Adopting Augmented Reality to Improve Visual Inspection in a Single-Visit Cervical Cancer Screening Framework

Adopting Augmented Reality to Improve Visual Inspection in a Single-Visit Cervical Cancer Screening Framework | 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 Adopting Augmented Reality to Improve Visual Inspection in a Single-Visit Cervical Cancer Screening Framework Seema Singhal, Tapan Gandhi, Arjun Ganguly, Aarthi S Jayraj This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5484245/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 Cervical cancer is a major public health concern in India, accounting for one-fifth of the global burden. This study examines the use of Augmented Reality (AR) technology to enhance diagnostic accuracy among healthcare providers (HCPs) within a single-visit screening framework, addressing the shortage of expert gynaecologists for onsite mentoring. Methods We developed an AR-enabled tool using the Microsoft HoloLens 2 headset to assist in cervical cancer screening by identifying suspected lesion areas. A remote healthcare worker equipped with the HoloLens collaborated with a specialized practitioner operating a computer to annotate suspicious regions on a simulated plastic cervix model with a designated lesion, simulating real-life conditions. Results The AR system projected a 3D cervix model into the real environment for remote annotation, demonstrating an average error rate of 8.75% (± 2.3%) during trials. Conclusion The HoloLens 2 AR system has been shown to enhance the accuracy and efficiency of visual cervical cancer screening, with significant potential to improve screening in underserved areas. Future plans include using two AR devices to enhance accuracy in real-world data collection and further trials to validate its effectiveness and scalability in diverse healthcare settings. Obstetrics & Gynecology Cervical cancer Augmented reality Virtual reality Real-time visualization Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Introduction Cervical cancer is a significant public health issue in India, contributing to approximately one-fifth of the global burden of the disease. With an estimated 127,526 new cases and 79,906 deaths reported in 2022, cervical cancer poses a critical challenge for healthcare systems, particularly among women in low- and middle-income countries ( 1 ). Despite being a preventable disease, many women present with advanced stages of cervical cancer due to inadequate access to screening and treatment services . Existing literature highlights the effectiveness of systematic and quality-assured cervical cancer screening programs in reducing incidence rates significantly. Studies have shown that population-based screening can lead to more than a 70% reduction in cervical cancer cases in developed countries. However, similar success has not been replicated in India and other low-resource settings, where screening coverage remains alarmingly low, often below 20%. The subjective nature of current screening methods, such as visual inspection with acetic acid (VIA), further complicates accurate diagnosis and treatment. Single visit approach (SVA) or see-and-treat strategy significant increases effectiveness of screening programs by linking immediate treatment in a single healthcare visit and is shown to be feasible and acceptable ( 2 , 3 ). The major challenge for implementation of SVA is lack of resources in terms of trained gynaecologists and inadequate healthcare personnel ( 4 ). Augmented Reality (AR) is increasingly being applied in healthcare and holds tremendous future potential ( 5 ). AR overlays virtual objects onto the real world, enabling users to interact with these elements. In recent years, AR has gained popularity in medical applications, especially in simulation training, where it facilitates interaction with 3D digital models, providing a better understanding of human anatomy for surgical procedures ( 6 ). There is an urgent need to address these gaps by providing effective mentorship and guidance for healthcare providers (HCPs). In this project, we aimed to examine the feasibility of utilizing the Microsoft HoloLens 2, an AR-based Head Mounted Display (HMD), for remotely assisting healthcare workers in cervical cancer screening. This system aims to bridge the gap in access to specialized healthcare services while enhancing diagnostic accuracy within a single-visit framework, leveraging AR technology to improve screening outcomes and ensure timely treatment. Currently, we report on Phase I of our research, which focuses on developing an AR-enabled camera tool customized for cervical photography. Methodology Overview of the System : The implemented system utilizes Microsoft HoloLens 2 augmented reality (AR) technology to enhance cervical cancer screening in rural healthcare settings. A healthcare worker, stationed in a remote location, dons the HoloLens while conducting patient screenings. This device connects the healthcare worker to a remote, specialized physician through a computer interface, enabling real-time visual supervision and guidance. Real-Time Collaboration: The remote doctor can observe the healthcare worker's perspective in real-time, facilitating immediate feedback during the screening process. When a potentially malignant area is identified, the doctor annotates the suspicious region using their computer interface. These annotations are then superimposed as 3D markings on the HoloLens display, allowing the healthcare worker to accurately target and collect tissue samples from the designated areas for biopsy. This two-way communication system has been effectively established, ensuring seamless collaboration between the healthcare worker and the remote physician, supported by a stable internet connection. Components of the Proposed Solution: The proposed solution comprises several key components: Microsoft HoloLens 2 AR glasses A standard computer for remote access A dummy cervix model for training and simulation A reliable internet connection to support bidirectional communication Screening Methodology In this setup, we developed a specific methodology for cervical cancer screening that leverages the capabilities of the HoloLens 2 AR headset. The healthcare worker, located at the patient's site, uses the HoloLens to visualize and annotate suspected areas on the cervix. Concurrently, a specialized practitioner remotely views the healthcare worker's field of vision, allowing for real-time annotations of suspected regions on the cervix. This collaborative approach assists in pinpointing areas that require further examination or biopsy. Experimental Trials To evaluate the effectiveness of our application, we conducted a series of trials utilizing a simulated cervix model made from plastic. This model contained a designated lesion area. During each trial session, one participant wearing the HoloLens faced the dummy cervix while another participant utilized a computer to mark suspected lesion areas on it. This simulation mimicked an actual cervix sample extraction procedure. Trial Design: We executed 20 sessions, each comprising 10 trials. In each trial, a remote annotator was tasked with identifying and annotating the designated region on the dummy cervical model using AR software. The individual wearing the AR headset could simultaneously view these annotations on the cervical model. Following each trial, we captured images of both the annotations and their representation on the cervical model for subsequent analysis. Results Through a series of trials, we assessed the precision of the annotation markers placed by a remote annotator in relation to their actual rendering on the HoloLens device. The analysis of the annotation accuracy from the AR sessions, as depicted in Fig. 5 , reveals significant discrepancies between the markers placed by the remote annotator and the actual rendering on the HoloLens device. The primary source of error appears to stem from the use of a single HoloLens AR device in conjunction with a computer. The remote annotator places markers on a 2D computer screen, which are then projected onto a 3D object using the HoloLens 2. This process results in accurate x and y coordinates; however, a notable offset in the z coordinate introduces unpredictability in the positioning of annotations. Table 1 summarizes the error percentages and standard deviations observed during the trials. Table 1 Error rates from the AR sample sessions on the dummy cervix model. Session No Error Percentage (%) Standard Deviation 1 8.74 2.5 2 11.02 3.92 3 5.76 2.77 4 9.76 4.18 5 6.43 0.48 6 7.11 3.74 7 14.28 2.07 8 6.69 1.92 9 11.57 0.56 10 12.42 4.35 11 9.23 3.49 12 5.13 0.61 13 4.12 2.78 14 6.89 3.46 15 11.96 2.11 16 13.15 0.32 17 8.92 4.58 18 10.01 1.14 19 8.7 0.89 20 3.71 1.76 The average error percentage across all sessions was calculated to be 8.75% with a standard deviation of ± 2.3% for this configuration using a single AR device. Discussion The implementation of the Microsoft HoloLens 2 augmented reality (AR) system has yielded promising results in facilitating remote cervical cancer screening. With a single AR device, we achieved an average error rate of 8.75% (± 2.3%), indicating a significant potential for enhancing screening accuracy in resource-limited settings. However, this level of accuracy also highlights the need for further improvements. To optimize annotation precision, we propose the incorporation of a dual AR device system, which is expected to substantially reduce errors and enhance marker placement and visualization on the AR device. This advancement would provide healthcare workers with more precise guidance in identifying and sampling suspicious regions on the cervix, thus minimizing diagnostic errors. A critical barrier to effective screening remains the lack of continuous mentoring and supervision for trained healthcare professionals (HCPs), which can lead to overtreatment or missed positive cases. Recognizing this challenge, the Government of India has proposed transforming 150,000 health sub-centres, primary health centres, and urban primary health centres into Health and Wellness Centres (HWCs) by 2022. These centres are designed to deliver comprehensive primary healthcare services, including cervical cancer screening, at the community level. Managed primarily by trained nurses and medical officers, it is recommended that an additional nurse be assigned to HWCs where cervical cancer screening is conducted. While healthcare staff will receive training to screen for and treat pre-invasive lesions, regular expert guidance will be essential during procedures for troubleshooting and decision-making. Our approach introduces an innovative method for annotating cervical images using the HoloLens 2 and AR technology. Unlike traditional methods that primarily rely on contour or Convolutional Neural Network (CNN)-based techniques, our solution offers an interactive platform that allows for real-time collaboration between healthcare workers and remote specialists. To our knowledge, this is one of the first initiatives to leverage AR for remote cervical cancer screening, enabling expert physicians to perform manual segmentation of cervical images directly. This pilot project has proven to be a computationally cost-effective tool for annotation, requiring no extensive training processes typically associated with CNNs ( 7 – 12 ). The growing adoption of AR systems in gynecologic surgeries further underscores their effectiveness in enhancing visualization and facilitating real-time interaction during procedures. For instance, AR has been successfully utilized in fibroid mapping, significantly improving detection rates of myomas during surgical interventions. Additionally, experimental AR systems have shown promise in the real-time identification of critical anatomical structures, such as the ureter, during complex surgeries. These applications highlight AR's potential to improve procedural accuracy and patient outcomes. Our proposed solution specifically addresses challenges in cervical cancer screening within resource-limited environments by providing on-site healthcare workers with remote expert supervision. While single-visit approaches (SVA) can enhance patient compliance, the absence of continuous mentorship may lead to suboptimal outcomes, such as overtreatment or missed diagnoses. The initiative to establish Health and Wellness Centres (HWCs) in India for comprehensive healthcare services, including cervical cancer screening, presents an excellent opportunity to integrate AR technology into these practices. Moreover, AR technology not only facilitates real-time guidance during the screening and treatment of pre-invasive cervical lesions but also enhances the learning experience for healthcare workers. Unlike artificial intelligence (AI)-based tools that depend on static image databases and lack interactive capabilities, our AR system fosters direct communication between healthcare workers and specialists, thereby improving screening accuracy. Although our initial findings are encouraging, further validation through extensive clinical trials is necessary to assess the effectiveness of the dual-AR device system comprehensively. Additionally, challenges related to infrastructure limitations in rural areas—particularly concerning the need for a stable internet connection—must be addressed. Future studies should focus on refining this technology and evaluating its feasibility within low-resource settings to ensure broader accessibility. Conclusion In summary, our findings support the integration of augmented reality technology into cervical cancer screening practices as a viable solution for enhancing accuracy and accessibility in underserved areas. By fostering remote collaboration between healthcare workers and specialized practitioners, we anticipate that our dual-AR device system will significantly improve the screening process and ultimately contribute to better health outcomes in cervical cancer prevention and treatment. Declarations The participants consented to participate in the study and that they were informed of the protocols Acknowledgement: None Conflicts of interests: The authors declare no conflicts of interests. Funding: No funding received by any of the authors for this work. References Bray F, Laversanne M, Sung H, Ferlay J, Siegel RL, Soerjomataram I et al (2024) Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 74(3):229–263 Martin CE, Tergas AI, Wysong M, Reinsel M, Estep D, Varallo J (2014) Evaluation of a single-visit approach to cervical cancer screening and treatment in G uyana: Feasibility, effectiveness and lessons learned. J Obstet Gynaecol Res 40(6):1707–1716 Shiferaw N, Salvador-Davila G, Kassahun K, Brooks MI, Weldegebreal T, Tilahun Y et al (2016) The Single-Visit Approach as a Cervical Cancer Prevention Strategy Among Women With HIV in Ethiopia: Successes and Lessons Learned. Glob Health Sci Pract 4(1):87–98 Saidu R, Morhason-Bello I (2022) Same-day test and treat for early detection and treatment of cervical cancer in LMICs. Lancet Glob Health 10(9):e1226–e1227 Zhu E, Hadadgar A, Masiello I, Zary N (2014) Augmented reality in healthcare education: an integrative review. PeerJ 2:e469 Navab N, Blum T, Wang L, Okur A, Wendler T (2012) First deployments of augmented reality in operating rooms. Computer 45:48–55 Zhao L, Li K, Wang M, Yin J, Zhu E, Wu C et al (2016) Automatic cytoplasm and nuclei segmentation for color cervical smear image using an efficient gap-search MRF. Comput Biol Med 71:46–56 Gautam S, Bhavsar A, Sao AK, H KK (2018) CNN based segmentation of nuclei in PAP-smear images with selective pre-processing. In: Gurcan MN, Tomaszewski JE, editors. Medical Imaging 2018: Digital Pathology [Internet]. Houston, United States: SPIE; [cited 2024 Nov 16]. p. 32. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/10581/2293526/CNN-based-segmentation-of-nuclei-in-PAP-smear-images-with/ 10.1117/12.2293526.full Tan X, Li K, Zhang J, Wang W, Wu B, Wu J et al (2021) Automatic model for cervical cancer screening based on convolutional neural network: a retrospective, multicohort, multicenter study. Cancer Cell Int 21(1):35 YOLO_CC Deep Learning based Approach for Early Stage Detection of Cervical Cancer from Cervix Images Using YOLOv5s Model | IEEE Conference Publication | IEEE Xplore [Internet]. [cited 2024 Nov 16]. https://ieeexplore.ieee.org/document/9807871 Hodneland E, Kaliyugarasan S, Wagner-Larsen KS, Lura N, Andersen E, Bartsch H et al (2022) Fully Automatic Whole-Volume Tumor Segmentation in Cervical Cancer. Cancers 14(10):2372 Song Y, Zhu L, Qin J, Lei B, Sheng B, Choi KS (2019) Segmentation of Overlapping Cytoplasm in Cervical Smear Images via Adaptive Shape Priors Extracted From Contour Fragments. IEEE Trans Med Imaging 38(12):2849–2862 Additional Declarations The authors declare no competing interests. Supplementary Files Graphicabstract.png Graphic abstract 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-5484245","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":380114749,"identity":"cbb26b26-380e-4802-bec3-600bef0cae43","order_by":0,"name":"Seema Singhal","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBElEQVRIiWNgGAWjYDCCA1CaDYwKbIBMxsYDuNVjaDFIA2lpIE4LRJfBYXRBTMB3+/jDBx9z7Oz5pNuvPfhhcN5ubfthoC01NtG4tEieyzE2nLktObFN5ky5YY/B7eRtZxKBWo6l5Tbg0GJwhodNmncbcwKbRE6aBA9Qi9kBoBbGhsN4tLA///13W709SIvkH4NzyWbnHxLSwmDGzLjtMGObRPoxaR6DA3ZmNwjYInmGx1iyd9vxxDaJHDZpGYPkBLMbQFsS8PiF7wz7ww8/t1Xby89Ifyb5psLO3ux8+sMHH2pscGpBAjwGIDIRrDKBsHIQYH8AIu2JUzwKRsEoGAUjCQAA1XJigfffdYAAAAAASUVORK5CYII=","orcid":"","institution":"All India Institute of Medical Sciences, New Delhi","correspondingAuthor":true,"prefix":"","firstName":"Seema","middleName":"","lastName":"Singhal","suffix":""},{"id":380115484,"identity":"87ee5e31-8c6b-4b39-bd65-4acdb7f014e8","order_by":1,"name":"Tapan Gandhi","email":"","orcid":"","institution":"Indian Institute of Technology, Delhi","correspondingAuthor":false,"prefix":"","firstName":"Tapan","middleName":"","lastName":"Gandhi","suffix":""},{"id":380115485,"identity":"e8aa3678-3e81-41f1-beb2-4772580c23b0","order_by":2,"name":"Arjun Ganguly","email":"","orcid":"","institution":"All India Institute of Medical Sciences, New Delhi","correspondingAuthor":false,"prefix":"","firstName":"Arjun","middleName":"","lastName":"Ganguly","suffix":""},{"id":380115486,"identity":"5c28ae23-b0ec-42b3-a4b8-805a75e7be9f","order_by":3,"name":"Aarthi S Jayraj","email":"","orcid":"","institution":"All India Institute of Medical Sciences, New Delhi","correspondingAuthor":false,"prefix":"","firstName":"Aarthi","middleName":"S","lastName":"Jayraj","suffix":""}],"badges":[],"createdAt":"2024-11-19 14:13:26","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-5484245/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5484245/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":69769024,"identity":"1d51ab0d-3904-486d-bf04-c95c29b32252","added_by":"auto","created_at":"2024-11-25 06:15:43","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":10532,"visible":true,"origin":"","legend":"\u003cp\u003eMicrosoft HoloLens 2\u003c/p\u003e","description":"","filename":"Figure1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-5484245/v1/21e1c4b3b8a45e06bd9dd100.jpg"},{"id":69769022,"identity":"0777e66a-6ca5-48e9-a7e9-0b74678f06c5","added_by":"auto","created_at":"2024-11-25 06:15:43","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":267747,"visible":true,"origin":"","legend":"\u003cp\u003eHealthcare worker utilizing AR tools for cervical cancer inspection on a dummy model\u003c/p\u003e","description":"","filename":"Figure2.png","url":"https://assets-eu.researchsquare.com/files/rs-5484245/v1/844d7c3740470fc54d604dc5.png"},{"id":69769021,"identity":"c00c1337-84d1-48b1-a023-8f933b19efc7","added_by":"auto","created_at":"2024-11-25 06:15:43","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":78443,"visible":true,"origin":"","legend":"\u003cp\u003eWorking principle of the solution\u003c/p\u003e","description":"","filename":"Figure3.png","url":"https://assets-eu.researchsquare.com/files/rs-5484245/v1/8d1609b014fe471af1ef0b20.png"},{"id":69769025,"identity":"356e1417-3fd7-4b45-ac59-1c2f6cc46dae","added_by":"auto","created_at":"2024-11-25 06:15:43","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":171190,"visible":true,"origin":"","legend":"\u003cp\u003eFlowchart detailing the sample collection process using our AR application hosted on HoloLens 2.\u003c/p\u003e","description":"","filename":"Figure4.png","url":"https://assets-eu.researchsquare.com/files/rs-5484245/v1/a20e7c7499292b0151305265.png"},{"id":69769026,"identity":"ac667f42-1649-4918-86c2-e65a070801be","added_by":"auto","created_at":"2024-11-25 06:15:43","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":684607,"visible":true,"origin":"","legend":"\u003cp\u003eImages of the remote annotators view (A) (C) (E) and the actual placement of the visual annotation marks as seen by the personnel wearing the AR device (B) (D) (F)\u003c/p\u003e","description":"","filename":"Figure5.png","url":"https://assets-eu.researchsquare.com/files/rs-5484245/v1/2d9e83961471e3c735bc2922.png"},{"id":69770031,"identity":"b8dbafac-6b8a-4a1d-83d6-b90c8e8fbaf3","added_by":"auto","created_at":"2024-11-25 06:24:12","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1821165,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5484245/v1/94880002-82a5-4fb5-864e-fe094ec7dae7.pdf"},{"id":69769510,"identity":"a67e7865-d01c-4bfd-8dcc-3bfbaefa303d","added_by":"auto","created_at":"2024-11-25 06:23:43","extension":"png","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2710992,"visible":true,"origin":"","legend":"\u003cp\u003eGraphic abstract\u003c/p\u003e","description":"","filename":"Graphicabstract.png","url":"https://assets-eu.researchsquare.com/files/rs-5484245/v1/0659d240e6d87600dac3c106.png"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eAdopting Augmented Reality to Improve Visual Inspection in a Single-Visit Cervical Cancer Screening Framework\u003c/p\u003e","fulltext":[{"header":"Introduction","content":"\u003cp\u003eCervical cancer is a significant public health issue in India, contributing to approximately one-fifth of the global burden of the disease. With an estimated 127,526 new cases and 79,906 deaths reported in 2022, cervical cancer poses a critical challenge for healthcare systems, particularly among women in low- and middle-income countries (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e). Despite being a preventable disease, many women present with advanced stages of cervical cancer due to inadequate access to screening and treatment services .\u003c/p\u003e \u003cp\u003eExisting literature highlights the effectiveness of systematic and quality-assured cervical cancer screening programs in reducing incidence rates significantly. Studies have shown that population-based screening can lead to more than a 70% reduction in cervical cancer cases in developed countries. However, similar success has not been replicated in India and other low-resource settings, where screening coverage remains alarmingly low, often below 20%. The subjective nature of current screening methods, such as visual inspection with acetic acid (VIA), further complicates accurate diagnosis and treatment. Single visit approach (SVA) or see-and-treat strategy significant increases effectiveness of screening programs by linking immediate treatment in a single healthcare visit and is shown to be feasible and acceptable (\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e). The major challenge for implementation of SVA is lack of resources in terms of trained gynaecologists and inadequate healthcare personnel (\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e). Augmented Reality (AR) is increasingly being applied in healthcare and holds tremendous future potential (\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e). AR overlays virtual objects onto the real world, enabling users to interact with these elements. In recent years, AR has gained popularity in medical applications, especially in simulation training, where it facilitates interaction with 3D digital models, providing a better understanding of human anatomy for surgical procedures (\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eThere is an urgent need to address these gaps by providing effective mentorship and guidance for healthcare providers (HCPs). In this project, we aimed to examine the feasibility of utilizing the Microsoft HoloLens 2, an AR-based Head Mounted Display (HMD), for remotely assisting healthcare workers in cervical cancer screening. This system aims to bridge the gap in access to specialized healthcare services while enhancing diagnostic accuracy within a single-visit framework, leveraging AR technology to improve screening outcomes and ensure timely treatment. Currently, we report on Phase I of our research, which focuses on developing an AR-enabled camera tool customized for cervical photography.\u003c/p\u003e"},{"header":"Methodology","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e\u003cem\u003eOverview of the System\u003c/em\u003e:\u003c/h2\u003e \u003cp\u003eThe implemented system utilizes Microsoft HoloLens 2 augmented reality (AR) technology to enhance cervical cancer screening in rural healthcare settings. A healthcare worker, stationed in a remote location, dons the HoloLens while conducting patient screenings. This device connects the healthcare worker to a remote, specialized physician through a computer interface, enabling real-time visual supervision and guidance.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eReal-Time Collaboration:\u003c/h3\u003e\n\u003cp\u003eThe remote doctor can observe the healthcare worker's perspective in real-time, facilitating immediate feedback during the screening process. When a potentially malignant area is identified, the doctor annotates the suspicious region using their computer interface. These annotations are then superimposed as 3D markings on the HoloLens display, allowing the healthcare worker to accurately target and collect tissue samples from the designated areas for biopsy. This two-way communication system has been effectively established, ensuring seamless collaboration between the healthcare worker and the remote physician, supported by a stable internet connection.\u003c/p\u003e\n\u003ch3\u003eComponents of the Proposed Solution:\u003c/h3\u003e\n\u003cp\u003eThe proposed solution comprises several key components:\u003c/p\u003e \u003cp\u003e \u003cul\u003e \u003cli\u003e \u003cp\u003eMicrosoft HoloLens 2 AR glasses\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eA standard computer for remote access\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eA dummy cervix model for training and simulation\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eA reliable internet connection to support bidirectional communication\u003c/p\u003e \u003c/li\u003e \u003c/ul\u003e \u003c/p\u003e\n\u003ch3\u003eScreening Methodology\u003c/h3\u003e\n\u003cp\u003eIn this setup, we developed a specific methodology for cervical cancer screening that leverages the capabilities of the HoloLens 2 AR headset. The healthcare worker, located at the patient's site, uses the HoloLens to visualize and annotate suspected areas on the cervix. Concurrently, a specialized practitioner remotely views the healthcare worker's field of vision, allowing for real-time annotations of suspected regions on the cervix. This collaborative approach assists in pinpointing areas that require further examination or biopsy.\u003c/p\u003e\n\u003ch3\u003eExperimental Trials\u003c/h3\u003e\n\u003cp\u003eTo evaluate the effectiveness of our application, we conducted a series of trials utilizing a simulated cervix model made from plastic. This model contained a designated lesion area. During each trial session, one participant wearing the HoloLens faced the dummy cervix while another participant utilized a computer to mark suspected lesion areas on it. This simulation mimicked an actual cervix sample extraction procedure.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eTrial Design:\u003c/h2\u003e \u003cp\u003eWe executed 20 sessions, each comprising 10 trials. In each trial, a remote annotator was tasked with identifying and annotating the designated region on the dummy cervical model using AR software. The individual wearing the AR headset could simultaneously view these annotations on the cervical model. Following each trial, we captured images of both the annotations and their representation on the cervical model for subsequent analysis.\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cp\u003eThrough a series of trials, we assessed the precision of the annotation markers placed by a remote annotator in relation to their actual rendering on the HoloLens device. The analysis of the annotation accuracy from the AR sessions, as depicted in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e, reveals significant discrepancies between the markers placed by the remote annotator and the actual rendering on the HoloLens device. The primary source of error appears to stem from the use of a single HoloLens AR device in conjunction with a computer. The remote annotator places markers on a 2D computer screen, which are then projected onto a 3D object using the HoloLens 2. This process results in accurate x and y coordinates; however, a notable offset in the z coordinate introduces unpredictability in the positioning of annotations. Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e summarizes the error percentages and standard deviations observed during the trials.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eError rates from the AR sample sessions on the dummy cervix model.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSession No\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eError Percentage (%)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eStandard Deviation\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e8.74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2.5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e11.02\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3.92\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e5.76\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2.77\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e9.76\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4.18\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e6.43\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.48\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e7.11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3.74\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e14.28\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2.07\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e6.69\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.92\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e11.57\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.56\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e12.42\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4.35\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e9.23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3.49\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e5.13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.61\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4.12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2.78\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e6.89\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3.46\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e11.96\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2.11\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e13.15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.32\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e8.92\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4.58\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e10.01\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.14\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e8.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.89\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3.71\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.76\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eThe average error percentage across all sessions was calculated to be 8.75% with a standard deviation of \u0026plusmn;\u0026thinsp;2.3% for this configuration using a single AR device.\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eThe implementation of the Microsoft HoloLens 2 augmented reality (AR) system has yielded promising results in facilitating remote cervical cancer screening. With a single AR device, we achieved an average error rate of 8.75% (\u0026plusmn;\u0026thinsp;2.3%), indicating a significant potential for enhancing screening accuracy in resource-limited settings. However, this level of accuracy also highlights the need for further improvements. To optimize annotation precision, we propose the incorporation of a dual AR device system, which is expected to substantially reduce errors and enhance marker placement and visualization on the AR device. This advancement would provide healthcare workers with more precise guidance in identifying and sampling suspicious regions on the cervix, thus minimizing diagnostic errors.\u003c/p\u003e \u003cp\u003eA critical barrier to effective screening remains the lack of continuous mentoring and supervision for trained healthcare professionals (HCPs), which can lead to overtreatment or missed positive cases. Recognizing this challenge, the Government of India has proposed transforming 150,000 health sub-centres, primary health centres, and urban primary health centres into Health and Wellness Centres (HWCs) by 2022. These centres are designed to deliver comprehensive primary healthcare services, including cervical cancer screening, at the community level. Managed primarily by trained nurses and medical officers, it is recommended that an additional nurse be assigned to HWCs where cervical cancer screening is conducted. While healthcare staff will receive training to screen for and treat pre-invasive lesions, regular expert guidance will be essential during procedures for troubleshooting and decision-making.\u003c/p\u003e \u003cp\u003eOur approach introduces an innovative method for annotating cervical images using the HoloLens 2 and AR technology. Unlike traditional methods that primarily rely on contour or Convolutional Neural Network (CNN)-based techniques, our solution offers an interactive platform that allows for real-time collaboration between healthcare workers and remote specialists. To our knowledge, this is one of the first initiatives to leverage AR for remote cervical cancer screening, enabling expert physicians to perform manual segmentation of cervical images directly. This pilot project has proven to be a computationally cost-effective tool for annotation, requiring no extensive training processes typically associated with CNNs (\u003cspan additionalcitationids=\"CR8 CR9 CR10 CR11\" citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eThe growing adoption of AR systems in gynecologic surgeries further underscores their effectiveness in enhancing visualization and facilitating real-time interaction during procedures. For instance, AR has been successfully utilized in fibroid mapping, significantly improving detection rates of myomas during surgical interventions. Additionally, experimental AR systems have shown promise in the real-time identification of critical anatomical structures, such as the ureter, during complex surgeries. These applications highlight AR's potential to improve procedural accuracy and patient outcomes.\u003c/p\u003e \u003cp\u003eOur proposed solution specifically addresses challenges in cervical cancer screening within resource-limited environments by providing on-site healthcare workers with remote expert supervision. While single-visit approaches (SVA) can enhance patient compliance, the absence of continuous mentorship may lead to suboptimal outcomes, such as overtreatment or missed diagnoses. The initiative to establish Health and Wellness Centres (HWCs) in India for comprehensive healthcare services, including cervical cancer screening, presents an excellent opportunity to integrate AR technology into these practices.\u003c/p\u003e \u003cp\u003eMoreover, AR technology not only facilitates real-time guidance during the screening and treatment of pre-invasive cervical lesions but also enhances the learning experience for healthcare workers. Unlike artificial intelligence (AI)-based tools that depend on static image databases and lack interactive capabilities, our AR system fosters direct communication between healthcare workers and specialists, thereby improving screening accuracy.\u003c/p\u003e \u003cp\u003eAlthough our initial findings are encouraging, further validation through extensive clinical trials is necessary to assess the effectiveness of the dual-AR device system comprehensively. Additionally, challenges related to infrastructure limitations in rural areas\u0026mdash;particularly concerning the need for a stable internet connection\u0026mdash;must be addressed. Future studies should focus on refining this technology and evaluating its feasibility within low-resource settings to ensure broader accessibility.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eIn summary, our findings support the integration of augmented reality technology into cervical cancer screening practices as a viable solution for enhancing accuracy and accessibility in underserved areas. By fostering remote collaboration between healthcare workers and specialized practitioners, we anticipate that our dual-AR device system will significantly improve the screening process and ultimately contribute to better health outcomes in cervical cancer prevention and treatment.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003eThe participants consented to participate in the study and that they were informed of the protocols\u003c/p\u003e\u003cp\u003eAcknowledgement: None\u003c/p\u003e\n\u003cp\u003eConflicts of interests: The authors declare no conflicts of interests.\u003c/p\u003e\n\u003cp\u003eFunding: No funding received by any of the authors for this work.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eBray F, Laversanne M, Sung H, Ferlay J, Siegel RL, Soerjomataram I et al (2024) Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 74(3):229\u0026ndash;263\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMartin CE, Tergas AI, Wysong M, Reinsel M, Estep D, Varallo J (2014) Evaluation of a single-visit approach to cervical cancer screening and treatment in G uyana: Feasibility, effectiveness and lessons learned. J Obstet Gynaecol Res 40(6):1707\u0026ndash;1716\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShiferaw N, Salvador-Davila G, Kassahun K, Brooks MI, Weldegebreal T, Tilahun Y et al (2016) The Single-Visit Approach as a Cervical Cancer Prevention Strategy Among Women With HIV in Ethiopia: Successes and Lessons Learned. Glob Health Sci Pract 4(1):87\u0026ndash;98\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSaidu R, Morhason-Bello I (2022) Same-day test and treat for early detection and treatment of cervical cancer in LMICs. Lancet Glob Health 10(9):e1226\u0026ndash;e1227\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhu E, Hadadgar A, Masiello I, Zary N (2014) Augmented reality in healthcare education: an integrative review. PeerJ 2:e469\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNavab N, Blum T, Wang L, Okur A, Wendler T (2012) First deployments of augmented reality in operating rooms. Computer 45:48\u0026ndash;55\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhao L, Li K, Wang M, Yin J, Zhu E, Wu C et al (2016) Automatic cytoplasm and nuclei segmentation for color cervical smear image using an efficient gap-search MRF. Comput Biol Med 71:46\u0026ndash;56\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGautam S, Bhavsar A, Sao AK, H KK (2018) CNN based segmentation of nuclei in PAP-smear images with selective pre-processing. In: Gurcan MN, Tomaszewski JE, editors. Medical Imaging 2018: Digital Pathology [Internet]. Houston, United States: SPIE; [cited 2024 Nov 16]. p. 32. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.spiedigitallibrary.org/conference-proceedings-of-spie/10581/2293526/CNN-based-segmentation-of-nuclei-in-PAP-smear-images-with/\u003c/span\u003e\u003cspan address=\"https://www.spiedigitallibrary.org/conference-proceedings-of-spie/10581/2293526/CNN-based-segmentation-of-nuclei-in-PAP-smear-images-with/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1117/12.2293526.full\u003c/span\u003e\u003cspan address=\"10.1117/12.2293526.full\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTan X, Li K, Zhang J, Wang W, Wu B, Wu J et al (2021) Automatic model for cervical cancer screening based on convolutional neural network: a retrospective, multicohort, multicenter study. Cancer Cell Int 21(1):35\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYOLO_CC Deep Learning based Approach for Early Stage Detection of Cervical Cancer from Cervix Images Using YOLOv5s Model | IEEE Conference Publication | IEEE Xplore [Internet]. [cited 2024 Nov 16]. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://ieeexplore.ieee.org/document/9807871\u003c/span\u003e\u003cspan address=\"https://ieeexplore.ieee.org/document/9807871\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHodneland E, Kaliyugarasan S, Wagner-Larsen KS, Lura N, Andersen E, Bartsch H et al (2022) Fully Automatic Whole-Volume Tumor Segmentation in Cervical Cancer. Cancers 14(10):2372\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSong Y, Zhu L, Qin J, Lei B, Sheng B, Choi KS (2019) Segmentation of Overlapping Cytoplasm in Cervical Smear Images via Adaptive Shape Priors Extracted From Contour Fragments. IEEE Trans Med Imaging 38(12):2849\u0026ndash;2862\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"All India Institute of Medical Sciences","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"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":"Cervical cancer, Augmented reality, Virtual reality, Real-time visualization","lastPublishedDoi":"10.21203/rs.3.rs-5484245/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5484245/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cb\u003eBackground\u003c/b\u003e\u003c/p\u003e \u003cp\u003eCervical cancer is a major public health concern in India, accounting for one-fifth of the global burden. This study examines the use of Augmented Reality (AR) technology to enhance diagnostic accuracy among healthcare providers (HCPs) within a single-visit screening framework, addressing the shortage of expert gynaecologists for onsite mentoring.\u003c/p\u003e\u003cp\u003e\u003cb\u003eMethods\u003c/b\u003e\u003c/p\u003e \u003cp\u003eWe developed an AR-enabled tool using the Microsoft HoloLens 2 headset to assist in cervical cancer screening by identifying suspected lesion areas. A remote healthcare worker equipped with the HoloLens collaborated with a specialized practitioner operating a computer to annotate suspicious regions on a simulated plastic cervix model with a designated lesion, simulating real-life conditions.\u003c/p\u003e\u003cp\u003e\u003cb\u003eResults\u003c/b\u003e\u003c/p\u003e \u003cp\u003eThe AR system projected a 3D cervix model into the real environment for remote annotation, demonstrating an average error rate of 8.75% (\u0026plusmn;\u0026thinsp;2.3%) during trials.\u003c/p\u003e\u003cp\u003e\u003cb\u003eConclusion\u003c/b\u003e\u003c/p\u003e \u003cp\u003eThe HoloLens 2 AR system has been shown to enhance the accuracy and efficiency of visual cervical cancer screening, with significant potential to improve screening in underserved areas. Future plans include using two AR devices to enhance accuracy in real-world data collection and further trials to validate its effectiveness and scalability in diverse healthcare settings.\u003c/p\u003e","manuscriptTitle":"Adopting Augmented Reality to Improve Visual Inspection in a Single-Visit Cervical Cancer Screening Framework","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-25 06:15:38","doi":"10.21203/rs.3.rs-5484245/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":"f38327f7-d9b7-4533-9275-550cc159d049","owner":[],"postedDate":"November 25th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":40482026,"name":"Obstetrics \u0026 Gynecology"}],"tags":[],"updatedAt":"2024-11-25T06:15:38+00:00","versionOfRecord":[],"versionCreatedAt":"2024-11-25 06:15:38","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5484245","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5484245","identity":"rs-5484245","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}