SyndMobile: A Hybrid MobileViT-GAN Framework for TCM Syndrome Differentiation in Infertility Diagnosis

SyndMobile: A Hybrid MobileViT-GAN Framework for TCM Syndrome Differentiation in Infertility Diagnosis | 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 SyndMobile: A Hybrid MobileViT-GAN Framework for TCM Syndrome Differentiation in Infertility Diagnosis ZHU Zijing, XU Tiancheng, XIA Youbing This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7396691/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 Infertility affects approximately one-sixth of the global reproductive-age population (WHO, 2024), highlighting the urgent need for precise and early diagnosis. Traditional Chinese Medicine (TCM) provides a holistic framework for syndrome differentiation but is hindered by subjectivity, unquantifiable criteria, and diagnostic inefficiency. Objective: To develop an efficient, interpretable, and resource-friendly AI model capable of fine-grained classification of TCM syndromes in infertility diagnostics. Methods: We propose SyndMobile, a lightweight framework integrating a MobileViT-based hybrid architecture that fuses local (CNN) and global (Transformer) features. The model incorporates self-supervised pretraining, cascaded classification layers, and a generative adversarial network (GAN) module for adversarial data augmentation. Attention mechanisms are used to capture diffuse pathological features characteristic of composite syndromes. The model was evaluated on a 12-class classification task covering 3 pathology types and 4 TCM syndromes. Results: SyndMobile achieved an accuracy of 72.33% on the 12-class task, outperforming nine other lightweight models, with only 4.95 million parameters and an inference time of 45 seconds per image. The model demonstrated clinician-level interpretability and practical suitability for resource-constrained medical environments. Conclusion: SyndMobile offers a promising solution for standardized and efficient TCM syndrome diagnosis in infertility cases, combining the interpretability and holistic focus of TCM with the robustness and efficiency of modern AI techniques. Its lightweight design and high accuracy make it particularly suitable for deployment in low-resource healthcare settings. Biological sciences/Computational biology and bioinformatics Health sciences/Diseases Health sciences/Health care Physical sciences/Mathematics and computing Health sciences/Medical research Full Text Additional Declarations No competing interests reported. Supplementary Files data.rar 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-7396691","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":519180185,"identity":"eae429ce-7a3f-4ac8-94e8-4460540b5e07","order_by":0,"name":"ZHU Zijing","email":"","orcid":"","institution":"Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"ZHU","middleName":"","lastName":"Zijing","suffix":""},{"id":519180190,"identity":"6e6e3a3b-c5f9-4a37-aed7-9cc1876173c6","order_by":1,"name":"XU Tiancheng","email":"","orcid":"","institution":"Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"XU","middleName":"","lastName":"Tiancheng","suffix":""},{"id":519180192,"identity":"61c8315f-062d-4127-8d61-01dd437345a4","order_by":2,"name":"XIA Youbing","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8klEQVRIiWNgGAWjYFACHgaJhAobOX4GhgSIwAFitDw4k2Ys2UCKFsmHbYcSN8BVEtJicCP34I3EtgPGxrcbnkn8zGGQ47uRwPi5AI8WyRl5yRYJ5+7Imd05kCbZu43BWPJGArP0DDxa+CVyzCQSyp4Zm91ISJNm3MaQuOFGAhszDx4tbGAtbIcTN8+AaKknqAViS9vhxA0SEC0JBoS0SPa8A/oFGMgSNxKSLXu3SRjOPPOwWRqfFoPjuQdv/gBF5YycxBs/t9nI8x1PPvgZnxYGgQQYiwfEkgBixgZ8GoCeOQBjsR/ArWoUjIJRMApGNAAAkOZREbgHIrEAAAAASUVORK5CYII=","orcid":"","institution":"Nanjing University of Chinese Medicine","correspondingAuthor":true,"prefix":"","firstName":"XIA","middleName":"","lastName":"Youbing","suffix":""}],"badges":[],"createdAt":"2025-08-18 07:08:45","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7396691/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7396691/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104891182,"identity":"10b111da-7fe6-436b-bd2c-67cd02186d85","added_by":"auto","created_at":"2026-03-18 10:43:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":21840736,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7396691/v1_covered_901cf342-a0e7-4b38-93c3-7cf1dbc2ba90.pdf"},{"id":92076798,"identity":"bb8e62d7-d452-44e1-a20f-6b49e2c58a6a","added_by":"auto","created_at":"2025-09-24 11:05:31","extension":"rar","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":684902733,"visible":true,"origin":"","legend":"","description":"","filename":"data.rar","url":"https://assets-eu.researchsquare.com/files/rs-7396691/v1/96c2a08230c75cbb6bcbc9fb.rar"}],"financialInterests":"No competing interests reported.","formattedTitle":"SyndMobile: A Hybrid MobileViT-GAN Framework for TCM Syndrome Differentiation in Infertility Diagnosis","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":"","lastPublishedDoi":"10.21203/rs.3.rs-7396691/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7396691/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Infertility affects approximately one-sixth of the global reproductive-age population (WHO, 2024), highlighting the urgent need for precise and early diagnosis. Traditional Chinese Medicine (TCM) provides a holistic framework for syndrome differentiation but is hindered by subjectivity, unquantifiable criteria, and diagnostic inefficiency. Objective: To develop an efficient, interpretable, and resource-friendly AI model capable of fine-grained classification of TCM syndromes in infertility diagnostics. Methods: We propose SyndMobile, a lightweight framework integrating a MobileViT-based hybrid architecture that fuses local (CNN) and global (Transformer) features. The model incorporates self-supervised pretraining, cascaded classification layers, and a generative adversarial network (GAN) module for adversarial data augmentation. Attention mechanisms are used to capture diffuse pathological features characteristic of composite syndromes. The model was evaluated on a 12-class classification task covering 3 pathology types and 4 TCM syndromes. Results: SyndMobile achieved an accuracy of 72.33% on the 12-class task, outperforming nine other lightweight models, with only 4.95 million parameters and an inference time of 45 seconds per image. The model demonstrated clinician-level interpretability and practical suitability for resource-constrained medical environments. Conclusion: SyndMobile offers a promising solution for standardized and efficient TCM syndrome diagnosis in infertility cases, combining the interpretability and holistic focus of TCM with the robustness and efficiency of modern AI techniques. Its lightweight design and high accuracy make it particularly suitable for deployment in low-resource healthcare settings.","manuscriptTitle":"SyndMobile: A Hybrid MobileViT-GAN Framework for TCM Syndrome Differentiation in Infertility Diagnosis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-24 11:04:53","doi":"10.21203/rs.3.rs-7396691/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":"68550fe6-2ba8-43c2-8778-a4627483b9f1","owner":[],"postedDate":"September 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":55166755,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":55166756,"name":"Health sciences/Diseases"},{"id":55166757,"name":"Health sciences/Health care"},{"id":55166758,"name":"Physical sciences/Mathematics and computing"},{"id":55166759,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2026-03-18T10:41:56+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-24 11:04:53","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7396691","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7396691","identity":"rs-7396691","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}