AI-assisted cervical cytology precancerous screening for high-risk population in resource limited regions using compact microscope

AI-assisted cervical cytology precancerous screening for high-risk population in resource limited regions using compact microscope | 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 AI-assisted cervical cytology precancerous screening for high-risk population in resource limited regions using compact microscope Xiuli Liu, Jiaxin Bai, Ning Li, Hua Ye, Xu Li, Li Chen, Junbo Hu, and 11 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4513507/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract The insufficient coverage of cervical cytology screening in underdeveloped countries or remote areas is currently the bottleneck hurdle to its widespread implementation. Conventional centralized medical screening methods are heavily dependent on sizable, costly investments as well as sufficient qualified pathologists. In this paper, we have developed a cervical precancerous assisted-screening system for identifying high-risk squamous intraepithelial lesion (SIL) cases in regions with limited resources. This system utilizes a low-cost miniature microscope and a low-pathologist-reliance artificial intelligence algorithm. We design a low-cost compact microscope with pixel resolution about 0.87 mm/pixel for imaging cytology slides. To tackle the challenge of sparely-distributed lesion cells in cytology whole slide images (WSIs), we have developed a dual-stage slide classification model. In first stage, we train an instance-level classifier by self-supervised pretraining on large-number unlabeled cervical images and transfer learning on small-number labeled images, aiming to reduce negative cells within a slide. In the second stage, we employ our proposed Att-Transformer, which aggregates deep features extracted from the top 200 lesion probabilities instances, for slide-level classification. We train and validate our model on 3,510 low-resolution WSIs collected from four different centers, and evaluate our model on 364 slides from two external centers in remote areas, achieving AUC (area under receiver operating characteristic curve) of 0.87 and 0.89 respectively for screening high risk cases. We also evaluate it on new independent cohorts of 391 slides from the original four centers and achieve AUC of 0.89. Overall, all the results indicate that integration of our innovative algorithm together with the compact microscope represents a promising approach to cervical cytology precancerous screening for high-risk population in medical resource limited regions. This affordable and accessible screening is significant as it contributes towards the goal of eliminating cervical cancer worldwide. Health sciences/Health care/Public health Health sciences/Health care/Disease prevention Health sciences/Medical research/Epidemiology Cervical cytology precancerous screening resource limited regions compact microscope computational cytology Full Text Additional Declarations There is NO Competing Interest. Supplementary Files figureoridata.rar Dataset 1 Supplementary1.docx Supplementary2.pdf Cite Share Download PDF Status: Under Review 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-4513507","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":313299050,"identity":"f4be2822-22aa-4fef-8768-65ba502f6e04","order_by":0,"name":"Xiuli Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6ElEQVRIie3RsQqCQBjA8e84OBfNVQnqFb5ojl6lcHVobGgwhHOpN7B6hhZpNIRafIDgliBocmgVHDq1ocV0bLj/cBzH/bg7DkCl+sc06sWwBGAasM/SrIVQIkkqCa0IdiNAeDnpSjAh68TYR8OeJA+9KMDUXIT81Exsn3iJEYkRp6CNDY5gbzIk27SZmLQmRBLWNzwEvLlIq6s2xCoSimlF9AJh2kbqUzwxrwmTp1gtpHzLObwIh8tt9o6PdSt9Ls7bHwSvfvLKVmJyCPyLlRWDgRk4x3v+g3wlP0iml0PcCahUKpWqsTei40XpWJ6vaQAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0001-6663-1647","institution":"Britton Chance Center for Biomedical Photonics, Wuhan National Laboratory for Optoelectronics-Huazhong University of Science and Technology, Wuhan, Hubei 430074, China","correspondingAuthor":true,"prefix":"","firstName":"Xiuli","middleName":"","lastName":"Liu","suffix":""},{"id":313299051,"identity":"06387971-f73c-4f46-a36b-5568f8c4ee9d","order_by":1,"name":"Jiaxin Bai","email":"","orcid":"","institution":"Britton Chance Center for Biomedical Photonics, Wuhan National Laboratory for Optoelectronics-Huazhong University of Science and Technology, Wuhan, Hubei 430074, China","correspondingAuthor":false,"prefix":"","firstName":"Jiaxin","middleName":"","lastName":"Bai","suffix":""},{"id":313299052,"identity":"d4d6d7bf-cf0e-498e-aeb8-a2d25aa3b5ce","order_by":2,"name":"Ning Li","email":"","orcid":"","institution":"Collaborative Innovation Center for Biomedical Engineering, Wuhan National Laboratory for Optoelectronics-Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Ning","middleName":"","lastName":"Li","suffix":""},{"id":313299053,"identity":"2862f74f-fbd9-44ca-b1ca-c640b213a3ad","order_by":3,"name":"Hua Ye","email":"","orcid":"","institution":"School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University","correspondingAuthor":false,"prefix":"","firstName":"Hua","middleName":"","lastName":"Ye","suffix":""},{"id":313299054,"identity":"2523f35c-c37d-483c-afba-6f3e834e6c74","order_by":4,"name":"Xu Li","email":"","orcid":"","institution":"Britton Chance Center for Biomedical Photonics, Wuhan National Laboratory for Optoelectronics-Huazhong University of Science and Technology, Wuhan, Hubei 430074, China","correspondingAuthor":false,"prefix":"","firstName":"Xu","middleName":"","lastName":"Li","suffix":""},{"id":313299055,"identity":"3e2fcceb-c3c7-45e8-a035-218af02aea3a","order_by":5,"name":"Li Chen","email":"","orcid":"","institution":"Tongji Medical College, Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Li","middleName":"","lastName":"Chen","suffix":""},{"id":313299056,"identity":"10d57a25-b619-41f1-a678-3102876fccd1","order_by":6,"name":"Junbo Hu","email":"","orcid":"","institution":"Tongji Medical College, Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Junbo","middleName":"","lastName":"Hu","suffix":""},{"id":313299057,"identity":"5fbf23ec-c60b-49ab-ab6c-d1ae3cc7f063","order_by":7,"name":"Baochuan Pang","email":"","orcid":"","institution":"Wuhan Landing Institute for Artificial Intelligence Cancer Diagnosis Industry Development, Wuhan, Hubei, China","correspondingAuthor":false,"prefix":"","firstName":"Baochuan","middleName":"","lastName":"Pang","suffix":""},{"id":313299058,"identity":"b642ffa8-093a-47f4-8a2c-5991096b86c6","order_by":8,"name":"Xiaodong Chen","email":"","orcid":"","institution":"Duodao People's Hospital, Jingmen, Hubei, China","correspondingAuthor":false,"prefix":"","firstName":"Xiaodong","middleName":"","lastName":"Chen","suffix":""},{"id":313299059,"identity":"972c0495-14de-4251-a627-04edb3c802ec","order_by":9,"name":"Gong Rao","email":"","orcid":"","institution":"Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Gong","middleName":"","lastName":"Rao","suffix":""},{"id":313299060,"identity":"48703b14-67fa-4cfb-a5a8-97eed2a84c95","order_by":10,"name":"Qinglei Hu","email":"","orcid":"","institution":"Convergence Technology Co., Ltd, Wuhan, Hubei, China","correspondingAuthor":false,"prefix":"","firstName":"Qinglei","middleName":"","lastName":"Hu","suffix":""},{"id":313299061,"identity":"484d0bd8-028e-45b4-ab63-6601d1430124","order_by":11,"name":"Shijie Liu","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Shijie","middleName":"","lastName":"Liu","suffix":""},{"id":313299062,"identity":"29436d9b-48ed-4948-bca8-388ff4535de8","order_by":12,"name":"Si Sun","email":"","orcid":"","institution":"Wuhan Union Hospital","correspondingAuthor":false,"prefix":"","firstName":"Si","middleName":"","lastName":"Sun","suffix":""},{"id":313299063,"identity":"bbbb4e3b-14e8-42f3-a12e-2fb1b3a74f86","order_by":13,"name":"Cheng Li","email":"","orcid":"","institution":"Wuhan Landing Institute for Artificial Intelligence Cancer Diagnosis Industry Development, Wuhan, Hubei, China","correspondingAuthor":false,"prefix":"","firstName":"Cheng","middleName":"","lastName":"Li","suffix":""},{"id":313299064,"identity":"c4091639-5e74-402c-a5a7-3783c50d4c9c","order_by":14,"name":"Xiaohua Lv","email":"","orcid":"","institution":"Huazhong University of Science and Technology-Wuhan National Lab for Optoelectronics","correspondingAuthor":false,"prefix":"","firstName":"Xiaohua","middleName":"","lastName":"Lv","suffix":""},{"id":313299065,"identity":"0e7539e3-2c47-4258-9702-ef0acf4f91bd","order_by":15,"name":"Shaoqun zeng","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Shaoqun","middleName":"","lastName":"zeng","suffix":""},{"id":313299066,"identity":"d3053f6e-7fda-4260-8503-dfbd8799e46e","order_by":16,"name":"Jing Cai","email":"","orcid":"","institution":"Union Hospital, Tongji Medical College, Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Jing","middleName":"","lastName":"Cai","suffix":""},{"id":313299067,"identity":"3d0f6e12-6b63-4f47-82f3-8eca547a3ff6","order_by":17,"name":"Shenghua Cheng","email":"","orcid":"","institution":"School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, China","correspondingAuthor":false,"prefix":"","firstName":"Shenghua","middleName":"","lastName":"Cheng","suffix":""}],"badges":[],"createdAt":"2024-06-01 12:00:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4513507/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4513507/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":58191150,"identity":"65c09e81-9443-4e09-b719-c0dbbfffb485","added_by":"auto","created_at":"2024-06-12 08:28:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1121230,"visible":true,"origin":"","legend":"","description":"","filename":"AIassistedcervicalcytologyprecancerousscreeningforhighriskpopulationinresourcelimitedareasusingtinymicroscope.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4513507/v1_covered_2e9f1ce8-517f-48b5-9bcd-14fac35feccc.pdf"},{"id":58190340,"identity":"ca897e61-fce2-4c49-bd2b-b1d7f7462003","added_by":"auto","created_at":"2024-06-12 08:20:52","extension":"rar","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":559764,"visible":true,"origin":"","legend":"Dataset 1","description":"","filename":"figureoridata.rar","url":"https://assets-eu.researchsquare.com/files/rs-4513507/v1/574f4fc2140891f32d854e57.rar"},{"id":58190341,"identity":"f84d6d2d-d30b-4f05-92f0-61e19c794342","added_by":"auto","created_at":"2024-06-12 08:20:52","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":498507,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementary1.docx","url":"https://assets-eu.researchsquare.com/files/rs-4513507/v1/77e970a5c227981ad49e113a.docx"},{"id":58190342,"identity":"9f3a32ed-aad1-4665-a0d4-5ed0c5ab3a77","added_by":"auto","created_at":"2024-06-12 08:20:52","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":8550387,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementary2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4513507/v1/54223851411cb53a627992de.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"AI-assisted cervical cytology precancerous screening for high-risk population in resource limited regions using compact microscope","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Cervical cytology precancerous screening, resource limited regions, compact microscope, computational cytology","lastPublishedDoi":"10.21203/rs.3.rs-4513507/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4513507/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe insufficient coverage of cervical cytology screening in underdeveloped countries or remote areas is currently the bottleneck hurdle to its widespread implementation. Conventional centralized medical screening methods are heavily dependent on sizable, costly investments as well as sufficient qualified pathologists. In this paper, we have developed a cervical precancerous assisted-screening system for identifying high-risk squamous intraepithelial lesion (SIL) cases in regions with limited resources. This system utilizes a low-cost miniature microscope and a low-pathologist-reliance artificial intelligence algorithm. We design a low-cost compact microscope with pixel resolution about 0.87 mm/pixel for imaging cytology slides. To tackle the challenge of sparely-distributed lesion cells in cytology whole slide images (WSIs), we have developed a dual-stage slide classification model. In first stage, we train an instance-level classifier by self-supervised pretraining on large-number unlabeled cervical images and transfer learning on small-number labeled images, aiming to reduce negative cells within a slide. In the second stage, we employ our proposed Att-Transformer, which aggregates deep features extracted from the top 200 lesion probabilities instances, for slide-level classification. We train and validate our model on 3,510 low-resolution WSIs collected from four different centers, and evaluate our model on 364 slides from two external centers in remote areas, achieving AUC (area under receiver operating characteristic curve) of 0.87 and 0.89 respectively for screening high risk cases. We also evaluate it on new independent cohorts of 391 slides from the original four centers and achieve AUC of 0.89. Overall, all the results indicate that integration of our innovative algorithm together with the compact microscope represents a promising approach to cervical cytology precancerous screening for high-risk population in medical resource limited regions. This affordable and accessible screening is significant as it contributes towards the goal of eliminating cervical cancer worldwide.\u003c/p\u003e","manuscriptTitle":"AI-assisted cervical cytology precancerous screening for high-risk population in resource limited regions using compact microscope","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-12 08:20:47","doi":"10.21203/rs.3.rs-4513507/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"efeb29b2-cb65-4885-9aaa-a02a455237b9","owner":[],"postedDate":"June 12th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":33124967,"name":"Health sciences/Health care/Public health"},{"id":33124968,"name":"Health sciences/Health care/Disease prevention"},{"id":33124969,"name":"Health sciences/Medical research/Epidemiology"}],"tags":[],"updatedAt":"2025-07-24T11:40:39+00:00","versionOfRecord":[],"versionCreatedAt":"2024-06-12 08:20:47","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4513507","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4513507","identity":"rs-4513507","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}