A Multimodal Deep Learning Method Based on Multiple Medical Images for Fuchs Endothelial Corneal Dystrophy Diagnosis

A Multimodal Deep Learning Method Based on Multiple Medical Images for Fuchs Endothelial Corneal Dystrophy 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 Research Article A Multimodal Deep Learning Method Based on Multiple Medical Images for Fuchs Endothelial Corneal Dystrophy Diagnosis En-shuo Liu, Li-li Cao, Jing-hao Qu, Hao-ran Wu, Ge-ge Xiao, Li-xue Shuai, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8473446/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 12 You are reading this latest preprint version Abstract Purpose To establish a multimodal deep learning network for the fully automated diagnosis of Fuchs endothelial corneal dystrophy (FECD). Methods The ResNet-50 neural network was trained and validated using patients with FECD, patients with other anterior segment diseases, and healthy controls. Single-modal and multimodal models were developed on the basis of anterior segment photographs, anterior segment OCT images, and IVCM images. Independent test sets were employed to assess the diagnostic performance of the models, with evaluation metrics including precision, recall, F1 score, and accuracy. Results The multimodal model achieved a precision of 0.9663 and a recall of 0.971, with an F1 score of 0.9685, in distinguishing between FECD, other anterior segment diseases, and healthy eyes at the single-eye level. The diagnostic performance was significantly better than that of single-modal models based on anterior segment photographs (F1 score: 0.8664) and anterior segment OCT (F1 score: 0.8334) but slightly better than that of the single-modal model based on IVCM (F1 score: 0.9537). Conclusion This study presents the first multimodal deep learning model for diagnosing FECD, effectively distinguishing it from healthy corneas and various anterior segment disorders. Translational Relevance: This multimodal AI integrates standard slit-lamp photo, OCT and IVCM inputs to deliver instant, technician-level FECD screening without extra hardware. Embedding the ResNet-50 classifier in EMR or cloud platforms could halve unnecessary corneal referrals and prioritise endothelial transplants before cataract surgery. Fuchs endothelial corneal dystrophy multimodal deep learning artificial intelligence Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 05 Feb, 2026 Reviews received at journal 03 Feb, 2026 Reviews received at journal 31 Jan, 2026 Reviews received at journal 25 Jan, 2026 Reviewers agreed at journal 24 Jan, 2026 Reviewers agreed at journal 23 Jan, 2026 Reviewers agreed at journal 22 Jan, 2026 Reviewers agreed at journal 19 Jan, 2026 Reviewers invited by journal 16 Jan, 2026 Editor assigned by journal 30 Dec, 2025 Submission checks completed at journal 30 Dec, 2025 First submitted to journal 29 Dec, 2025 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-8473446","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":576560084,"identity":"7d9b3f26-077d-4a9a-99f2-4bc12dbb7add","order_by":0,"name":"En-shuo Liu","email":"","orcid":"","institution":"Peking University Third Hospital","correspondingAuthor":false,"prefix":"","firstName":"En-shuo","middleName":"","lastName":"Liu","suffix":""},{"id":576560086,"identity":"4ca2ed3f-4f3d-4c19-946f-a273ff3e6896","order_by":1,"name":"Li-li Cao","email":"","orcid":"","institution":"Institute of Automation","correspondingAuthor":false,"prefix":"","firstName":"Li-li","middleName":"","lastName":"Cao","suffix":""},{"id":576560088,"identity":"e4aaed61-5591-430c-a5d1-907e15ae8de3","order_by":2,"name":"Jing-hao Qu","email":"","orcid":"","institution":"Peking University Third Hospital","correspondingAuthor":false,"prefix":"","firstName":"Jing-hao","middleName":"","lastName":"Qu","suffix":""},{"id":576560089,"identity":"53353439-619b-4273-b052-108bac1c5162","order_by":3,"name":"Hao-ran Wu","email":"","orcid":"","institution":"Institute of Automation","correspondingAuthor":false,"prefix":"","firstName":"Hao-ran","middleName":"","lastName":"Wu","suffix":""},{"id":576560090,"identity":"7d75b173-f3f0-4ad5-9451-eb42ded89316","order_by":4,"name":"Ge-ge Xiao","email":"","orcid":"","institution":"Peking University Third Hospital","correspondingAuthor":false,"prefix":"","firstName":"Ge-ge","middleName":"","lastName":"Xiao","suffix":""},{"id":576560091,"identity":"30206a11-364b-4fc5-a1e4-216c25a96480","order_by":5,"name":"Li-xue Shuai","email":"","orcid":"","institution":"Peking University Third Hospital","correspondingAuthor":false,"prefix":"","firstName":"Li-xue","middleName":"","lastName":"Shuai","suffix":""},{"id":576560092,"identity":"757f7889-055a-421a-a398-2c88e95a355e","order_by":6,"name":"Shao-feng Gu","email":"","orcid":"","institution":"Peking University Third Hospital","correspondingAuthor":false,"prefix":"","firstName":"Shao-feng","middleName":"","lastName":"Gu","suffix":""},{"id":576560093,"identity":"e8d294b9-c9e5-4139-b087-7b46e993281e","order_by":7,"name":"Hai-kun Wang","email":"","orcid":"","institution":"Peking University Third Hospital","correspondingAuthor":false,"prefix":"","firstName":"Hai-kun","middleName":"","lastName":"Wang","suffix":""},{"id":576560094,"identity":"8b95a37e-b31b-410c-8014-2c65f2e0694f","order_by":8,"name":"Ke-chao Zheng","email":"","orcid":"","institution":"Nanjing Artificial Intelligence Research of IA","correspondingAuthor":false,"prefix":"","firstName":"Ke-chao","middleName":"","lastName":"Zheng","suffix":""},{"id":576560095,"identity":"93a693cd-01e3-4b4f-a7dd-5cf075950b5a","order_by":9,"name":"Rong-mei Peng","email":"","orcid":"","institution":"Peking University Third Hospital","correspondingAuthor":false,"prefix":"","firstName":"Rong-mei","middleName":"","lastName":"Peng","suffix":""},{"id":576560096,"identity":"e8a5e4c6-a671-46db-ba7a-76f029dd4ab3","order_by":10,"name":"Jing Hong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAElEQVRIiWNgGAWjYBACAxAhASTZ2JsPGCQY2PDw8zcQqYWP51hCwYeCNBnJGQeI0AICchI5Ch9nfDhsY9CQgF+LOXvv4RcWBXfs2iRyGDfzGJznMWA4wPjhYw5uLZY959IsJAyeJbfxvD1szGNwm8ecuYFZcuY2PA67kWNmIGFwOJmNPS8NrMWy4QAbMy9RWhhyzH/zGJzjMTiQQFCL8QOgFjs2jhwDwxkGB4jQcuaMGTCQDyewAQPZ4INBMo/kjIPN+P1yvMf4s8Sfw/by7aCo/GNnz8/ffPDDRzxagIBNWoKBIbEBIcDYgEspDDB//MDAYE9I1SgYBaNgFIxgAACYWVSQ2WRoXgAAAABJRU5ErkJggg==","orcid":"","institution":"Peking University Third Hospital","correspondingAuthor":true,"prefix":"","firstName":"Jing","middleName":"","lastName":"Hong","suffix":""}],"badges":[],"createdAt":"2025-12-29 13:23:55","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8473446/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8473446/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100796310,"identity":"6e49f57a-6e5f-4cc6-9482-9088360d9ecc","added_by":"auto","created_at":"2026-01-21 13:42:35","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2230628,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/253297ab6a0b3f13fca7c919.docx"},{"id":100643167,"identity":"6bdc01f1-9deb-48e3-b6a7-6eab6ffab201","added_by":"auto","created_at":"2026-01-20 03:48:28","extension":"png","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1762708,"visible":true,"origin":"","legend":"","description":"","filename":"Figure1.png","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/ad969058fbfcdb6c9d3755f0.png"},{"id":100643175,"identity":"1162ba7c-33ce-46b7-8ced-5915f51c3a90","added_by":"auto","created_at":"2026-01-20 03:48:28","extension":"png","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4711531,"visible":true,"origin":"","legend":"","description":"","filename":"Figure2.png","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/ab3739a54704fc4a2065a8a9.png"},{"id":100643170,"identity":"d9faca9c-68b3-40fc-bfbd-5b0b3dd568c0","added_by":"auto","created_at":"2026-01-20 03:48:28","extension":"docx","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17077,"visible":true,"origin":"","legend":"","description":"","filename":"Table1.docx","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/fc46ae143cb89403c17ee8ad.docx"},{"id":100796320,"identity":"06cbbf1c-a85d-419a-8abe-cab59e415956","added_by":"auto","created_at":"2026-01-21 13:42:38","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4736263,"visible":true,"origin":"","legend":"","description":"","filename":"Figure3.png","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/69b2f98935bb8679011fb860.png"},{"id":100796344,"identity":"c061b55e-ae7a-45db-aacb-e7ec89123341","added_by":"auto","created_at":"2026-01-21 13:42:41","extension":"docx","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16702,"visible":true,"origin":"","legend":"","description":"","filename":"Table2.docx","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/53f52ddd5db2dd813bafeae7.docx"},{"id":100803991,"identity":"c15e0748-5e35-4c19-a850-235a744058e2","added_by":"auto","created_at":"2026-01-21 14:33:37","extension":"docx","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16877,"visible":true,"origin":"","legend":"","description":"","filename":"Table3.docx","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/c689b38b3d8800ab9ee74e6a.docx"},{"id":100643172,"identity":"8c228597-7c51-476c-b535-e914fb9bbf18","added_by":"auto","created_at":"2026-01-20 03:48:28","extension":"docx","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16939,"visible":true,"origin":"","legend":"","description":"","filename":"Table4.docx","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/7fb8c9e360c8fb286e62d17a.docx"},{"id":100643177,"identity":"e4782fab-473b-4555-95f5-eb0f5dab62c5","added_by":"auto","created_at":"2026-01-20 03:48:28","extension":"docx","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16902,"visible":true,"origin":"","legend":"","description":"","filename":"Table5.docx","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/a33340661c0c2386821a5db5.docx"},{"id":100643183,"identity":"9d1d373e-93b5-4a23-807a-5d38d257a070","added_by":"auto","created_at":"2026-01-20 03:48:29","extension":"docx","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16799,"visible":true,"origin":"","legend":"","description":"","filename":"Table6.docx","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/d135fe33c6938aa88e18dca7.docx"},{"id":100796180,"identity":"4aa12b8f-0d6a-4503-96c7-53b6a5a69260","added_by":"auto","created_at":"2026-01-21 13:41:25","extension":"json","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":11171,"visible":true,"origin":"","legend":"","description":"","filename":"42710620a7874e6d9cb9a76c11d5e5b7.json","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/2f4068fa5e1de47704a45b59.json"},{"id":100796400,"identity":"6bc0608b-d78c-4771-b34f-a3fc0229e561","added_by":"auto","created_at":"2026-01-21 13:43:02","extension":"xml","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":137094,"visible":true,"origin":"","legend":"","description":"","filename":"42710620a7874e6d9cb9a76c11d5e5b71enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/78d1dc1a4fab5539ba12ca6e.xml"},{"id":100796448,"identity":"38683096-1d87-46bb-8f45-438426762714","added_by":"auto","created_at":"2026-01-21 13:43:12","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1762708,"visible":true,"origin":"","legend":"","description":"","filename":"Figure1.png","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/c987a7717585767ba72fa748.png"},{"id":100643184,"identity":"f455776c-9944-4f70-b9a0-d0e15c07b0fe","added_by":"auto","created_at":"2026-01-20 03:48:29","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4711531,"visible":true,"origin":"","legend":"","description":"","filename":"Figure2.png","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/6d5b469fa53abb20bf32a265.png"},{"id":100643180,"identity":"d78d228d-6fcf-459f-90fb-dffca3d6620a","added_by":"auto","created_at":"2026-01-20 03:48:29","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4736263,"visible":true,"origin":"","legend":"","description":"","filename":"Figure3.png","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/b7e2a13a49583f82a9fd4a49.png"},{"id":100643186,"identity":"c114f490-bcc0-4766-a303-ade6d558ba98","added_by":"auto","created_at":"2026-01-20 03:48:29","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":419630,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/54e5d8b4cf5814efb469d933.png"},{"id":101296550,"identity":"918e614e-89b5-4a50-ba60-9ab6ee3fa6e0","added_by":"auto","created_at":"2026-01-28 09:14:34","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":938516,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/1eaaf21bf7897832499b2a29.png"},{"id":100643182,"identity":"dca66835-3c75-414b-9d86-75df71280a64","added_by":"auto","created_at":"2026-01-20 03:48:29","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":783976,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/25e0d64726117a09474bfb67.png"},{"id":100643188,"identity":"3070bcb5-a5b6-4fc9-b7e3-4aa27be2dc9e","added_by":"auto","created_at":"2026-01-20 03:48:29","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":240655,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure1.png","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/34d9c34f13d61b7c8f4f3f93.png"},{"id":100643193,"identity":"13811396-1682-455a-aa62-55d5adc840f3","added_by":"auto","created_at":"2026-01-20 03:48:30","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":597779,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure2.png","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/7a5e27c04937ff64c82d0454.png"},{"id":100643190,"identity":"23eff90c-6509-4280-ac4b-25914fcd38d8","added_by":"auto","created_at":"2026-01-20 03:48:29","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":668367,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure3.png","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/5d35f5ff3d51921c93cba066.png"},{"id":100796274,"identity":"ae6083d4-1925-4f65-bc1d-2b82385fce66","added_by":"auto","created_at":"2026-01-21 13:42:24","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":87144,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/dc3e5a1be74170e66ea1726e.png"},{"id":100643185,"identity":"f7a5a640-ed1c-496b-b338-7c79c01d56fd","added_by":"auto","created_at":"2026-01-20 03:48:29","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":86732,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/8fbeeba125005b8e2e718243.png"},{"id":100643192,"identity":"a0f32117-66f1-4b8b-8cad-f3a7be1c20f3","added_by":"auto","created_at":"2026-01-20 03:48:29","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":89327,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/59a8de6646e0102f74135fe7.png"},{"id":100643189,"identity":"0e5161ac-4b4d-482d-8ea2-3bee7e68e19e","added_by":"auto","created_at":"2026-01-20 03:48:29","extension":"xml","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":136024,"visible":true,"origin":"","legend":"","description":"","filename":"42710620a7874e6d9cb9a76c11d5e5b71structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/fd3ed3dc88bbe0fc9ac507ee.xml"},{"id":100796509,"identity":"6c358d39-f911-4afc-bbcb-4a220eb021df","added_by":"auto","created_at":"2026-01-21 13:43:49","extension":"html","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":151565,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1/b5957a9a81aaa826add66e5c.html"},{"id":101298875,"identity":"2cea03d5-f634-48d4-91aa-cf6a97a7dc1d","added_by":"auto","created_at":"2026-01-28 09:36:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":746397,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8473446/v1_covered_d3fb8ee4-4eac-456e-ad71-6194e32a5d70.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Multimodal Deep Learning Method Based on Multiple Medical Images for Fuchs Endothelial Corneal Dystrophy Diagnosis","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"bmc-ophthalmology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"boph","sideBox":"Learn more about [BMC Ophthalmology](http://bmcophthalmol.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/boph","title":"BMC Ophthalmology","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Fuchs endothelial corneal dystrophy, multimodal, deep learning, artificial intelligence","lastPublishedDoi":"10.21203/rs.3.rs-8473446/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8473446/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003ePurpose\u003c/h2\u003e \u003cp\u003eTo establish a multimodal deep learning network for the fully automated diagnosis of Fuchs endothelial corneal dystrophy (FECD).\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eThe ResNet-50 neural network was trained and validated using patients with FECD, patients with other anterior segment diseases, and healthy controls. Single-modal and multimodal models were developed on the basis of anterior segment photographs, anterior segment OCT images, and IVCM images. Independent test sets were employed to assess the diagnostic performance of the models, with evaluation metrics including precision, recall, F1 score, and accuracy.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eThe multimodal model achieved a precision of 0.9663 and a recall of 0.971, with an F1 score of 0.9685, in distinguishing between FECD, other anterior segment diseases, and healthy eyes at the single-eye level. The diagnostic performance was significantly better than that of single-modal models based on anterior segment photographs (F1 score: 0.8664) and anterior segment OCT (F1 score: 0.8334) but slightly better than that of the single-modal model based on IVCM (F1 score: 0.9537).\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eThis study presents the first multimodal deep learning model for diagnosing FECD, effectively distinguishing it from healthy corneas and various anterior segment disorders.\u003c/p\u003e\u003ch2\u003eTranslational Relevance:\u003c/h2\u003e \u003cp\u003eThis multimodal AI integrates standard slit-lamp photo, OCT and IVCM inputs to deliver instant, technician-level FECD screening without extra hardware. Embedding the ResNet-50 classifier in EMR or cloud platforms could halve unnecessary corneal referrals and prioritise endothelial transplants before cataract surgery.\u003c/p\u003e","manuscriptTitle":"A Multimodal Deep Learning Method Based on Multiple Medical Images for Fuchs Endothelial Corneal Dystrophy Diagnosis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-20 03:48:23","doi":"10.21203/rs.3.rs-8473446/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-05T06:24:05+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-03T19:24:33+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-31T17:58:24+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-25T06:32:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"260137515175140727744916415281925975240","date":"2026-01-24T17:50:46+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"131431102294168549855508134992146426881","date":"2026-01-23T19:39:48+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"22332504528474886109273224404282023526","date":"2026-01-23T03:38:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"327043666767689786839546873782932086192","date":"2026-01-19T06:13:57+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-01-16T10:13:00+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-31T03:10:38+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-12-31T03:09:46+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Ophthalmology","date":"2025-12-29T13:12:08+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-ophthalmology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"boph","sideBox":"Learn more about [BMC Ophthalmology](http://bmcophthalmol.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/boph","title":"BMC Ophthalmology","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"c8e346cf-ef81-4727-a761-3643161f3901","owner":[],"postedDate":"January 20th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-05-06T07:54:49+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-20 03:48:23","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8473446","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8473446","identity":"rs-8473446","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}