AI in cytology: where digital meets diagnostic

Though abstracts are beginning to show platforms demonstrating real-time feedback to cytopathologists and proceduralists, challenges remain, including limited annotated data, variation in sample preparation, and the need for seamless integration with existing microscopes and digital platforms. Ongoing studies aim to create portable, AI-powered ROSE tools that could bring expert-level cytologic evaluation to remote or underserved settings.

Implementation and validation: recommended guidelines. Digital cytology implementation is a stepwise process. According to the recommendations of the American Society of Cytopathology, success depends on systematic platform evaluation, validation, and ongoing quality assurance.^{10, 11}

• System selection requires input from cytotechnologists, cytopathologists, IT staff, and administrators. Key steps include evaluating vendor platforms, performing pilot testing, and aligning the digital system with laboratory workflow and data storage needs.
• Validation must confirm that digital diagnoses are equivalent to glass slides. The CAP and the ASC recommend at least 60 test cases with 95 percent concordance across stains and preparations. Any major hardware or software change requires repeat validation.
• Quality assurance and maintenance are continuous. Routine checks on scanner performance, image quality, and user competency ensure reliability and regulatory compliance.

Although AI integration remains limited, most systems are currently used as screening aids rather than primary diagnostic tools. Their success hinges on transparent validation, clear performance metrics, and defined regulatory pathways.⁷

1. Wilbur DC, Black-Schaffer WS, Luff RD, et al. The Becton Dickinson FocalPoint GS Imaging System: clinical trials demonstrate significantly improved sensitivity for the detection of important cervical lesions. Am J Clin Pathol. 2009;132(5):767–775.
2. Bai X, Wei J, Starr D, et al. Assessment of efficacy and accuracy of cervical cytology screening with artificial intelligence assistive system. Mod Pathol. 2024;37(6):100486.
3. Doxtader EE, Ooms K, Brainard JA, et al. Papanicolaou test interpretation utilizing the Hologic Genius Digital Diagnostics System vs manual glass slide review: a retrospective study of 596 cases. Am J Clin Pathol. 2025;164(3):513–521.
4. Vaickus LJ, Suriawinata AA, Wei JW, Liu X. Automating the Paris System for urine cytopathology—a hybrid deep-learning and morphometric approach. Cancer Cytopathol. 2019;127(2):98–115.
5. Ou YC, Tsao TY, Chang MC, et al. Evaluation of an artificial intelligence algorithm for assisting the Paris System in reporting urinary cytology: a pilot study. Cancer Cytopathol. 2022;130(11):872–880.
6. Liu TJ, Yang WC, Huang SM, et al. Evaluating artificial intelligence–enhanced digital urine cytology for bladder cancer diagnosis. Cancer Cytopathol. 2024;132(11):686–695.
7. VandeHaar MA, Al-Asi H, Doganay F, et al. Challenges and opportunities in cytopathology artificial intelligence. Bioengineering (Basel). 2025;12(2):176.
8. Saieg M, Lago PP, Pusztaszeri MP. Generative artificial intelligence as an aid in interpreting thyroid FNA cytopathological images: are we there yet? Cancer Cytopathol. 2026;134(1):e70069.
9. Yan S, Li Y, Pan L, Jiang H, Gong L, Jin F. The application of artificial intelligence for Rapid On-Site Evaluation during flexible bronchoscopy. Front Oncol. 2024;14:1360831.
10. Kim D, Thrall MJ, Michelow P, et al. The current state of digital cytology and artificial intelligence (AI): global survey results from the American Society of Cytopathology Digital Cytology Task Force. J Am Soc Cytopathol. 2024;13(5):319–328.
11. Kim D, Sundling KE, Virk R, et al. Digital cytology part 2: artificial intelligence in cytology: a concept paper with review and recommendations from the American Society of Cytopathology Digital Cytology Task Force. J Am Soc Cytopathol. 2024;13(2):97–110.

Dr. Enbom is a senior gynecological and breast pathologist and cytopathologist at Quest Diagnostics, West Hills, Calif. Dr. Liu is associate professor of pathology and director of cytopathology, Dartmouth Hitchcock Medical Center, Lebanon, NH. Drs. Enbom and Liu are members of the CAP Cytopathology Committee.