Comparative Evaluation of U-Net-Based Conditioned Diffusion Model and Cycle-GAN for Unpaired CT-MRI Brain Image Synthesis with XAI Validation

Comparative Evaluation of U-Net-Based Conditioned Diffusion Model and Cycle-GAN for Unpaired CT-MRI Brain Image Synthesis with XAI Validation | 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 Comparative Evaluation of U-Net-Based Conditioned Diffusion Model and Cycle-GAN for Unpaired CT-MRI Brain Image Synthesis with XAI Validation Atantra Das Gupta, Yashpal Yadav, N Khandelwal This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8458482/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 Imaging pipelines in healthcare are often limited by reliance on a single imaging modality. Patients with metal implants or pacemakers cannot undergo MRI scans. Emergency stroke diagnostics typically depend solely on quick CT scans. Pediatric cases prefer lower radiation, ruling out multimodal imaging. In these situations, cross-modal image synthesis has become an appealing approach for generating one modality from another, particularly in brain imaging, such as converting CT to MRI and vice versa, where pairwise alignment poses challenges. The study evaluated two advanced models for unpaired CT and MRI brain image synthesis: the Conditioned diffusion model and Cycle-GAN, both built on the same U-Net architecture. Different training approaches were used—iterative denoising for the diffusion model and adversarial training for Cycle-GAN—to compare their effectiveness. Both models were trained for 2000 epochs and evaluated using task-specific metrics, including Fréchet Inception Distance, Inception Score, LPIPS, and the Dice index for tissue segmentation. The conditioned diffusion model consistently outperformed the adversarial model across all performance metrics, reducing the FID score by 39.5%, increasing the IS score by 19.0%, and enhancing anatomical fidelity. Explainability analyses revealed an over 18-fold increase in attention to relevant anatomical regions, with a 48% reduction in attention to less important areas. Radiologists confirmed that the diffusion model offered more realistic images, greater diagnostic confidence, and higher Turing test scores. Although computationally more intensive, the diffusion model demonstrated stronger alignment with actual anatomical features and medical standards. Health sciences/Health care/Medical imaging/Brain imaging Health sciences/Anatomy/Nervous system/Brain Full Text Additional Declarations Ethics and Consent Statement The Jordan University Hospital MR-CT Brain Dataset has been collected with Institutional Review Board (IRB) approval (IRB no. 16/161/2020) and patient consent. All procedures have been carried out in accordance with the World Medical Association's Code of Ethics (Declaration of Helsinki). Data Availability The study utilized open-source data from the Jordan University Hospital. The original data is available via the Unpaired MR-CT Brain Dataset for Unsupervised Image Translation (Mendeley Data). There is NO Competing Interest. 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-8458482","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":571126160,"identity":"a597244a-0e93-43de-998d-c89de76e1515","order_by":0,"name":"Atantra Das Gupta","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0ElEQVRIiWNgGAWjYBADxn4QmVBAjFo2ID4A1DKzAaTFgBQtGw6AeMRo4Z/f/Ozxxz12spvPr0788MCAQZ5f7AB+LRLH2MwNDjxLNt524+1mCaDDDGfOTiBgzTEGM4kDB5gTt904uwGkJcHgNgEt8sfYvwG11CdunnF28w+itBgc4wHZcjhxA3/vNuJsMTyWUyZx5sBx4xk3eLdZJBhIEPaL3OHj2yQqDlTL9vef3XzzR4WNPL80AS0IIAFWKUGschDgP0CK6lEwCkbBKBhJAADeaUoF08IsWAAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-0593-2582","institution":"NIMS, Rajasthan","correspondingAuthor":true,"prefix":"","firstName":"Atantra","middleName":"Das","lastName":"Gupta","suffix":""},{"id":571126161,"identity":"f00d1af5-3492-422a-8adc-6c32029dfe0b","order_by":1,"name":"Yashpal Yadav","email":"","orcid":"","institution":"NIMS University","correspondingAuthor":false,"prefix":"","firstName":"Yashpal","middleName":"","lastName":"Yadav","suffix":""},{"id":571126162,"identity":"e82e735c-2b21-432b-917f-746d7e1c9397","order_by":2,"name":"N Khandelwal","email":"","orcid":"","institution":"NIMS University","correspondingAuthor":false,"prefix":"","firstName":"N","middleName":"","lastName":"Khandelwal","suffix":""}],"badges":[],"createdAt":"2025-12-27 04:20:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8458482/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8458482/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":99770878,"identity":"85db6f6b-f359-4a10-85ef-486d646be2ff","added_by":"auto","created_at":"2026-01-08 08:54:09","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37479302,"visible":true,"origin":"","legend":"","description":"","filename":"DSVsCycleGANmanuscriptforNatureBE.docx","url":"https://assets-eu.researchsquare.com/files/rs-8458482/v1/144c32c41f962c949df1216a.docx"},{"id":99770876,"identity":"f5608611-f094-4542-98b3-00a8c511ea9d","added_by":"auto","created_at":"2026-01-08 08:54:09","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5200,"visible":true,"origin":"","legend":"","description":"","filename":"COMMSMED260068T.json","url":"https://assets-eu.researchsquare.com/files/rs-8458482/v1/e11c5f7cdceb2876bf458897.json"},{"id":100368314,"identity":"5bbfa1c3-79d3-405e-b4e1-deac4dd10803","added_by":"auto","created_at":"2026-01-16 07:57:50","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2475231,"visible":true,"origin":"","legend":"","description":"","filename":"DSVsCycleGANmanuscriptforNatureBE.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8458482/v1_covered_1a70bcf0-a6c6-47d3-a6c9-6ed82fa91fe6.pdf"}],"financialInterests":"\u003cp\u003eEthics and Consent Statement The Jordan University Hospital MR-CT Brain Dataset has been collected with Institutional Review Board (IRB) approval (IRB no. 16/161/2020) and patient consent. All procedures have been carried out in accordance with the World Medical Association's Code of Ethics (Declaration of Helsinki). Data Availability The study utilized open-source data from the Jordan University Hospital. The original data is available via the Unpaired MR-CT Brain Dataset for Unsupervised Image Translation (Mendeley Data).\u003c/p\u003e\n\u003cp\u003eThere is \u003cstrong\u003eNO\u003c/strong\u003e Competing Interest.\u003c/p\u003e","formattedTitle":"Comparative Evaluation of U-Net-Based Conditioned Diffusion Model and Cycle-GAN for Unpaired CT-MRI Brain Image Synthesis with XAI Validation","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"","lastPublishedDoi":"10.21203/rs.3.rs-8458482/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8458482/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Imaging pipelines in healthcare are often limited by reliance on a single imaging modality. Patients with metal implants or pacemakers cannot undergo MRI scans. Emergency stroke diagnostics typically depend solely on quick CT scans. Pediatric cases prefer lower radiation, ruling out multimodal imaging. In these situations, cross-modal image synthesis has become an appealing approach for generating one modality from another, particularly in brain imaging, such as converting CT to MRI and vice versa, where pairwise alignment poses challenges.\r\n The study evaluated two advanced models for unpaired CT and MRI brain image synthesis: the Conditioned diffusion model and Cycle-GAN, both built on the same U-Net architecture. Different training approaches were used—iterative denoising for the diffusion model and adversarial training for Cycle-GAN—to compare their effectiveness. Both models were trained for 2000 epochs and evaluated using task-specific metrics, including Fréchet Inception Distance, Inception Score, LPIPS, and the Dice index for tissue segmentation.\r\nThe conditioned diffusion model consistently outperformed the adversarial model across all performance metrics, reducing the FID score by 39.5%, increasing the IS score by 19.0%, and enhancing anatomical fidelity. Explainability analyses revealed an over 18-fold increase in attention to relevant anatomical regions, with a 48% reduction in attention to less important areas. Radiologists confirmed that the diffusion model offered more realistic images, greater diagnostic confidence, and higher Turing test scores. Although computationally more intensive, the diffusion model demonstrated stronger alignment with actual anatomical features and medical standards.","manuscriptTitle":"Comparative Evaluation of U-Net-Based Conditioned Diffusion Model and Cycle-GAN for Unpaired CT-MRI Brain Image Synthesis with XAI Validation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-08 08:53:12","doi":"10.21203/rs.3.rs-8458482/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":"ad6b1837-8c7f-4933-afa8-2622ea293046","owner":[],"postedDate":"January 8th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":60776051,"name":"Health sciences/Health care/Medical imaging/Brain imaging"},{"id":60776052,"name":"Health sciences/Anatomy/Nervous system/Brain"}],"tags":[],"updatedAt":"2026-01-13T17:01:27+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-08 08:53:12","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8458482","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8458482","identity":"rs-8458482","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}