{"paper_id":"412725be-166a-423d-83d4-dff7e845f092","body_text":"Integrated 3D Deep Learning Approach: YOLO-Decoupled Candidate Detection and 3D CNN-Driven False Positive Reduction for Lung Nodule Analysis in CT | 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 Integrated 3D Deep Learning Approach: YOLO-Decoupled Candidate Detection and 3D CNN-Driven False Positive Reduction for Lung Nodule Analysis in CT Tengfei Zhao, Weiyan Tong, Zhixiao Wang, Junxin Chen, Chong Fu, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8204090/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract Lung cancer often presents with small pulmonary nodules in its early stages, making early detection and diagnosis of these nodules vital for treatment. This paper proposes a two-step automatic pulmonary nodule detection method. For candidate nodule detection, we decouple detection and classification in YOLO for axial slice analysis, using an Attention Feature Fusion ResBlock (AFF-ResBlock) to enhance the network and weighted cluster non-maximum suppression (NMS) for post-processing. In false positive reduction, a 3D CNN architecture is designed. 3D CNNs capture richer 3D spatial information than 2D ones. We also integrate multi-scale contextual information. Our algorithm achieves 95.3% accuracy on the LUNA16 dataset, proving its effectiveness. Pulmonary Nodule Detection Lung Cancer YOLO Framework 3D CNN Architecture Multi-scale Contextual Information Full Text Additional Declarations No competing interests reported. Supplementary Files supplement.zip Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 04 Dec, 2025 Editor assigned by journal 03 Dec, 2025 Submission checks completed at journal 03 Dec, 2025 First submitted to journal 25 Nov, 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-8204090\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":false,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":555387997,\"identity\":\"6fe4efe7-7164-44e0-b39f-155823d7c03b\",\"order_by\":0,\"name\":\"Tengfei Zhao\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Shenyang University of Technology\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Tengfei\",\"middleName\":\"\",\"lastName\":\"Zhao\",\"suffix\":\"\"},{\"id\":555387998,\"identity\":\"1ebba532-83ae-4977-bbcd-2467d63afb74\",\"order_by\":1,\"name\":\"Weiyan Tong\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6ElEQVRIiWNgGAWjYPACCSBmPgBhHyCglgehhS2BgSGBeC1gpgFxWuzZew+/5qmwSOyf3fP5M+8PBjm+GwmMnwvw2cJzLs2a54xE4ow7Z7dJ8yQwGEveSGCWnoFPi0SOmXFum0Riw43cbcxALYkbbiSwMfMQ1PJPInH+jZzHn4Fa6onRYvw4t0ECaHgOA8hhCQYEtZw5Y8b855iE8cYbaWaSc9IkDGeeedgsjU8Le3uP8ccZNXWy824kP/7wxsZGnu948sHP+LQAARsoHh0bIBwQm7EBvwZgQvkAJOwJqRoFo2AUjIIRDAABRkn1KlUZ2gAAAABJRU5ErkJggg==\",\"orcid\":\"\",\"institution\":\"Shenyang University of Technology\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Weiyan\",\"middleName\":\"\",\"lastName\":\"Tong\",\"suffix\":\"\"},{\"id\":555387999,\"identity\":\"e6891504-ba25-4ac2-8788-134f162e4b4e\",\"order_by\":2,\"name\":\"Zhixiao Wang\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Northeastern University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Zhixiao\",\"middleName\":\"\",\"lastName\":\"Wang\",\"suffix\":\"\"},{\"id\":555388001,\"identity\":\"026960ed-eb79-4f23-acb4-6a267a48f7ef\",\"order_by\":3,\"name\":\"Junxin Chen\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Dalian University of Technology\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Junxin\",\"middleName\":\"\",\"lastName\":\"Chen\",\"suffix\":\"\"},{\"id\":555388004,\"identity\":\"7fa112a9-6a88-48e4-b1d2-2cc01f38dcad\",\"order_by\":4,\"name\":\"Chong Fu\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Northeastern University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Chong\",\"middleName\":\"\",\"lastName\":\"Fu\",\"suffix\":\"\"},{\"id\":555388006,\"identity\":\"6237acdb-ae2c-4577-9d9d-f58292289571\",\"order_by\":5,\"name\":\"Cheng Gao\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Shenyang University of Technology\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Cheng\",\"middleName\":\"\",\"lastName\":\"Gao\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2025-11-25 14:08:05\",\"currentVersionCode\":1,\"declarations\":\"\",\"doi\":\"10.21203/rs.3.rs-8204090/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-8204090/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":97646653,\"identity\":\"f680f27e-530e-4cb3-b55a-1cfa88398397\",\"added_by\":\"auto\",\"created_at\":\"2025-12-08 04:54:52\",\"extension\":\"json\",\"order_by\":0,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":6979,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"bec83a17f0c34cb8b5ccdf7e0500dbff.json\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8204090/v1/ff8452e8c75b0f021a92251e.json\"},{\"id\":97672465,\"identity\":\"58c96e47-d771-4620-8ede-6eeaf666e286\",\"added_by\":\"auto\",\"created_at\":\"2025-12-08 09:38:03\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":1132841,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Manuscript.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8204090/v1_covered_82610c47-e191-452e-aedd-417c5c674c1e.pdf\"},{\"id\":97646654,\"identity\":\"4b85dea6-2dba-4499-b230-327ac63c51cc\",\"added_by\":\"auto\",\"created_at\":\"2025-12-08 04:54:52\",\"extension\":\"zip\",\"order_by\":0,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"supplement\",\"size\":1507584,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"supplement.zip\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8204090/v1/f7cf54c60281c65fe4595ea3.zip\"}],\"financialInterests\":\"No competing interests reported.\",\"formattedTitle\":\"Integrated 3D Deep Learning Approach: YOLO-Decoupled Candidate Detection and 3D CNN-Driven False Positive Reduction for Lung Nodule Analysis in CT\",\"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\":\"info@researchsquare.com\",\"identity\":\"signal-image-and-video-processing\",\"isNatureJournal\":false,\"hasQc\":true,\"allowDirectSubmit\":false,\"externalIdentity\":\"sivp\",\"sideBox\":\"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)\",\"snPcode\":\"11760\",\"submissionUrl\":\"https://submission.nature.com/new-submission/11760/3\",\"title\":\"Signal, Image and Video Processing\",\"twitterHandle\":\"\",\"acdcEnabled\":true,\"dfaEnabled\":true,\"editorialSystem\":\"em\",\"reportingPortfolio\":\"Springer Hybrid\",\"inReviewEnabled\":true,\"inReviewRevisionsEnabled\":false},\"keywords\":\"Pulmonary Nodule Detection, Lung Cancer, YOLO Framework, 3D CNN Architecture, Multi-scale Contextual Information\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-8204090/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-8204090/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"\\nLung cancer often presents with small pulmonary nodules in its early stages, making early detection and diagnosis of these nodules vital for treatment. \\nThis paper proposes a two-step automatic pulmonary nodule detection method.\\n For candidate nodule detection, we decouple detection and classification in YOLO for axial slice analysis, using an Attention Feature Fusion ResBlock (AFF-ResBlock) to enhance the network and weighted cluster non-maximum suppression (NMS) for post-processing. \\n In false positive reduction, a 3D CNN architecture is designed. 3D CNNs capture richer 3D spatial information than 2D ones.\\n We also integrate multi-scale contextual information.\\n Our algorithm achieves 95.3\\\\% accuracy on the LUNA16 dataset, proving its effectiveness.\\n\",\"manuscriptTitle\":\"Integrated 3D Deep Learning Approach: YOLO-Decoupled Candidate Detection and 3D CNN-Driven False Positive Reduction for Lung Nodule Analysis in CT\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2025-12-08 04:54:48\",\"doi\":\"10.21203/rs.3.rs-8204090/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0},{\"type\":\"reviewersInvited\",\"content\":\"\",\"date\":\"2025-12-04T16:35:15+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorAssigned\",\"content\":\"\",\"date\":\"2025-12-03T11:07:03+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"checksComplete\",\"content\":\"\",\"date\":\"2025-12-03T11:06:54+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"submitted\",\"content\":\"Signal, Image and Video Processing\",\"date\":\"2025-11-25T13:52:13+00:00\",\"index\":\"\",\"fulltext\":\"\"}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"identity\":\"signal-image-and-video-processing\",\"isNatureJournal\":false,\"hasQc\":true,\"allowDirectSubmit\":false,\"externalIdentity\":\"sivp\",\"sideBox\":\"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)\",\"snPcode\":\"11760\",\"submissionUrl\":\"https://submission.nature.com/new-submission/11760/3\",\"title\":\"Signal, Image and Video Processing\",\"twitterHandle\":\"\",\"acdcEnabled\":true,\"dfaEnabled\":true,\"editorialSystem\":\"em\",\"reportingPortfolio\":\"Springer Hybrid\",\"inReviewEnabled\":true,\"inReviewRevisionsEnabled\":false}}],\"origin\":\"\",\"ownerIdentity\":\"5c9760f2-0ee3-4ab7-8765-64f9898feff3\",\"owner\":[],\"postedDate\":\"December 8th, 2025\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"under-review\",\"subjectAreas\":[],\"tags\":[],\"updatedAt\":\"2025-12-08T04:54:48+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2025-12-08 04:54:48\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-8204090\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-8204090\",\"identity\":\"rs-8204090\",\"version\":[\"v1\"]},\"buildId\":\"8U1c8b4HqxoKbykW_rLl7\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}