Deep Learning-based Malaria Parasite Image Classification on Real Microscopy Data

Deep Learning-based Malaria Parasite Image Classification on Real Microscopy Data | 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 Deep Learning-based Malaria Parasite Image Classification on Real Microscopy Data Francesco Branda, Lilia Andriani, Riccardo Lucis, Annamaria Defilippo, and 6 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9311051/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 Background and Objective: Accurate and timely malaria diagnosis, including species-level identification of Plasmodium , is essential for guiding effective treatment and disease management. Traditional light microscopy remains the diagnostic gold standard but relies on highly trained personnel, limiting its accessibility in resource-constrained regions. Recent advances in deep learning have enabled automated image-based diagnosis with high performance; however, accurate differentiation among Plasmodium species remains a major challenge. This study aims to evaluate and compare the effectiveness of different deep learning architectures for automated malaria species identification from microscopy images. { Methods : Three architectures were systematically assessed: a convolutional backbone (ResNet-50), a Vision Transformer (ViT), and a hybrid ResNet–ViT framework. All models were trained from scratch, without using pre-trained weights, on a dataset comprising real-world thick blood smear images augmented with publicly available microscopy data from Kaggle. The ResNet module was employed to extract robust local morphological features, while the ViT component captured long-range dependencies and contextual relationships within the images. Results: Across cross-validation experiments, all three architectures demonstrated consistently high diagnostic performance. ResNet‑50 obtained an accuracy of 95.7%, F1‑score 95.2%, and ROC‑AUC 0.997. The ViT model reached an accuracy of 92.9\%, F1‑score 92.6%, and ROC‑AUC 0.992. The hybrid ResNet–ViT achieved an accuracy of 95.2%, F1‑score 94.7%, and ROC‑AUC 0.997. These results confirm that all architectures can reliably distinguish among Plasmodium species, with the hybrid model effectively integrating local and global feature representations. Conclusions: The findings highlight that convolutional, transformer-based, and hybrid deep learning architectures can be successfully trained on real microscopy data for species-level malaria diagnosis. These results support the feasibility of implementing scalable, automated diagnostic systems to enhance accuracy and accessibility of malaria detection, particularly in resource-limited healthcare settings. Full Text Additional Declarations No competing interests reported. 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-9311051","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":618500023,"identity":"dd9b7a7a-01c8-48d7-bf2e-5ff6d7c3aeb9","order_by":0,"name":"Francesco Branda","email":"","orcid":"","institution":"Università Campus Bio-Medico","correspondingAuthor":false,"prefix":"","firstName":"Francesco","middleName":"","lastName":"Branda","suffix":""},{"id":618500024,"identity":"7b35467c-c664-4fa2-9529-b41d97240e2d","order_by":1,"name":"Lilia Andriani","email":"","orcid":"","institution":"ASST della Valtellina e dell'Alto Lario","correspondingAuthor":false,"prefix":"","firstName":"Lilia","middleName":"","lastName":"Andriani","suffix":""},{"id":618500025,"identity":"ae7ed913-5f39-4dad-8a14-2f4941b8e0e1","order_by":2,"name":"Riccardo Lucis","email":"","orcid":"","institution":"University of Udine","correspondingAuthor":false,"prefix":"","firstName":"Riccardo","middleName":"","lastName":"Lucis","suffix":""},{"id":618500026,"identity":"14130246-29ff-4998-91fd-e2203627001b","order_by":3,"name":"Annamaria Defilippo","email":"","orcid":"","institution":"Magna Graecia University","correspondingAuthor":false,"prefix":"","firstName":"Annamaria","middleName":"","lastName":"Defilippo","suffix":""},{"id":618500027,"identity":"a45ac67b-62eb-4775-955e-f7f8bc92dceb","order_by":4,"name":"Ugo Lomoio","email":"","orcid":"","institution":"University of Calabria","correspondingAuthor":false,"prefix":"","firstName":"Ugo","middleName":"","lastName":"Lomoio","suffix":""},{"id":618500028,"identity":"0db13c05-8cb4-4d06-923a-3e33fc439487","order_by":5,"name":"Barbara Puccio","email":"","orcid":"","institution":"Magna Graecia University","correspondingAuthor":false,"prefix":"","firstName":"Barbara","middleName":"","lastName":"Puccio","suffix":""},{"id":618500029,"identity":"baa936c8-92ef-47fd-8386-4e98c2ecd723","order_by":6,"name":"Massimo Ciccozzi","email":"","orcid":"","institution":"Università Campus Bio-Medico","correspondingAuthor":false,"prefix":"","firstName":"Massimo","middleName":"","lastName":"Ciccozzi","suffix":""},{"id":618500030,"identity":"f4bc2bf5-d235-4b63-b13e-557e8922e42c","order_by":7,"name":"Fabio Scarpa","email":"","orcid":"","institution":"University of Sassari","correspondingAuthor":false,"prefix":"","firstName":"Fabio","middleName":"","lastName":"Scarpa","suffix":""},{"id":618500031,"identity":"89789239-32c9-4f4b-9a33-e5c980bd8c8d","order_by":8,"name":"Pierangelo Veltri","email":"","orcid":"","institution":"University of Calabria","correspondingAuthor":false,"prefix":"","firstName":"Pierangelo","middleName":"","lastName":"Veltri","suffix":""},{"id":618500032,"identity":"13ef623f-4b46-4fc2-a53f-fec171f6b182","order_by":9,"name":"Pietro Hiram Guzzi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAArklEQVRIiWNgGAWjYBACAwhpw8DAjOASpSUNpoUIPVAlh9H4+IA5/xrjjz8KziduZ2d+/IGh4A9hLZYz3hgYSBjcTtzZzAZ0FVEOu3HGIMEAqGXDYR6GBKK1HEgwOAfWcoA4Led7DBsOGBwAaWFsINIWtmLGBoNk4w2H2YwZEgyMibHl8OaPP/7YyW44f/jxhw9/5AhrYZBIQOIk4FCECvgPEKVsFIyCUTAKRjIAALx3OC2pERg3AAAAAElFTkSuQmCC","orcid":"","institution":"Magna Graecia University","correspondingAuthor":true,"prefix":"","firstName":"Pietro","middleName":"Hiram","lastName":"Guzzi","suffix":""}],"badges":[],"createdAt":"2026-04-03 09:08:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9311051/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9311051/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106741672,"identity":"66e63fd6-b92e-4e16-be8f-f1f6bb6923d8","added_by":"auto","created_at":"2026-04-13 03:40:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":18816838,"visible":true,"origin":"","legend":"","description":"","filename":"Archivio.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9311051/v1_covered_c93cefbc-df0d-465a-904e-bb564c8b3a3e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Deep Learning-based Malaria Parasite Image Classification on Real Microscopy Data","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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-9311051/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9311051/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground and Objective:\u003c/strong\u003e \u0026nbsp;Accurate and timely malaria diagnosis, including species-level identification of \u003cem\u003ePlasmodium\u003c/em\u003e, is essential for guiding effective treatment and disease management. Traditional light microscopy remains the diagnostic gold standard but relies on highly trained personnel, limiting its accessibility in resource-constrained regions. Recent advances in deep learning have enabled automated image-based diagnosis with high performance; however, accurate differentiation among \u003cem\u003ePlasmodium\u003c/em\u003e species remains a major challenge. This study aims to evaluate and compare the effectiveness of different deep learning architectures for automated malaria species identification from microscopy images.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e{\u003cstrong\u003eMethods\u003c/strong\u003e: \u0026nbsp;Three architectures were systematically assessed: a convolutional backbone (ResNet-50), a Vision Transformer (ViT), and a hybrid ResNet–ViT framework. All models were trained from scratch, without using pre-trained weights, on a dataset comprising real-world thick blood smear images augmented with publicly available microscopy data from Kaggle. The ResNet module was employed to extract robust local morphological features, while the ViT component captured long-range dependencies and contextual relationships within the images. \u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults:\u003c/strong\u003e \u0026nbsp;Across cross-validation experiments, all three architectures demonstrated consistently high diagnostic performance.\u0026nbsp;\u0026nbsp;ResNet‑50 obtained an accuracy of 95.7%, F1‑score 95.2%, and ROC‑AUC 0.997. The ViT model reached an accuracy of 92.9\\%, F1‑score 92.6%, and ROC‑AUC 0.992. The hybrid ResNet–ViT achieved an accuracy of 95.2%, F1‑score 94.7%, and ROC‑AUC 0.997. These results confirm that all architectures can reliably distinguish among Plasmodium species, with the hybrid model effectively integrating local and global feature representations.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusions:\u003c/strong\u003e \u0026nbsp;The findings highlight that convolutional, transformer-based, and hybrid deep learning architectures can be successfully trained on real microscopy data for species-level malaria diagnosis. These results support the feasibility of implementing scalable, automated diagnostic systems to enhance accuracy and accessibility of malaria detection, particularly in resource-limited healthcare settings.\u003c/p\u003e","manuscriptTitle":"Deep Learning-based Malaria Parasite Image Classification on Real Microscopy Data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-13 03:39:13","doi":"10.21203/rs.3.rs-9311051/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":"2594211c-9410-4672-91fc-7316d4906973","owner":[],"postedDate":"April 13th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-04-30T15:05:05+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-30T12:00:33+00:00","index":62,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-09T20:23:27+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-13 03:39:13","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9311051","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9311051","identity":"rs-9311051","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}