Enhancing pix2pix with Swin Transformer for Cross Modal Brain CT-MR synthesis

Enhancing pix2pix with Swin Transformer for Cross Modal Brain CT-MR synthesis | 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 Enhancing pix2pix with Swin Transformer for Cross Modal Brain CT-MR synthesis Mario Verdicchio, Francesco Isgrò, Marco Salvatore, Marco Aiello This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7565545/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 Cross-modal medical image synthesis, such as generating a brain computed tomography (CT) from a magnetic resonance (MR) and vice versa, plays an increasingly crucial role in the management of cerebral diseases. Conventional CNN-based models, such as pix2pix, have demonstrated utility in this domain but are limited in capturing long-range dependencies and global anatomical context, often compromising fidelity. This study introduces an enhanced image-to-image translation framework that replaces the standard U-Net generator in pix2pix with SwinUNETR, a transformer-based architecture. Leveraging hierarchical self-attention mechanisms, the model effectively captures both local and global features, enabling the synthesis of anatomically realistic images. The framework was evaluated on CT-to-MR (sMR) and MR-to-CT (sCT) synthesis tasks using 2,091 paired CT and T1-weighted MR scans from public datasets (OASIS-3, SynthRAD2023) and an internal cohort of patients with neurodegenerative disorders. Quantitative metrics, including Multi-Scale Structural Similarity (MS-SSIM) and Peak Signal-to-Noise Ratio (PSNR), were used to benchmark performance against a pix2pix baseline.The proposed method consistently outperformed the baseline, achieving an MS-SSIM of 0.952 and a PSNR of 26.07 dB in sCT. In sMR, it achieved an MS-SSIM of 0.948 and a PSNR of 26.07 dB, while preserving gray–white matter contrast—an essential feature for the assessment of neurodegenerative diseases. These results highlight the potential of Transformer-based architectures like SwinUNETR to advance high-fidelity cross-modal synthesis, particularly in neurological applications. 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-7565545","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":520041317,"identity":"554cf4e2-a2b1-4b8c-96a3-1ce41c5cbda9","order_by":0,"name":"Mario Verdicchio","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDElEQVRIiWNgGAWjYJCCAxAqsYGBsUGCgR/EfgAUZCNai2QDkJ0A0oJPDwQkMAC1MDAYHIBqwWWNbvvZhwc+MByWM29Pbvzwc4eFnPH5M2YPEmruMPDJN2DVYnYm3eDgDIbDxjJnHjZL9p6RMDa7kWNukHDsGU6HmR1IYzjMw5CWOEMisY2ZsU0icdsNHjOJBLbDuLWcfwbWUg/Xsrn/DFDLPzxaboBtsUmQgGnZwJBjBmTj0/KM4eAMAxvDGTwgv7RJGEvcSCuTSOx7xsPGloDDYWnMHz5USMhLsKc//PCzrU6Ov//wNokP3+7IyTcfwG4NGBig8DjAXB486jEA+wNSVI+CUTAKRsHwBwCl/1z+L72T3gAAAABJRU5ErkJggg==","orcid":"","institution":"IRCCS SYNLAB SDN","correspondingAuthor":true,"prefix":"","firstName":"Mario","middleName":"","lastName":"Verdicchio","suffix":""},{"id":520041318,"identity":"da787b4b-6bcb-467c-9587-d5db69847742","order_by":1,"name":"Francesco Isgrò","email":"","orcid":"","institution":"University of Naples Federico II","correspondingAuthor":false,"prefix":"","firstName":"Francesco","middleName":"","lastName":"Isgrò","suffix":""},{"id":520041319,"identity":"8e756360-d2a6-4e9a-84c2-63d7a4b642ff","order_by":2,"name":"Marco Salvatore","email":"","orcid":"","institution":"IRCCS SYNLAB SDN","correspondingAuthor":false,"prefix":"","firstName":"Marco","middleName":"","lastName":"Salvatore","suffix":""},{"id":520041320,"identity":"11272a3c-2cb1-4fb6-a659-4c76685ba5b8","order_by":3,"name":"Marco Aiello","email":"","orcid":"","institution":"IRCCS SYNLAB SDN","correspondingAuthor":false,"prefix":"","firstName":"Marco","middleName":"","lastName":"Aiello","suffix":""}],"badges":[],"createdAt":"2025-09-08 14:53:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7565545/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7565545/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92145769,"identity":"f2a1623b-06bb-4142-9a0f-fc0e132a6eb2","added_by":"auto","created_at":"2025-09-25 07:07:09","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5861,"visible":true,"origin":"","legend":"","description":"","filename":"adbea05d228f4a238e7ff92b47930963.json","url":"https://assets-eu.researchsquare.com/files/rs-7565545/v1/631616f88803f607704286aa.json"},{"id":94598050,"identity":"c2be2f77-494c-41c6-8052-55f3472b87e9","added_by":"auto","created_at":"2025-10-28 18:51:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3053130,"visible":true,"origin":"","legend":"","description":"","filename":"Enhancingpix2pixwithSwinTransformerforCrossModalCTMRBrainsynthesis.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7565545/v1_covered_403c0c61-c7f1-4bbe-889b-1fa28ed1034e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhancing pix2pix with Swin Transformer for Cross Modal Brain CT-MR synthesis","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-7565545/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7565545/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eCross-modal medical image synthesis, such as generating a brain computed tomography (CT) from a magnetic resonance (MR) and vice versa, plays an increasingly crucial role in the management of cerebral diseases. Conventional CNN-based models, such as pix2pix, have demonstrated utility in this domain but are limited in capturing long-range dependencies and global anatomical context, often compromising fidelity.\u003c/p\u003e\n\u003cp\u003eThis study introduces an enhanced image-to-image translation framework that replaces the standard U-Net generator in pix2pix with SwinUNETR, a transformer-based architecture. Leveraging hierarchical self-attention mechanisms, the model effectively captures both local and global features, enabling the synthesis of anatomically realistic images.\u003c/p\u003e\n\u003cp\u003eThe framework was evaluated on CT-to-MR (sMR) and MR-to-CT (sCT) synthesis tasks using 2,091 paired CT and T1-weighted MR scans from public datasets (OASIS-3, SynthRAD2023) and an internal cohort of patients with neurodegenerative disorders. Quantitative metrics, including Multi-Scale Structural Similarity (MS-SSIM) and Peak Signal-to-Noise Ratio (PSNR), were used to benchmark performance against a pix2pix baseline.The proposed method consistently outperformed the baseline, achieving an MS-SSIM of 0.952 and a PSNR of 26.07 dB in sCT. In sMR, it achieved an MS-SSIM of 0.948 and a PSNR of 26.07 dB, while preserving gray–white matter contrast—an essential feature for the assessment of neurodegenerative diseases.\u003c/p\u003e\n\u003cp\u003eThese results highlight the potential of Transformer-based architectures like SwinUNETR to advance high-fidelity cross-modal synthesis, particularly in neurological applications.\u003c/p\u003e","manuscriptTitle":"Enhancing pix2pix with Swin Transformer for Cross Modal Brain CT-MR synthesis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-25 07:07:04","doi":"10.21203/rs.3.rs-7565545/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":"bf7f2ed4-3ef6-4f2c-a019-b5557096fadb","owner":[],"postedDate":"September 25th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-10-28T18:10:32+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-25 07:07:04","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7565545","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7565545","identity":"rs-7565545","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}