DAGM-Net: A Dynamic Adaptive Graph and Multi-scale Network for Accurate Jaw Cyst Segmentation

DAGM-Net: A Dynamic Adaptive Graph and Multi-scale Network for Accurate Jaw Cyst Segmentation | 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 DAGM-Net: A Dynamic Adaptive Graph and Multi-scale Network for Accurate Jaw Cyst Segmentation Chongwu Liu, Chunhua Lin, Xiapei Wang, Xiaofei Zhang, Tenteng Zhang, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7479498/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 6 You are reading this latest preprint version Abstract Accurate diagnosis and segmentation of jaw cysts hold substantial clinical significance; however, current deep learning approaches often struggle to capture complex anatomical structures and handle contextual variability. To address these challenges, this paper introduces a novel Dynamic Adaptive Graph and Multi-scale Network (DAGM-Net), which incorporates several innovative layers designed to enhance segmentation performance. Firstly, the Dynamic Graph Topology Learning (DGTL) layer adaptively constructs graph connectivity based on node feature similarity, enabling the model to better capture semantic relationships within the data. Next, the Residual Graph Convolution with Feature Rectification (RGC-FR) layer propagates node information through a three-stage feature rectification process, effectively compensating for feature loss and improving discriminative representation. Additionally, the Progressive Multi-scale Aggregation (PMA) layer hierarchically fuses multi-scale encoder features, thereby enriching contextual information and increasing representational power. To further strengthen optimization, a unified loss with momentum-based adaptive weighting is employed to dynamically balance multiple objectives and promote stable training. Comprehensive evaluations on benchmark datasets demonstrate that DAGM-Net achieves effective improvements in jaw cyst segmentation compared to existing methods. Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Physical sciences/Mathematics and computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 18 May, 2026 Reviewers invited by journal 29 Sep, 2025 Editor assigned by journal 19 Sep, 2025 Editor invited by journal 10 Sep, 2025 Submission checks completed at journal 09 Sep, 2025 First submitted to journal 09 Sep, 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-7479498","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":526861338,"identity":"6eee52a7-42c9-4eb7-ad4d-3f2fcaaf22d8","order_by":0,"name":"Chongwu Liu","email":"","orcid":"","institution":"Fujian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Chongwu","middleName":"","lastName":"Liu","suffix":""},{"id":526861339,"identity":"522884a9-97e0-4907-aead-a4e01235dec7","order_by":1,"name":"Chunhua Lin","email":"","orcid":"","institution":"Fujian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Chunhua","middleName":"","lastName":"Lin","suffix":""},{"id":526861340,"identity":"d81fe5fa-f0d8-4b75-9b01-5aaa5b07b865","order_by":2,"name":"Xiapei Wang","email":"","orcid":"","institution":"Fujian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Xiapei","middleName":"","lastName":"Wang","suffix":""},{"id":526861341,"identity":"b3318ae0-f77d-477a-a3dc-43f1c573152a","order_by":3,"name":"Xiaofei Zhang","email":"","orcid":"","institution":"Xiamen University","correspondingAuthor":false,"prefix":"","firstName":"Xiaofei","middleName":"","lastName":"Zhang","suffix":""},{"id":526861342,"identity":"c422d7ab-c548-441d-8414-edcbcf3d5dad","order_by":4,"name":"Tenteng Zhang","email":"","orcid":"","institution":"Xiamen University","correspondingAuthor":false,"prefix":"","firstName":"Tenteng","middleName":"","lastName":"Zhang","suffix":""},{"id":526861344,"identity":"7b97c8df-0a6d-49a1-a146-d05a9c59c2a4","order_by":5,"name":"Hao Lin","email":"","orcid":"","institution":"Xiamen University","correspondingAuthor":false,"prefix":"","firstName":"Hao","middleName":"","lastName":"Lin","suffix":""},{"id":526861347,"identity":"540ecdd8-0699-4e37-9c17-a77d551b35d4","order_by":6,"name":"Xiaodian Xiong","email":"","orcid":"","institution":"Xiamen University","correspondingAuthor":false,"prefix":"","firstName":"Xiaodian","middleName":"","lastName":"Xiong","suffix":""},{"id":526861349,"identity":"a38a2209-447a-4c4d-8148-60f7c0e45352","order_by":7,"name":"Yue Huang","email":"","orcid":"","institution":"Fujian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yue","middleName":"","lastName":"Huang","suffix":""},{"id":526861351,"identity":"d20b0ef8-5077-43ee-838b-85ef8ba71e3a","order_by":8,"name":"Chunfang Wu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6klEQVRIiWNgGAWjYHACNiCWA2LmAx8kwAIJRGkxBtGJM0jVwmM4g4EYLQY3kp895t1hIG/Ov+Zjg2XOYQZ+9hwDhp878GlJMzfmPWNguHPG240NktsOM0j2vDFg7D2DW4vZjRw2ad62P4wbbpzd/gCkxeBGjgEzYxtBLQb2G26ceQi2xZ5YLYkbzvcwgrUYSBDQYn/mmZnk3DaD5A032AyBWtJ5JM48KzjYi0eLZHvyM4m3bQa2G84fftgsuc1ajr89eeODn3i0IIBEAgMzMCp5QOwDxGhgYOA/wMD4gTilo2AUjIJRMMIAACQ4U7HSWPBkAAAAAElFTkSuQmCC","orcid":"","institution":"Fujian Medical University","correspondingAuthor":true,"prefix":"","firstName":"Chunfang","middleName":"","lastName":"Wu","suffix":""}],"badges":[],"createdAt":"2025-08-28 10:53:40","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7479498/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7479498/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93187817,"identity":"32b392ff-e3ab-4300-88fe-84e1854ee190","added_by":"auto","created_at":"2025-10-10 03:27:53","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9461,"visible":true,"origin":"","legend":"","description":"","filename":"a3214a3adeca4b1bbd14c10ed1eb4e44.json","url":"https://assets-eu.researchsquare.com/files/rs-7479498/v1/17289d99142e6e07ad1f680e.json"},{"id":93187824,"identity":"5b82ab14-e778-4844-bd3f-79d3ddae258c","added_by":"auto","created_at":"2025-10-10 03:27:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":286767,"visible":true,"origin":"","legend":"","description":"","filename":"EthicalCommitteeApproval.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7479498/v1/fbaad5bdd007d3e0513e5871.pdf"},{"id":93187831,"identity":"f4529bd3-b92b-4c81-a186-eddec8ea7116","added_by":"auto","created_at":"2025-10-10 03:27:58","extension":"png","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":219219,"visible":true,"origin":"","legend":"","description":"","filename":"JawMain.png","url":"https://assets-eu.researchsquare.com/files/rs-7479498/v1/6c8d8365cad0b5fb7985693b.png"},{"id":93187818,"identity":"c7c4f10a-9399-4a02-99a9-f2669b4388cb","added_by":"auto","created_at":"2025-10-10 03:27:53","extension":"jpg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":90031,"visible":true,"origin":"","legend":"","description":"","filename":"ResolutionImage.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7479498/v1/433d80cfba1e48de84d0656f.jpg"},{"id":93187821,"identity":"16db0394-7e49-486a-895e-b52b273c51fe","added_by":"auto","created_at":"2025-10-10 03:27:53","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":273080,"visible":true,"origin":"","legend":"","description":"","filename":"Result.png","url":"https://assets-eu.researchsquare.com/files/rs-7479498/v1/ed789feaa1b40579f622cf94.png"},{"id":93187819,"identity":"1ba99203-727a-486d-b320-35b8f361b2e2","added_by":"auto","created_at":"2025-10-10 03:27:53","extension":"pdf","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":34700,"visible":true,"origin":"","legend":"","description":"","filename":"SRResponse.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7479498/v1/8cb66b1412c54423450c10e7.pdf"},{"id":93187826,"identity":"922d2b4f-9a23-4dcc-902e-eb774ed03d2b","added_by":"auto","created_at":"2025-10-10 03:27:53","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":177259,"visible":true,"origin":"","legend":"","description":"","filename":"Sota2.png","url":"https://assets-eu.researchsquare.com/files/rs-7479498/v1/0cda463bddebffbbc890d84b.png"},{"id":93188640,"identity":"e238baee-b6b6-42f5-b6f6-174577b9c505","added_by":"auto","created_at":"2025-10-10 03:35:53","extension":"pdf","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":728300,"visible":true,"origin":"","legend":"","description":"","filename":"ScientifficReportsDAGMNetADynamicAdaptiveGraphandMultiscaleNetworkforAccurateJawCystSegmentation2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7479498/v1/04e35d6f2e050066ca074e59.pdf"},{"id":93188637,"identity":"ca5853ff-8983-4e5e-9de7-23a71f66daa3","added_by":"auto","created_at":"2025-10-10 03:35:53","extension":"ldf","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":49107,"visible":true,"origin":"","legend":"","description":"","filename":"jabbrvltwaall.ldf","url":"https://assets-eu.researchsquare.com/files/rs-7479498/v1/366f7045ec3169eb00794582.ldf"},{"id":93187829,"identity":"1f4ea4fc-95ee-459f-a914-503a26960556","added_by":"auto","created_at":"2025-10-10 03:27:53","extension":"ldf","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":268657,"visible":true,"origin":"","legend":"","description":"","filename":"jabbrvltwaen.ldf","url":"https://assets-eu.researchsquare.com/files/rs-7479498/v1/a34a5747bd29af3f4721e938.ldf"},{"id":93189684,"identity":"c4cea4ea-541f-4e23-b618-9911cc2ddada","added_by":"auto","created_at":"2025-10-10 03:51:53","extension":"sty","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15480,"visible":true,"origin":"","legend":"","description":"","filename":"jabbrv.sty","url":"https://assets-eu.researchsquare.com/files/rs-7479498/v1/f86b66cbca7db30b13e445ef.sty"},{"id":93187828,"identity":"26a32a40-2c05-4c00-896d-c448187b83b7","added_by":"auto","created_at":"2025-10-10 03:27:53","extension":"bst","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36153,"visible":true,"origin":"","legend":"","description":"","filename":"naturemagdoi.bst","url":"https://assets-eu.researchsquare.com/files/rs-7479498/v1/3ae3be73af39e3b5e11bfe19.bst"},{"id":93189312,"identity":"eebae94a-587c-4aa7-b730-65c46f8bbba4","added_by":"auto","created_at":"2025-10-10 03:43:53","extension":"cls","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5824,"visible":true,"origin":"","legend":"","description":"","filename":"wlscirep.cls","url":"https://assets-eu.researchsquare.com/files/rs-7479498/v1/f15f524d4bcbad1994bfba02.cls"},{"id":93187825,"identity":"a6711165-b33c-42e9-a90a-2d7dd12b4cba","added_by":"auto","created_at":"2025-10-10 03:27:53","extension":"xml","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":84888,"visible":true,"origin":"","legend":"","description":"","filename":"a3214a3adeca4b1bbd14c10ed1eb4e441structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7479498/v1/0b9251d99bac82e9f01e33c3.xml"},{"id":93190478,"identity":"13c49fad-5b9b-4ebb-bc8a-dba5c1b18c1f","added_by":"auto","created_at":"2025-10-10 03:59:55","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":808367,"visible":true,"origin":"","legend":"","description":"","filename":"ScientifficReportsDAGMNetADynamicAdaptiveGraphandMultiscaleNetworkforAccurateJawCystSegmentation2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7479498/v1_covered_b3ba2b8d-d877-40b5-a6ab-fc76b565acc0.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"DAGM-Net: A Dynamic Adaptive Graph and Multi-scale Network for Accurate Jaw Cyst Segmentation","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7479498/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7479498/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate diagnosis and segmentation of jaw cysts hold substantial clinical significance; however, current deep learning approaches often struggle to capture complex anatomical structures and handle contextual variability. To address these challenges, this paper introduces a novel Dynamic Adaptive Graph and Multi-scale Network (DAGM-Net), which incorporates several innovative layers designed to enhance segmentation performance. Firstly, the Dynamic Graph Topology Learning (DGTL) layer adaptively constructs graph connectivity based on node feature similarity, enabling the model to better capture semantic relationships within the data. Next, the Residual Graph Convolution with Feature Rectification (RGC-FR) layer propagates node information through a three-stage feature rectification process, effectively compensating for feature loss and improving discriminative representation. Additionally, the Progressive Multi-scale Aggregation (PMA) layer hierarchically fuses multi-scale encoder features, thereby enriching contextual information and increasing representational power. To further strengthen optimization, a unified loss with momentum-based adaptive weighting is employed to dynamically balance multiple objectives and promote stable training. Comprehensive evaluations on benchmark datasets demonstrate that DAGM-Net achieves effective improvements in jaw cyst segmentation compared to existing methods.","manuscriptTitle":"DAGM-Net: A Dynamic Adaptive Graph and Multi-scale Network for Accurate Jaw Cyst Segmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-10 03:27:48","doi":"10.21203/rs.3.rs-7479498/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"310230266007575396619487667251045213815","date":"2026-05-18T08:14:18+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-29T05:14:39+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-19T09:33:39+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-09-10T08:48:21+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-09T15:29:28+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-09-09T15:26:42+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"d0e1ffbf-00af-49c1-b5c1-4c6c59eb6940","owner":[],"postedDate":"October 10th, 2025","published":true,"recentEditorialEvents":[{"type":"reviewerAgreed","content":"310230266007575396619487667251045213815","date":"2026-05-18T08:14:18+00:00","index":164,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":55999484,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":55999485,"name":"Physical sciences/Engineering"},{"id":55999486,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2025-10-10T03:27:48+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-10 03:27:48","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7479498","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7479498","identity":"rs-7479498","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}