Forecasting Alzheimer’s Disease Progression via Identity-preserved Denoising Diffusion Generative Adversarial Network

Forecasting Alzheimer’s Disease Progression via Identity-preserved Denoising Diffusion Generative Adversarial Network | 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 Forecasting Alzheimer’s Disease Progression via Identity-preserved Denoising Diffusion Generative Adversarial Network Zhuangzhuang Li, Tongtong Che, Shaozhen Yan, Dong Wang, Yong Liu, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7846693/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract Forecasting the progression of Alzheimer’s disease (AD) is essential for evaluating secondary prevention measures thought to modify the disease trajectory. However, accurate prediction of longitudinal MRIs remains challenging, particularly in preserving subject identity, as deep generative models may potentially generate plausible future MRIs of different individuals from a single baseline scan. In the present study, we developed a novel identity-preserved denoising diffusion generative adversarial network (IP-DDGAN) capable of rapidly generating subject-specific longitudinal MRIs conditioned on metadata. Concretely, we developed an identity-preservation strategy with a metadata-guided module and identity-preserved regularization terms to maintain subject identity in synthetic longitudinal MRIs. Furthermore, we comprehensively integrated the morphometrics, subject identity consistency and image-level quality metrics to evaluate the fidelity and biological plausibility of synthetic longitudinal MRIs. The results demonstrate that the synthetic MRIs generated by IP-DDGAN retain biological and disease-related phenotypes, exhibiting sufficient realism to support their application in downstream tasks. Our proposed model is capable of capturing temporal biological and disease-related changes and forecasting the different progression trajectories, including critical transitions from cognitively normal (CN) to mild cognitive impairment (MCI) and from MCI to AD. Biological sciences/Computational biology and bioinformatics Physical sciences/Mathematics and computing Biological sciences/Neuroscience Full Text Additional Declarations No competing interests reported. Supplementary Files supplementmaterials.docx Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 26 Jan, 2026 Reviews received at journal 23 Dec, 2025 Reviews received at journal 16 Dec, 2025 Reviews received at journal 15 Dec, 2025 Reviewers agreed at journal 09 Dec, 2025 Reviewers agreed at journal 08 Dec, 2025 Reviewers agreed at journal 07 Dec, 2025 Reviewers invited by journal 07 Dec, 2025 Editor assigned by journal 16 Oct, 2025 Submission checks completed at journal 16 Oct, 2025 First submitted to journal 13 Oct, 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-7846693","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":545269974,"identity":"f9c0c033-9059-4ee0-806d-3fe450ac2083","order_by":0,"name":"Zhuangzhuang Li","email":"","orcid":"","institution":"Beijing University of Posts and Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Zhuangzhuang","middleName":"","lastName":"Li","suffix":""},{"id":545269976,"identity":"46d86d82-0f1b-446e-a4b8-135bde310632","order_by":1,"name":"Tongtong Che","email":"","orcid":"","institution":"Beijing Normal University","correspondingAuthor":false,"prefix":"","firstName":"Tongtong","middleName":"","lastName":"Che","suffix":""},{"id":545269977,"identity":"7fc1a47e-dba3-49a5-94a0-75d6a74e36c3","order_by":2,"name":"Shaozhen Yan","email":"","orcid":"","institution":"Xuanwu Hospital of Capital Medical University","correspondingAuthor":false,"prefix":"","firstName":"Shaozhen","middleName":"","lastName":"Yan","suffix":""},{"id":545269978,"identity":"a6f6e0d9-fb9d-4b67-ab7f-bae3779df758","order_by":3,"name":"Dong Wang","email":"","orcid":"","institution":"Beijing University of Posts and Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Dong","middleName":"","lastName":"Wang","suffix":""},{"id":545269979,"identity":"4a6f399e-a6c0-4d67-b084-a5eb93bcfb6b","order_by":4,"name":"Yong Liu","email":"","orcid":"","institution":"Beijing University of Posts and Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Yong","middleName":"","lastName":"Liu","suffix":""},{"id":545269980,"identity":"79877dc3-30b8-40bd-acea-96217ffbdc55","order_by":5,"name":"Kun Zhao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA00lEQVRIiWNgGAWjYBACCSBmBmI5AwifmXgtxkAtjA0kaUncQLQWyRm5hz8X1Nikb5fIPf6AocI6sYH97AG8WqQl8hKMZxxLy905Iy+xgeFMemIDT14CXi1yEjkGyTxsh3M33MgxbGBsO5zYIMFjQFDLYZ5/h9MNwFr+EaFFWiLHsJm37XACREsDEVoke94YM/P2pRnu7HmXOCPhWLpxG08Ofi0Sx3OMP/N8s5E3Z8898OFDjbVsP/sZ/FqQAA8DQwKQYiNWPUTLKBgFo2AUjAJsAACxA0G3D2uG3gAAAABJRU5ErkJggg==","orcid":"","institution":"Beijing University of Posts and Telecommunications","correspondingAuthor":true,"prefix":"","firstName":"Kun","middleName":"","lastName":"Zhao","suffix":""}],"badges":[],"createdAt":"2025-10-13 08:53:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7846693/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7846693/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97138947,"identity":"44dd6dd1-fe96-42e8-8bf0-8361e842cd9d","added_by":"auto","created_at":"2025-12-01 09:59:27","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2475332,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-7846693/v1/78219a5dd8a0be4ea012c552.docx"},{"id":97137961,"identity":"d88e4bcf-930a-41cb-a8ee-b6d9748f2306","added_by":"auto","created_at":"2025-12-01 09:58:22","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8105,"visible":true,"origin":"","legend":"","description":"","filename":"cf1afa8b63724080b317aed6b0500737.json","url":"https://assets-eu.researchsquare.com/files/rs-7846693/v1/3f4abb2dd5024e342ffa0fe9.json"},{"id":97139143,"identity":"b3659c21-bb1c-4f1c-b335-f9d7fae81d1e","added_by":"auto","created_at":"2025-12-01 09:59:41","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":281773,"visible":true,"origin":"","legend":"","description":"","filename":"supplementmaterials.docx","url":"https://assets-eu.researchsquare.com/files/rs-7846693/v1/84af8d9b9cbc72222e2c8071.docx"},{"id":96993453,"identity":"da9962ea-3b56-4fdf-b8ff-a07a9622ad98","added_by":"auto","created_at":"2025-11-28 11:52:43","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":141411,"visible":true,"origin":"","legend":"","description":"","filename":"cf1afa8b63724080b317aed6b05007371enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7846693/v1/2375932678ada5f7b1929341.xml"},{"id":96993445,"identity":"fa45066f-b210-4b21-95e6-c4f693863f8b","added_by":"auto","created_at":"2025-11-28 11:52:43","extension":"jpeg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":419005,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7846693/v1/22b31338ff164dde9c84b34b.jpeg"},{"id":96993446,"identity":"dd03f39a-589d-4cfe-b6a9-29c3bf73a7c7","added_by":"auto","created_at":"2025-11-28 11:52:43","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":561062,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7846693/v1/2be9cf4a27013a1f79dd399f.jpeg"},{"id":97139509,"identity":"beb5833c-6ace-4c42-b413-4fcc506275f3","added_by":"auto","created_at":"2025-12-01 10:00:33","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":582674,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7846693/v1/660b02c85cc5293f77c086e5.jpeg"},{"id":97138295,"identity":"6e3159e8-c046-4a4b-b5f9-104ab175499b","added_by":"auto","created_at":"2025-12-01 09:58:44","extension":"jpeg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":203099,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7846693/v1/c236fe61664182ea411ad63a.jpeg"},{"id":96993442,"identity":"d351526e-b7e0-4fda-a45c-fdcfa9f1377e","added_by":"auto","created_at":"2025-11-28 11:52:43","extension":"jpeg","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":597201,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7846693/v1/f6f3e6cdd50b5da2f976a761.jpeg"},{"id":96993450,"identity":"13806ff7-63dd-48af-a6dc-b30dc60f886b","added_by":"auto","created_at":"2025-11-28 11:52:43","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":190545,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7846693/v1/7b960eea44198c50567be0c7.png"},{"id":96993449,"identity":"9b7fb63d-ab80-4e6f-857f-777fdc4c3bc7","added_by":"auto","created_at":"2025-11-28 11:52:43","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":239728,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7846693/v1/015de485e02e5ba4e6102cfd.png"},{"id":97137462,"identity":"1e93c97f-a61a-4486-88d8-20fe9ede9270","added_by":"auto","created_at":"2025-12-01 09:57:48","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":212737,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7846693/v1/15a6afae5b23db3af5eb93d8.png"},{"id":97139184,"identity":"0b06cdfd-a4f9-4fae-901a-d7ed0ac32fd3","added_by":"auto","created_at":"2025-12-01 09:59:43","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":78135,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7846693/v1/1a14cb3593f1200d09f67c13.png"},{"id":96993456,"identity":"dd5411c9-5258-4cdc-bd8e-30f89cc9f042","added_by":"auto","created_at":"2025-11-28 11:52:43","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":250146,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7846693/v1/9fe5f67790c31cd2f4688981.png"},{"id":96993457,"identity":"5b76c1d4-c653-47d3-b448-477e76b2ee14","added_by":"auto","created_at":"2025-11-28 11:52:43","extension":"xml","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":139036,"visible":true,"origin":"","legend":"","description":"","filename":"cf1afa8b63724080b317aed6b05007371structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7846693/v1/2486a43d993501cd9047b797.xml"},{"id":96993458,"identity":"baf8f708-fb6b-4cf8-8cba-2f8f49d72cc7","added_by":"auto","created_at":"2025-11-28 11:52:43","extension":"html","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":159165,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7846693/v1/a09b72c96b58cd799626be51.html"},{"id":97144801,"identity":"aca05d98-34d1-42fa-8e6e-0063b1e49c8c","added_by":"auto","created_at":"2025-12-01 10:12:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1572142,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7846693/v1_covered_4f581b2c-0896-4c0d-9133-12924b8f0dd2.pdf"},{"id":96993448,"identity":"9ae9b82e-380f-45cf-91e5-2745ea7929fb","added_by":"auto","created_at":"2025-11-28 11:52:43","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":281773,"visible":true,"origin":"","legend":"","description":"","filename":"supplementmaterials.docx","url":"https://assets-eu.researchsquare.com/files/rs-7846693/v1/c4357be92301766fa832e64a.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Forecasting Alzheimer’s Disease Progression via Identity-preserved Denoising Diffusion Generative Adversarial Network","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7846693/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7846693/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eForecasting the progression of Alzheimer\u0026rsquo;s disease (AD) is essential for evaluating secondary prevention measures thought to modify the disease trajectory. However, accurate prediction of longitudinal MRIs remains challenging, particularly in preserving subject identity, as deep generative models may potentially generate plausible future MRIs of different individuals from a single baseline scan. In the present study, we developed a novel identity-preserved denoising diffusion generative adversarial network (IP-DDGAN) capable of rapidly generating subject-specific longitudinal MRIs conditioned on metadata. Concretely, we developed an identity-preservation strategy with a metadata-guided module and identity-preserved regularization terms to maintain subject identity in synthetic longitudinal MRIs. Furthermore, we comprehensively integrated the morphometrics, subject identity consistency and image-level quality metrics to evaluate the fidelity and biological plausibility of synthetic longitudinal MRIs. The results demonstrate that the synthetic MRIs generated by IP-DDGAN retain biological and disease-related phenotypes, exhibiting sufficient realism to support their application in downstream tasks. Our proposed model is capable of capturing temporal biological and disease-related changes and forecasting the different progression trajectories, including critical transitions from cognitively normal (CN) to mild cognitive impairment (MCI) and from MCI to AD.\u003c/p\u003e","manuscriptTitle":"Forecasting Alzheimer’s Disease Progression via Identity-preserved Denoising Diffusion Generative Adversarial Network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-28 11:52:38","doi":"10.21203/rs.3.rs-7846693/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-01-27T01:51:55+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-23T16:22:09+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-16T18:26:16+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-16T02:30:44+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"122775504651253031765097486097337302386","date":"2025-12-10T01:35:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"58347910876976144076762976725637220913","date":"2025-12-08T15:13:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"134377250952117008628508836436258403004","date":"2025-12-08T02:29:59+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-08T01:21:47+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-16T14:46:21+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-16T05:11:06+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Digital Medicine","date":"2025-10-13T08:47:42+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"bd2eddcd-e2e7-4006-88e2-9d62193f5b7b","owner":[],"postedDate":"November 28th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":58016164,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":58016165,"name":"Physical sciences/Mathematics and computing"},{"id":58016166,"name":"Biological sciences/Neuroscience"}],"tags":[],"updatedAt":"2026-04-21T09:53:36+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-28 11:52:38","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7846693","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7846693","identity":"rs-7846693","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}