VandeHaar, Meredith A.

Artificial Intelligence (AI) has the potential to revolutionize cytopathology by enhancing diagnostic accuracy, efficiency, and accessibility. However, the implementation of AI in this field presents significant challenges and opportunities. This review paper explores the current landscape of AI applications in cytopathology, highlighting the critical challenges, including data quality and availability, algorithm development, integration and standardization, and clinical validation. We discuss challenges such as the limitation of only one optical section and z-stack scanning, the complexities associated with acquiring high-quality labeled data, the intricacies of developing robust and generalizable AI models, and the difficulties in integrating AI tools into existing laboratory workflows. The review also identifies substantial opportunities that AI brings to cytopathology. These include the potential for improved diagnostic accuracy through enhanced detection capabilities and consistent, reproducible results, which can reduce observer variability. AI-driven automation of routine tasks can significantly increase efficiency, allowing cytopathologists to focus on more complex analyses. Furthermore, AI can serve as a valuable educational tool, augmenting the training of cytopathologists and facilitating global health initiatives by making high-quality diagnostics accessible in resource-limited settings. The review underscores the importance of addressing these challenges to harness the full potential of AI in cytopathology, ultimately improving patient care and outcomes.

Objective A follow-up of women 50 years or older with concomitant positive high-risk human papillomavirus (HPV) genotypes other than 16 and 18 (hrHPVO) and negative Pap test (NILMPap) was conducted to better understand the implications of hrHPVO positivity on potential risk of developing significant high-grade lesions. Material and Methods A retrospective review of 2014 cytology data of patients with co-testing (Pap test and HPV DNA) identified 85 women 50 years or older with NILMPap and hrHPVO+. Results Most patients (63) had repeat co-testing on next follow-up. Of these, 41 patients with persistent hrHPVO+ status, 3 developed cervical intraepithelial neoplasia 2 (CIN2), and 1 CIN3. Nineteen patients were followed with biopsies. Of these, 7 biopsies were abnormal, 5 of which showed low-grade (CIN1) and 2 high-grade (CIN3) histology; none progressed on further follow-up. Three patients were followed with Pap test only, all had NILMPap, and none progressed on further follow-up. In summary, of the 85 patients, 26 developed abnormal histology during follow-up, 6 of whom had high-grade histology (CIN2 and CIN3, 3 each). The 5-year risk of CIN1+ in this cohort was 43.8% and for CIN2+ was 12.3%. The risk of abnormal histology did not differ significantly by prior history of Pap tests, histology, and/or HPV results. Conclusions A persistent positivity for hrHPVO indicated higher likelihood to develop a lesion, and this risk was not reduced for patients 50 and older compared with the published screening population risk.