EUVIMEDEUVIMED entdecken
Systematische ÜbersichtOpen Access · CC BY-NC 4.0

Artificial intelligence in nongynecologic cytology: A systematic review of current research and commercial tools

Tsandmaa Byambadorj iD, Mohammad Rizwan Alam, Yosep Chong

Cancer Cytopathology · 2026-04 · 134 (4)

DOI: 10.1002/cncy.70092 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift Cancer Cytopathology, online erschienen am 20.03.2026. Verfasst von Tsandmaa Byambadorj und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Artificial Intelligence, Cytodiagnosis. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Research Foundation of Korea.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Nongynecologic (non‐GYN) cytology plays an important role in cellular and molecular cancer diagnosis, although its use is limited by variability and interobserver discrepancies. Recent studies suggest that artificial intelligence (AI) may improve diagnostic consistency and performance.

Methods

This systematic review evaluated contemporary AI research in non‐GYN cytology and examined commercially available systems. MEDLINE, Embase, and the Cochrane Library were searched for English‐language studies published from January 2010 to September 2024. Of ~24,000 records screened, 71 met inclusion criteria. Commercial platforms (KFBIO, Landing Med, VitaDx/VisioCyt, AIxMED, and CellsVision) were assessed using publicly available regulatory documents, technical specifications, and vendor‐reported validation data.

Results

Many studies reported high internal diagnostic performance, often exceeding 90% accuracy. Patch‐level performance often reached ~94%, exceeding whole slide image‐level metrics. Reduced interobserver variability was frequently observed, with accuracies of 95.9% for senior and 94.4% for junior pathologists. Several studies documented shorter diagnostic time. Thyroid (37%) and urinary bladder (30%) cytology were most frequently studied. AI applications included categorization, segmentation, and atypia detection, with recent work exploring immunocytochemistry support, mutation‐associated pattern recognition, and indirect prediction of histologic features.

Conclusion

AI in non‐GYN cytology shows promise but remains limited by data set quality, weak external validation, and regulatory barriers. At present, AI tools function primarily as decision‐support systems. Advancing clinical adoption will require multicenter validation, standardized data sets, and careful integration with expert interpretation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceCytodiagnosisHumansObserver VariationIntelligent Systems

Stichwörter der Autor:innen

artificial intelligencecommercial AI toolsdeep learningnongynecologic cytologysystematic review

Autor:innen und Institutionen

  • Department of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea.

ORCID-Profile: Tsandmaa Byambadorj

Förderung

  • National Research Foundation of Korea

Zitieren

APA

Byambadorj, T., Alam, M. R., & Chong, Y. (2026). Artificial intelligence in nongynecologic cytology: A systematic review of current research and commercial tools. Cancer Cytopathology, 134(4). https://doi.org/10.1002/cncy.70092

Vancouver

Byambadorj T, Alam MR, Chong Y. Artificial intelligence in nongynecologic cytology: A systematic review of current research and commercial tools. Cancer Cytopathology. 2026;134(4). doi:10.1002/cncy.70092

BibTeX
@article{Byambadorj2026,
  author = {Byambadorj, Tsandmaa and Alam, Mohammad Rizwan and Chong, Yosep},
  title = {Artificial intelligence in nongynecologic cytology: A systematic review of current research and commercial tools},
  journal = {Cancer Cytopathology},
  year = {2026},
  volume = {134},
  number = {4},
  doi = {10.1002/cncy.70092}
}
Kostenlos starten →