A Data Fusion Deep Learning Approach for Accurate Organelle-Based Classification of Cancer Cells

A Data Fusion Deep Learning Approach for Accurate Organelle-Based Classification of Cancer Cells | 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 A Data Fusion Deep Learning Approach for Accurate Organelle-Based Classification of Cancer Cells Harrison Yee This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5187953/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Microscopy-based cancer cell classification has traditionally focused on observable cellular features, such as size, morphology, and pleomorphism. Recent advances in machine learning-based image analysis in cancer diagnostics have allowed for greater throughput and consistency in cancer cell analysis by extracting visibly non-discernable features. Specifically, classification based on sub-cellular organelles' shape and spatial feature distributions has been established as a highly accurate methodology. These handcrafted feature extraction methods, however, are limited in throughput and analytical trustworthiness. These criticisms arise from the manual use of external software for object rendering, handcrafted feature extraction, and classification, thus introducing potential biases and artificial features due to image processing. Herein, we introduce a deep learning approach using a patch-based convolutional neural network (CNN) with channel-wise intermediate data fusion to perform end-to-end breast cancer classification of fluorescent confocal microscopy images focused on separate feature analysis of each sub-cellular organelle of interest. In cross-validation studies on a dataset of six different breast cancer cell lines, our methodology achieved an average classification accuracy of 92.0 ± 0.9%, rivaling other methods. Ultimately, this work provides streamlined and organelle-focused feature analysis for automated deep learning-based cancer cell classification. Biological sciences/Cancer/Cancer screening Biological sciences/Cancer/Cancer imaging Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Posted Version 1 posted 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-5187953","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":365932392,"identity":"d27a2e06-aff2-4960-878c-735a37a3a5bf","order_by":0,"name":"Harrison Yee","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAApElEQVRIiWNgGAWjYHACNoYPDAw8QIYB8VoYZ5CshZkHwiBSi8Hx5mOPbffckWFgb94mQZyWM8fSjXOePeNh4DlWRqSWGzlm0jkHDvMwSOSYEanl/vtv0hYgLfJviNVyg4dNmgFsCw+RWiTPpJlJ9hx4xsPGk1ZsQZQWvuOHn0n8OHDHnp/98MYbRGlROACmDgDTALFAvgGqZRSMglEwCkYBTgAAQ68sgS3zVNAAAAAASUVORK5CYII=","orcid":"https://orcid.org/0009-0005-8580-1695","institution":"Rensselaer Polytechnic Institute","correspondingAuthor":true,"prefix":"","firstName":"Harrison","middleName":"","lastName":"Yee","suffix":""}],"badges":[],"createdAt":"2024-10-01 14:20:44","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":true,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":true},"doi":"10.21203/rs.3.rs-5187953/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5187953/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":66741910,"identity":"cc2c3cb8-a94b-4611-88f9-881503320ef9","added_by":"auto","created_at":"2024-10-16 05:58:28","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":747155,"visible":true,"origin":"","legend":"Article File","description":"","filename":"OTCCPDLJournalPaperfornaturecomm.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5187953/v1_covered_b9c4a042-edb6-41d3-8f24-b6ce1281796c.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"A Data Fusion Deep Learning Approach for Accurate Organelle-Based Classification of Cancer Cells","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-5187953/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5187953/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Microscopy-based cancer cell classification has traditionally focused on observable cellular features, such as size, morphology, and pleomorphism. Recent advances in machine learning-based image analysis in cancer diagnostics have allowed for greater throughput and consistency in cancer cell analysis by extracting visibly non-discernable features. Specifically, classification based on sub-cellular organelles' shape and spatial feature distributions has been established as a highly accurate methodology. These handcrafted feature extraction methods, however, are limited in throughput and analytical trustworthiness. These criticisms arise from the manual use of external software for object rendering, handcrafted feature extraction, and classification, thus introducing potential biases and artificial features due to image processing. Herein, we introduce a deep learning approach using a patch-based convolutional neural network (CNN) with channel-wise intermediate data fusion to perform end-to-end breast cancer classification of fluorescent confocal microscopy images focused on separate feature analysis of each sub-cellular organelle of interest. In cross-validation studies on a dataset of six different breast cancer cell lines, our methodology achieved an average classification accuracy of 92.0 ± 0.9%, rivaling other methods. Ultimately, this work provides streamlined and organelle-focused feature analysis for automated deep learning-based cancer cell classification.","manuscriptTitle":"A Data Fusion Deep Learning Approach for Accurate Organelle-Based Classification of Cancer Cells","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-10-16 05:34:21","doi":"10.21203/rs.3.rs-5187953/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"47fc3f88-b5ef-4e0f-b160-c443d8fff628","owner":[],"postedDate":"October 16th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":38928556,"name":"Biological sciences/Cancer/Cancer screening"},{"id":38928557,"name":"Biological sciences/Cancer/Cancer imaging"}],"tags":[],"updatedAt":"2024-10-16T05:34:21+00:00","versionOfRecord":[],"versionCreatedAt":"2024-10-16 05:34:21","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5187953","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5187953","identity":"rs-5187953","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}