OpenLB
Open Library of Bioscience
Advanced Search
Cytopathology : official journal of the British Society for Clinical Cytology
May, 2025;36 (3): 250-258.

Digital Cytology Combined With Artificial Intelligence Compared to Conventional Microscopy for Anal Cytology: A Preliminary Study.

Renê Gerhard, Cioly Rivero Colmenarez, Corinne Selle, Gaël Paul Hammer
Author Information
  1. Renê Gerhard: Centre National de Pathologie, Laboratoire National de Santé, Dudelange, Luxembourg. ORCID
  2. Cioly Rivero Colmenarez: Centre National de Pathologie, Laboratoire National de Santé, Dudelange, Luxembourg.
  3. Corinne Selle: Centre National de Pathologie, Laboratoire National de Santé, Dudelange, Luxembourg.
  4. Gaël Paul Hammer: Centre National de Pathologie, Laboratoire National de Santé, Dudelange, Luxembourg. ORCID
PMID: 40070157 DOI: 10.1111/cyt.13482

Abstract

INTRODUCTION: Recent studies have shown that digital cytology (DC) coupled with artificial intelligence (AI) algorithms is a valid approach to the diagnosis of cervico-vaginal lesions using liquid-based cytology (LBC). We evaluated the use of these methods for anal LBC specimens.
METHODS: A series of 124 anal LBC slides previously diagnosed by conventional microscopy (CC) were reviewed with a DC/AI system that generated a gallery of images. Diagnoses based on the selected images, according to the 2014 Bethesda System for Reporting Cervical Cytology, were compared to CC.
RESULTS: Overall, CC and DC/AI approaches detected a similar number of abnormal (ASC-US+) cases (63 and 62 cases, respectively). We observed an exact concordance between CC and DC in 70 (57.9%) cases, corresponding to a moderate agreement between the two approaches (κ = 0.41, p < 0.001). A moderate agreement (κ = 0.48, p < 0.001) was also found when positive cases were stratified into 'low-grade' (ASC-US, LSIL) and 'high-grade' lesions (ASC-H, HSIL). The DC/AI system detected more cases of higher severity (ASC-H, HSIL: 9 and 2 cases, respectively) than CC (3 cases classified as HSIL).
CONCLUSIONS: The number of ASC-US+ cases detected by both systems was similar. The DC/AI system detected more cases of higher severity compared to the CC.

Keywords

anal cytology artificial intelligence digital cytology

References

  1. G. M. Clifford, D. Georges, M. S. Shiels, et al., “A Meta‐Analysis of Anal Cancer Incidence by Risk Group: Toward a Unified Anal Cancer Risk Scale,” International Journal of Cancer 148, no. 1 (2021): 38–47.
  2. C. Lin, S. Franceschi, and G. M. Clifford, “Human Papillomavirus Types From Infection to Cancer in the Anus, According to Sex and HIV Status: A Systematic Review and Meta‐Analysis,” Lancet Infectious Diseases 18, no. 2 (2018): 198–206.
  3. M. A. Clarke and N. Wentzensen, “Strategies for Screening and Early Detection of Anal Cancers: A Narrative and Systematic Review and Meta‐Analysis of Cytology, HPV Testing, and Other Biomarkers,” Cancer Cytopathology 126, no. 7 (2018): 447–460.
  4. l. Spindler, I. Etienney, L. Abramowitz, et al., “Screening for Precancerous Anal Lesions Linked to Human Papillomaviruses: French Recommendations for Clinical Practice,” Techniques in Coloproctology 28, no. 1 (2024): 23.
  5. A. Albuquerque, E. Rios, and F. Schmitt, “Recommendations Favoring Anal Cytology as a Method for Anal Cancer Screening: A Systematic Review,” Cancers (Basel) 11, no. 12 (2019): 1942.
  6. J. M. Berry, J. M. Palefsky, N. Jay, S. C. Cheng, T. M. Darragh, and P. V. Chin‐Hong, “Performance Characteristics of Anal Cytology and Human Papillomavirus Testing in Patients With High‐Resolution Anoscopy‐Guided Biopsy of High‐Grade Anal Intraepithelial Neoplasia,” Diseases of the Colon and Rectum 52, no. 2 (2009): 239–247.
  7. J. C. N. Gonçalves, A. C. L. Macedo, K. Madeira, et al., “Accuracy of Anal Cytology for Diagnostic of Precursor Lesions of Anal Cancer: Systematic Review and Meta‐Analysis,” Diseases of the Colon and Rectum 62, no. 1 (2019): 112–120.
  8. C. Zhao, A. B. Domfeh, and R. M. Austin, “Histopathologic Outcomes and Clinical Correlations for High‐Risk Patients Screened With Anal Cytology,” Acta Cytologica 56, no. 1 (2012): 62–67.
  9. E. M. Betancourt, M. M. Wahbah, L. C. Been, E. Y. Chiao, D. R. Citron, and R. Lauricia, “Anal Cytology as a Predictor of Anal Intraepithelial Neoplasia in HIV‐Positive Men and Women,” Diagnostic Cytopathology 41, no. 8 (2013): 697–702.
  10. A. Albuquerque, M. Sheaff, O. Stirrup, et al., “Performance of Anal Cytology Compared With High‐Resolution Anoscopy and Histology in Women With Lower Anogenital Tract Neoplasia,” Clinical Infectious Diseases 67, no. 8 (2018): 1262–1268.
  11. I. Girolami, L. Pantanowitz, S. Marletta, et al., “Diagnostic Concordance Between Whole Slide Imaging and Conventional Light Microscopy in Cytopathology: A Systematic Review,” Cancer Cytopathology 128, no. 1 (2020): 17–28.
  12. E. F. Crowell, C. Bazin, F. Saunier, et al., “CytoProcessor™: A New Cervical Cancer Screening System for Remote Diagnosis,” Acta Cytologica 63, no. 3 (2019): 215–223.
  13. H. Ikenberg, S. Lieder, A. Ahr, M. Wilhelm, C. Schon, and A. Xhaja, “Comparison of the Hologic Genius Digital Diagnostics System With the ThinPrep Imaging System—A Retrospective Assessment,” Cancer Cytopathology 131, no. 7 (2023): 424–432.
  14. R. L. Cantley, X. Jing, B. Smola, W. Hao, S. Harrington, and L. Pantanowitz, “Validation of AI‐Assisted ThinPrep Pat Test Screening Using the Genius™ Digital Diagnostics System,” Journal of Pathology Informatics 15 (2024): 100391.
  15. T. M. Darragh and J. M. Palefsky, “Anal Cytology,” in The Bethesda System for Reporting Cervical Cytology: Definitions, Criteria, and Explanatory Notes, 3rd ed., ed. R. Nayar and D. C. Wilbur (Springer, 2015), 263–285.
  16. R Core Team, R: A Language and Environment for Statistical Computing (R Foundation for Statistical Computing, 2022), https://www.R‐project.org/.
  17. J. R. Landis and G. G. Koch, “The Measurement of Observer Agreement for Categorical Data,” Biometrics 33, no. 1 (1977): 159–174.
  18. J. H. Scholefield, J. Johnson, A. Hitchcock, et al., “Guidelines for Anal Cytology—To Make Cytological Diagnosis and Follow Up Much More Reliable,” Cytopathology 9, no. 1 (1998): 15–22.
  19. A. Lytwyn, I. E. Salit, J. Raboud, et al., “Interobserver Agreement in the Interpretation of Anal Intraepithelial Lesion,” Cancer 103, no. 7 (2005): 1447–1456.
  20. T. M. Darragh, D. Tokugawa, P. E. Castle, et al., “Interrater Agreement of Anal Cytology,” Cancer Cytopathology 121, no. 2 (2013): 72–78.
  21. M. Benevolo, F. Rollo, A. Latini, et al., “Interobserver Agreement in the Interpretation of Anal Cytology,” Cancer Cytopathology 132, no. 7 (2024): 419–424.
  22. D. F. I. Kurtycz, P. N. Staats, D. J. Chute, et al., “Bethesda Interobserver Reproducibility Study‐2 (BIRST‐2): Bethesda System 2014,” Journal of the American Society of Cytopathology 6, no. 4 (2017): 131–144.
  23. O. Bongaerts, C. Clevers, M. Debets, et al., “Conventional Microscopical Versus Digital Whole‐Slide Imaging‐Based of Thin‐Layer Cervical Specimens: A Validation Study,” Journal of Pathology Informatics 9 (2018): 29.

MeSH Term

Humans
Female
Artificial Intelligence
Cytodiagnosis
Microscopy
Adult
Middle Aged
Anal Canal
Aged
Uterine Cervical Neoplasms
Anus Neoplasms
Journal Article Comparative Study

Word Cloud

Created with Highcharts 10.0.0casesCCcytologyDC/AIdetectedLBCanalsystemdigitalDCartificialintelligencelesionsimagesCytologycomparedapproachessimilarnumberASC-US+respectivelymoderateagreementκ = 0p < 0001ASC-HHSILhigherseverityINTRODUCTION:RecentstudiesshowncoupledAIalgorithmsvalidapproachdiagnosiscervico-vaginalusingliquid-basedevaluatedusemethodsspecimensMETHODS:series124slidespreviouslydiagnosedconventionalmicroscopyreviewedgeneratedgalleryDiagnosesbasedselectedaccording2014BethesdaSystemReportingCervicalRESULTS:Overallabnormal6362observedexactconcordance70579%correspondingtwo4148alsofoundpositivestratified'low-grade'ASC-USLSIL'high-grade'HSIL:923classifiedCONCLUSIONS:systemsDigitalCombinedArtificialIntelligenceComparedConventionalMicroscopyAnalCytology:PreliminaryStudy

Similar Articles

Cited By