f07c2","added_by":"auto","created_at":"2025-11-11 16:46:15","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":76489,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/91da1021cab58d90bdef315e.png"},{"id":95665469,"identity":"f7ca4491-fca5-4484-9bfe-2f48b90a3abf","added_by":"auto","created_at":"2025-11-11 16:46:15","extension":"jpeg","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":294039,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/516add6bf733c242c6b38f8f.jpeg"},{"id":95797739,"identity":"41f56b9d-5062-4b55-b6e3-9c3078034879","added_by":"auto","created_at":"2025-11-13 08:09:56","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20925,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/e0ed0cac1fe85750d8a5e2b2.png"},{"id":95665467,"identity":"5b00a237-2d50-4843-956e-1d644a985da6","added_by":"auto","created_at":"2025-11-11 16:46:15","extension":"png","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":85129,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/2b3e249da322a3c190e1db13.png"},{"id":95665487,"identity":"81e7e538-8706-4dcf-9038-75c9487f590f","added_by":"auto","created_at":"2025-11-11 16:46:16","extension":"png","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40275,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/eb9fb8cbd6221cc7a9a9f1c9.png"},{"id":95665479,"identity":"9a3794e0-f861-49a6-8216-c537650a7497","added_by":"auto","created_at":"2025-11-11 16:46:16","extension":"png","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":31482,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/d0f91905b50efd224590107c.png"},{"id":95665475,"identity":"cf288ae8-7f38-4509-9cd0-cbc991e387cf","added_by":"auto","created_at":"2025-11-11 16:46:16","extension":"png","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":46445,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/b2e4766b36af79a3e507f560.png"},{"id":95665473,"identity":"99964a4f-3f76-4d31-8b76-a65294bc5cd1","added_by":"auto","created_at":"2025-11-11 16:46:15","extension":"png","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12926,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/8e5940283670cae44e306e02.png"},{"id":95665471,"identity":"dce78b01-bcf4-411e-8dd8-a3782845294a","added_by":"auto","created_at":"2025-11-11 16:46:15","extension":"png","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":23672,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage15.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/5e470aebdef8ea527ad48b96.png"},{"id":95797779,"identity":"f4695096-8092-4274-aa91-196df3f98d96","added_by":"auto","created_at":"2025-11-13 08:10:38","extension":"png","order_by":35,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":26730,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage16.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/2e87a108cdc389360186b7e4.png"},{"id":95665478,"identity":"bd259df6-13ed-468a-b9ad-ddca2f1c0ec7","added_by":"auto","created_at":"2025-11-11 16:46:16","extension":"png","order_by":36,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":23612,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage17.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/c05ec432c1e052cb4f26090d.png"},{"id":95798964,"identity":"38a4ace8-4408-453a-b7ff-3432254fbfff","added_by":"auto","created_at":"2025-11-13 08:18:15","extension":"png","order_by":37,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6547,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage18.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/d41e53de4edf32ce3b0e29b3.png"},{"id":95665476,"identity":"f258a4e7-223d-40c0-a2ce-0086e7f43b44","added_by":"auto","created_at":"2025-11-11 16:46:16","extension":"png","order_by":38,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19646,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage19.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/c16e3e4f8d3135f1a61ae8e8.png"},{"id":95665484,"identity":"729253b9-6d5a-4ab4-877e-75916e13ab80","added_by":"auto","created_at":"2025-11-11 16:46:16","extension":"png","order_by":39,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33912,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/a1a0f048305cf75b37259851.png"},{"id":95797453,"identity":"018ee941-8481-45b2-b232-f7957fbbeeb7","added_by":"auto","created_at":"2025-11-13 08:05:29","extension":"png","order_by":40,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16100,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage20.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/56ee89d40fa48e9956d0f8a1.png"},{"id":95665490,"identity":"5b28c634-f199-4509-8c06-31e073498ac5","added_by":"auto","created_at":"2025-11-11 16:46:16","extension":"png","order_by":41,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":51791,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage21.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/43e958b519a193e5912a2842.png"},{"id":95665481,"identity":"e2c00fa6-d377-4ef6-8414-098eef9198ce","added_by":"auto","created_at":"2025-11-11 16:46:16","extension":"png","order_by":42,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28047,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage22.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/a7af11981ff62327699cf02b.png"},{"id":95797621,"identity":"1febcdb4-a773-4afd-a923-da8aa1057935","added_by":"auto","created_at":"2025-11-13 08:08:11","extension":"png","order_by":43,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30791,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage23.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/18f1683e1cc17f429b50152f.png"},{"id":95665492,"identity":"67aed84e-918f-4aaa-8e43-f13f497a93f1","added_by":"auto","created_at":"2025-11-11 16:46:16","extension":"png","order_by":44,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12996,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage24.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/b516dbf4d51f7287c2e70c9f.png"},{"id":95665500,"identity":"93e18fc3-a4f7-40ba-bcba-bbbd1c08afc2","added_by":"auto","created_at":"2025-11-11 16:46:16","extension":"png","order_by":45,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":103258,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage25.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/a862a93fe2b627b8782e1d63.png"},{"id":95799227,"identity":"5e3fb924-0f41-4418-9f32-f6911b3f5375","added_by":"auto","created_at":"2025-11-13 08:19:13","extension":"png","order_by":46,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5883,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/b281ba45701108c785a733b7.png"},{"id":95665496,"identity":"9f065c36-6af9-47e3-9161-ff416e97d795","added_by":"auto","created_at":"2025-11-11 16:46:16","extension":"png","order_by":47,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":26874,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/92af076c8148f9c8e857dafa.png"},{"id":95665489,"identity":"e374a1f0-1370-4cb5-bedb-274f4ad8b82f","added_by":"auto","created_at":"2025-11-11 16:46:16","extension":"png","order_by":48,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":22149,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/b420e3ed552d9ba16a238ff4.png"},{"id":95797791,"identity":"e213cb20-cc3e-48e3-98fa-3b99133d0aaf","added_by":"auto","created_at":"2025-11-13 08:10:53","extension":"png","order_by":49,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13456,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/250d479974283769f1e4d583.png"},{"id":95797672,"identity":"91294d08-62bf-43b1-ac3e-e26656ce7a41","added_by":"auto","created_at":"2025-11-13 08:09:40","extension":"png","order_by":50,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29734,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/c2b6d9f690c28053e1220606.png"},{"id":95797710,"identity":"0cb19111-0a98-4d54-94d5-bd2e0d426361","added_by":"auto","created_at":"2025-11-13 08:09:52","extension":"png","order_by":51,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":18252,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/833cda7468d6a1dbc8b3e10a.png"},{"id":95797741,"identity":"d4b0d066-0863-4de6-ae3f-dffb6ce3fe2e","added_by":"auto","created_at":"2025-11-13 08:10:07","extension":"png","order_by":52,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":101310,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/14682927eac780dc15a1bb14.png"},{"id":95665498,"identity":"42040f46-29f2-48e3-b70a-36e855c29155","added_by":"auto","created_at":"2025-11-11 16:46:16","extension":"xml","order_by":53,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":107403,"visible":true,"origin":"","legend":"","description":"","filename":"ffe600033a8c4e41b82a560624c725b61structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/1a2de8ae17464d09a4f34a81.xml"},{"id":95665488,"identity":"85f2edf3-5808-438d-a8ce-c1b54ba157ae","added_by":"auto","created_at":"2025-11-11 16:46:16","extension":"html","order_by":54,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":122441,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1/c4d752bfdb1c274ffeff5f89.html"},{"id":104287944,"identity":"feade388-71fd-48ff-8cbb-564f6a6796af","added_by":"auto","created_at":"2026-03-10 05:56:11","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1228249,"visible":true,"origin":"","legend":"","description":"","filename":"SegmentationofBrainTumorsUsingaGenerativeAIEnhancedUNetModel..pdf","url":"https://assets-eu.researchsquare.com/files/rs-7900791/v1_covered_81878709-76ec-400d-8a93-9b3027b3bdcd.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Segmentation of Brain Tumors Using a Generative AI-Enhanced U-Net Model","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":"Brain tumor, generative AI, deep learning, U-Net architecture, data segmentation ","lastPublishedDoi":"10.21203/rs.3.rs-7900791/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7900791/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eGenerative AI is significantly transforming medical imaging by helping to overcome major obstacles such as data scarcity, the high cost of image annotation, and privacy concerns. This research explores the utilization of Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) for tasks including image generation, denoising, scan reconstruction, and the segmentation of anatomical structures. Using the publicly available BRATS2020 dataset, we implemented models such as GANs, VAEs, and the U-Net architecture. Performance was evaluated using metrics including the Structural Similarity Index (SSIM), the Dice Coefficient, and the Fr\u0026eacute;chet Inception Distance (FID). The results demonstrated a significant improvement in image quality and segmentation accuracy. A primary application was the automation of brain tumor segmentation from MRI scans, a task that is traditionally time-consuming, labor-intensive, and subject to inter-observer variability. This research presents an automated method using a U-Net convolutional neural network, which is specifically designed for biomedical image segmentation. The process involved data preparation, implementation of the U-Net model, and a thorough training phase. The model's performance was assessed using the Dice Similarity Coefficient (DSC) and Intersection over Union (IoU). The U-Net model achieved promising results in accurately segmenting brain tumor regions, demonstrating high potential as an effective tool for automated tumor outlining. On the BRATS2020 test data, the model achieved an accuracy of 99.18%, indicating high efficiency and superior performance compared to current state-of-the-art research. This work contributes to the growing field of deep learning in medical imaging by providing a detailed framework and reproducible results for brain tumor segmentation.\u003c/p\u003e","manuscriptTitle":"Segmentation of Brain Tumors Using a Generative AI-Enhanced U-Net Model","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-11 16:46:10","doi":"10.21203/rs.3.rs-7900791/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":"03067fa5-1e00-44a0-a910-23fd77665f5b","owner":[],"postedDate":"November 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":57723462,"name":"Biological sciences/Cancer"},{"id":57723463,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":57723464,"name":"Physical sciences/Engineering"},{"id":57723465,"name":"Health sciences/Health care"},{"id":57723466,"name":"Physical sciences/Mathematics and computing"},{"id":57723467,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2026-03-10T05:55:36+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-11 16:46:10","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7900791","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7900791","identity":"rs-7900791","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.