iSL-YOLOv11: Global–Local Attention Enhanced Small Lesion Detection in Mammography Images

iSL-YOLOv11: Global–Local Attention Enhanced Small Lesion Detection in Mammography Images | 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 iSL-YOLOv11: Global–Local Attention Enhanced Small Lesion Detection in Mammography Images Ningtao Sun, Junxi Wang, Xinyi Cao, Zhuoxi Mai, Yanchun Liang, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9211399/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 9 You are reading this latest preprint version Abstract At present, Breast cancer is one of the most common types of cancer among women worldwide. When it comes to breast cancer, the sooner we know, the more critical it is to keep someone alive. But really, in those clinical, day-today settings where a clinician would have a case they’re trying to make with a patient about a mammogram image, there will be other stuff like overlapping tissue, it might be blurry, maybe what you see on these pictures can’t be seen, or it’s small. They’ll need help finding something like a small tumor, so it makes doing an early-stage scan for breast cancer kind of hard to find stuff. To overcome the above problems, this paper proposes a new network architecture, iAFF-SEAM-LAE YOLOv11 (iSL-YOLOv11), that combines global and local structure-awareness. It dramatically improves extraction power and sensitivity toward small disease regions and could detect small lesions in complex mammograms. Experiments show that our newly proposed technique increases the mAP50-95 score of the original YOLOv11 baseline model for detecting lesions in mammography images by 27.4%. This is something you can use to make your computer better at telling if someone has breast cancer when you look at them from an X-ray picture, earlier than before. Biological sciences/Cancer Health sciences/Health care Health sciences/Oncology YOLO Global-Loacal Attention Breast Cancer Small Lesion Detection Mammography Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 05 May, 2026 Reviews received at journal 02 May, 2026 Reviewers agreed at journal 18 Apr, 2026 Reviews received at journal 17 Apr, 2026 Reviewers agreed at journal 10 Apr, 2026 Reviewers invited by journal 09 Apr, 2026 Editor assigned by journal 09 Apr, 2026 Submission checks completed at journal 04 Apr, 2026 First submitted to journal 04 Apr, 2026 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-9211399","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":620978815,"identity":"b50d2004-1635-45d5-87c6-16375ce88966","order_by":0,"name":"Ningtao Sun","email":"","orcid":"","institution":"Zhuhai College of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Ningtao","middleName":"","lastName":"Sun","suffix":""},{"id":620978817,"identity":"d0cf5089-f293-49d4-8e44-92a5621d9fda","order_by":1,"name":"Junxi Wang","email":"","orcid":"","institution":"Zhuhai College of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Junxi","middleName":"","lastName":"Wang","suffix":""},{"id":620978819,"identity":"88f0331c-2a74-4d37-8280-0bedca56b6c3","order_by":2,"name":"Xinyi Cao","email":"","orcid":"","institution":"Zhuhai College of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Xinyi","middleName":"","lastName":"Cao","suffix":""},{"id":620978821,"identity":"c6d770e1-4368-488c-9c98-51f86a74bc6a","order_by":3,"name":"Zhuoxi Mai","email":"","orcid":"","institution":"Zhuhai College of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhuoxi","middleName":"","lastName":"Mai","suffix":""},{"id":620978823,"identity":"46bcc0cc-1c53-41de-9fcf-2681a97da7e9","order_by":4,"name":"Yanchun Liang","email":"","orcid":"","institution":"Zhuhai College of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Yanchun","middleName":"","lastName":"Liang","suffix":""},{"id":620978825,"identity":"58c3be3a-d423-42ce-b394-e712abd161e3","order_by":5,"name":"Tao Cui","email":"","orcid":"","institution":"Changchun University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Tao","middleName":"","lastName":"Cui","suffix":""},{"id":620978828,"identity":"3db018bf-383e-4012-a75a-82f18fcbba71","order_by":6,"name":"Adriano Tavares","email":"","orcid":"","institution":"University of Minho","correspondingAuthor":false,"prefix":"","firstName":"Adriano","middleName":"","lastName":"Tavares","suffix":""},{"id":620978831,"identity":"6ee48d0b-1dcf-4e89-a96b-dced1262a1da","order_by":7,"name":"Dalin Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0klEQVRIiWNgGAWjYBACPmYGA4YHBgxyUD4zYS1sIC0JBgzGQDZjA3FaGEBaGBgSG4jXws688UNCwZ30+e3Hnz9gqLBObGA/e4CAw9iKJRIMnuU29uQYNjCcSU9s4MlLIKCFxwCo5XBuswQPYwNj2+HEBgkeA0JajH8AtaSzSbA/bGD8R5wWM5AtCTwSDIYNjA1EaWErswBqMZzBk2M4I+FYunEbTw5+Lfz8hzff+PDnsLx8+/EHHz7UWMv2s5/BrwUVJDCAY2oUjIJRMApGAaUAAL8mPP1XffyhAAAAAElFTkSuQmCC","orcid":"","institution":"Zhuhai College of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Dalin","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2026-03-24 11:40:58","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9211399/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9211399/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107180406,"identity":"7aa28f3e-2192-4d6a-9463-c13015b11551","added_by":"auto","created_at":"2026-04-17 16:55:31","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5136297,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptLatexV3.0.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9211399/v1_covered_36279fa0-8012-4364-a6af-3f741d5be791.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"iSL-YOLOv11: Global–Local Attention Enhanced Small Lesion Detection in Mammography Images","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":"YOLO, Global-Loacal Attention, Breast Cancer, Small Lesion Detection, Mammography","lastPublishedDoi":"10.21203/rs.3.rs-9211399/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9211399/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"At present, Breast cancer is one of the most common types of cancer among women worldwide. When it comes to breast cancer, the sooner we know, the more critical it is to keep someone alive. But really, in those clinical, day-today settings where a clinician would have a case they’re trying to make with a patient about a mammogram image, there will be other stuff like overlapping tissue, it might be blurry, maybe what you see on these pictures can’t be seen, or it’s small. They’ll need help finding something like a small tumor, so it makes doing an early-stage scan for breast cancer kind of hard to find stuff. To overcome the above problems, this paper proposes a new network architecture, iAFF-SEAM-LAE YOLOv11 (iSL-YOLOv11), that combines global and local structure-awareness. It dramatically improves extraction power and sensitivity toward small disease regions and could detect small lesions in complex mammograms. Experiments show that our newly proposed technique increases the mAP50-95 score of the original YOLOv11 baseline model for detecting lesions in mammography images by 27.4%. This is something you can use to make your computer better at telling if someone has breast cancer when you look at them from an X-ray picture, earlier than before.","manuscriptTitle":"iSL-YOLOv11: Global–Local Attention Enhanced Small Lesion Detection in Mammography Images","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-17 16:54:37","doi":"10.21203/rs.3.rs-9211399/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-05T16:18:05+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-02T08:50:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"253347310657691068773065258183261720181","date":"2026-04-18T08:48:56+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-17T12:37:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"5871326178848960034150784001575995590","date":"2026-04-10T12:45:57+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-09T21:41:04+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-09T07:47:04+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-04T13:30:21+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-04-04T13:27:34+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":"ed1f33a9-183c-4b13-8857-3192b8be4408","owner":[],"postedDate":"April 17th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-05T16:18:05+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-02T08:50:34+00:00","index":26,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":66089477,"name":"Biological sciences/Cancer"},{"id":66089478,"name":"Health sciences/Health care"},{"id":66089479,"name":"Health sciences/Oncology"}],"tags":[],"updatedAt":"2026-05-18T15:38:30+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-17 16:54:37","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9211399","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9211399","identity":"rs-9211399","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}