Study protocol for a two-site clinical trial to validate a smartphone-based artificial intelligence classifier identifying cervical precancer and cancer in HPV-positive women in Cameroon

Inès Baleydier, Pierre Vassilakos, Roser Viñals, Ania Wisniak, Bruno Kenfack, Jovanny Tsuala Fouogue, George Enownchong Enow Orock, Sophie Lemoupa Makajio, Evelyn Foguem Tincho, Manuela Undurraga, Magali Cattin, Solomzi Makohliso, Klaus Schönenberger, Alain Gervaix, Jean-Philippe Thiran, Patrick Petignat, Inès Baleydier, Pierre Vassilakos, Roser Viñals, Ania Wisniak, Bruno Kenfack, Jovanny Tsuala Fouogue, George Enownchong Enow Orock, Sophie Lemoupa Makajio, Evelyn Foguem Tincho, Manuela Undurraga, Magali Cattin, Solomzi Makohliso, Klaus Schönenberger, Alain Gervaix, Jean-Philippe Thiran, Patrick Petignat

Abstract

Introduction: Cervical cancer remains a major public health challenge in low- and middle-income countries (LMICs) due to financial and logistical issues. WHO recommendation for cervical cancer screening in LMICs includes HPV testing as primary screening followed by visual inspection with acetic acid (VIA) and treatment. However, VIA is a subjective procedure dependent on the healthcare provider's experience. Its accuracy can be improved by computer-aided detection techniques. Our aim is to assess the performance of a smartphone-based Automated VIA Classifier (AVC) relying on Artificial Intelligence to discriminate precancerous and cancerous lesions from normal cervical tissue.

Methods: The AVC study will be nested in an ongoing cervical cancer screening program called "3T-study" (for Test, Triage and Treat), including HPV self-sampling followed by VIA triage and treatment if needed. After application of acetic acid on the cervix, precancerous and cancerous cells whiten more rapidly than non-cancerous ones and their whiteness persists stronger overtime. The AVC relies on this key feature to determine whether the cervix is suspect for precancer or cancer. In order to train and validate the AVC, 6000 women aged 30 to 49 years meeting the inclusion criteria will be recruited on a voluntary basis, with an estimated 100 CIN2+, calculated using a confidence level of 95% and an estimated sensitivity of 90% +/-7% precision on either side. Diagnostic test performance of AVC test and two current standard tests (VIA and cytology) used routinely for triage will be evaluated and compared. Histopathological examination will serve as reference standard. Participants' and providers' acceptability of the technology will also be assessed. The study protocol was registered under ClinicalTrials.gov (number NCT04859530).

Expected results: The study will determine whether AVC test can be an effective method for cervical cancer screening in LMICs.

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1. Process description of the AVC…
Fig 1. Process description of the AVC test. Adapted with permission from [15].
Fig 2. Flowchart of the clinical trial.
Fig 2. Flowchart of the clinical trial.
Abbreviations: TZ = Transformation zone, LLETZ = Large loop excision of the transformation zone.
Fig 3. 3T study data management plan.
Fig 3. 3T study data management plan.
Cameroon: participants will be pseudonymized with an identification key consisting of a code number and the participant’s initials. A paper Case Report Form (pCRF) will be created for each research subject: it will contain its personal, medical and screening-related information. These data will also be electronically stored (eCRF) in a RDBMS (Relational Database Management System) using a dedicated CDMS software (Clinical Database Management System) called secuTrial®. This software will also be used to save VA images, AVC test results and delimitation maps. University Hospitals of Geneva: a secure password-protected PC at the Department of Pediatrics, Gynecology and Obstetrics (DFEA) will store all collected data (dashed rectangle) and eCRFs will be accessible on secuTrial®. Data management will be performed by the Unit of Clinical Investigation (UIC), a unit which is part of the Clinical Research Center (CRC) at HUG as well as by designated research assistants at the DFEA. Cytological and histopathological samples will be transported by aircraft and analyzed at the Division of Clinical Pathology of the HUG, in conformity with Swiss standards and international recommendations. Smartphone videos will be shared by SWITCH drive (https://www.switch.ch/drive/) in the form of 120 frames. The last frame will be labelled by a colposcopy specialist of HUG who will also manually delimitate any visible lesion. EPFL: Final results (positive/negative), lesion delimitation maps and probability maps (PNG format) obtained during the AVC test will be stored in a secure NAS server in EPFL.
Fig 4. Project schedule and milestones.
Fig 4. Project schedule and milestones.

References

    1. Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2018;68(6):394–424. doi: 10.3322/caac.21492
    1. Bruni L, Diaz M, Barrionuevo-Rosas L, Herrero R, Bray F, Bosch FX, et al.. Global estimates of human papillomavirus vaccination coverage by region and income level: a pooled analysis. The Lancet Global Health. 2016;4(7):e453–e63. doi: 10.1016/S2214-109X(16)30099-7
    1. Observatory GC. Cancer Tomorrow 2018 Estimates 2018. [Available from: .
    1. Das M. WHO launches strategy to accelerate elimination of cervical cancer. The Lancet Oncology. 2021;22(1):20–1. doi: 10.1016/S1470-2045(20)30729-4
    1. Organization WH. Guidelines for screening and treatment of precancerous lesions for cervical cancer prevention. 2013.
    1. Dijkstra MG, van Zummeren M, Rozendaal L, van Kemenade FJ, Helmerhorst TJ, Snijders PJ, et al.. Safety of extending screening intervals beyond five years in cervical screening programmes with testing for high risk human papillomavirus: 14 year follow-up of population based randomised cohort in the Netherlands. BMJ. 2016;355:i4924. doi: 10.1136/bmj.i4924
    1. Pierre V. Vingt années de lutte contre le cancer du col utérin en Afrique subsaharienne. Rev Med Suisse. 2019.
    1. Arrossi S, Thouyaret L, Herrero R, Campanera A, Magdaleno A, Cuberli M, et al.. Effect of self-collection of HPV DNA offered by community health workers at home visits on uptake of screening for cervical cancer (the EMA study): a population-based cluster-randomised trial. The Lancet Global Health. 2015;3(2):e85–e94. doi: 10.1016/S2214-109X(14)70354-7
    1. Bigoni J, Gundar M, Tebeu PM, Bongoe A, Schafer S, Fokom-Domgue J, et al.. Cervical cancer screening in sub-Saharan Africa: a randomized trial of VIA versus cytology for triage of HPV-positive women. Int J Cancer. 2015;137(1):127–34. doi: 10.1002/ijc.29353
    1. Gravitt PE, Paul P, Katki HA, Vendantham H, Ramakrishna G, Sudula M, et al.. Effectiveness of VIA, Pap, and HPV DNA testing in a cervical cancer screening program in a peri-urban community in Andhra Pradesh, India. PLoS One. 2010;5(10):e13711. doi: 10.1371/journal.pone.0013711
    1. Ajenifuja KO, Gage JC, Adepiti AC, Wentzensen N, Eklund C, Reilly M, et al.. A population-based study of visual inspection with acetic acid (VIA) for cervical screening in rural Nigeria. Int J Gynecol Cancer. 2013;23(3):507–12. doi: 10.1097/IGC.0b013e318280f395
    1. Etherington IJ, Luesley DM, Shafi MI, Dunn J, Hiller L, Jordan JA. Observer variability among colposcopists from the West Midlands region. Br J Obstet Gynaecol. 1997;104(12):1380–4. doi: 10.1111/j.1471-0528.1997.tb11007.x
    1. Tebeu PM, Fokom-Domgue J, Crofts V, Flahaut E, Catarino R, Untiet S, et al.. Effectiveness of a two-stage strategy with HPV testing followed by visual inspection with acetic acid for cervical cancer screening in a low-income setting. Int J Cancer. 2015;136(6):E743–50. doi: 10.1002/ijc.29250
    1. Kunckler M, Schumacher F, Kenfack B, Catarino R, Viviano M, Tincho E, et al.. Cervical cancer screening in a low-resource setting: a pilot study on an HPV-based screen-and-treat approach. Cancer Med. 2017;6(7):1752–61. doi: 10.1002/cam4.1089
    1. Viñals R, Vassilakos P, Rad MS, Undurraga M, Petignat P, Thiran J-P. Using Dynamic Features for Automatic Cervical Precancer Detection. Diagnostics. 2021;11(4). doi: 10.3390/diagnostics11040716
    1. Gallay C, Girardet A, Viviano M, Catarino R, Benski AC, Tran PL, et al.. Cervical cancer screening in low-resource settings: a smartphone image application as an alternative to colposcopy. Int J Womens Health. 2017;9:455–61. doi: 10.2147/IJWH.S136351
    1. Ricard-Gauthier D, Wisniak A, Catarino R, van Rossum AF, Meyer-Hamme U, Negulescu R, et al.. Use of Smartphones as Adjuvant Tools for Cervical Cancer Screening in Low-Resource Settings. J Low Genit Tract Dis. 2015;19(4):295–300. doi: 10.1097/LGT.0000000000000136
    1. Tran PL, Benski C, Viviano M, Petignat P, Combescure C, Jinoro J, et al.. PERFORMANCE OF SMARTPHONE-BASED DIGITAL IMAGES FOR CERVICAL CANCER SCREENING IN A LOW-RESOURCE CONTEXT. Int J Technol Assess Health Care. 2018;34(3):337–42. doi: 10.1017/S0266462318000260
    1. Levy J, de Preux M, Kenfack B, Sormani J, Catarino R, Tincho EF, et al.. Implementing the 3T-approach for cervical cancer screening in Cameroon: Preliminary results on program performance. Cancer Med. 2020;9(19):7293–300. doi: 10.1002/cam4.3355
    1. Fernandes K, Cardoso JS, Fernandes J. Automated Methods for the Decision Support of Cervical Cancer Screening Using Digital Colposcopies. IEEE Access. 2018;6:33910–27.
    1. Xue P, Ng MTA, Qiao Y. The challenges of colposcopy for cervical cancer screening in LMICs and solutions by artificial intelligence. BMC Med. 2020;18(1):169. doi: 10.1186/s12916-020-01613-x

Source: PubMed

Sponsorzy i współpracownicy

Warunki medyczne

Interwencje lekowe

3
Subskrybuj