Artificial Intelligence in Cervical Cytology: Opportunities and Limitations in Screening, Triage, and Diagnostic Support

Cervical cancer remains a major global health challenge, particularly in low- and middle-income countries, where access to screening, vaccination, and timely treatment may be limited. Cervical cytology has played an important historical role in prevention, but it is labor-intensive, time-consuming, and subject to observer variability and limited sensitivity. In many contemporary screening programs, HPV testing is now used as the primary screening test, while cytology is used mainly for the triage of HPV-positive women. In recent years, artificial intelligence (AI), particularly deep learning (DL), has shown considerable potential in medical image analysis and computer-aided diagnosis. This review summarizes current applications of AI in cervical cytology and related diagnostic workflows, including automated and assisted slide screening, liquid-based cytology, the triage of equivocal or HPV-positive cases, and colposcopy support. Across these settings, AI-assisted systems may improve efficiency, standardization, and diagnostic consistency, and may reduce workload in resource-constrained environments. However, the evidence is heterogeneous, and important challenges remain, including the need for large and diverse datasets, prospective validation, regulatory approval, digital infrastructure, workflow integration, and the resolution of ethical and legal issues. AI should therefore be regarded as a promising adjunct to human expertise rather than a replacement in cervical cytology and related clinical diagnostic pathways.