AI in Clinical Medicine, ISSN 2819-7437 online, Open Access
Article copyright, the authors; Journal compilation copyright, AI Clin Med and Elmer Press Inc
Journal website https://aicm.elmerpub.com

Review

Volume 2, March 2026, e16

Artificial Intelligence in Colposcopy: Diagnostic Performance, Clinical Applications, and Future Directions

Figures

↓  Figure 1. PRISMA flow diagram.
Figure 1.
↓  Figure 2. Artificial intelligence (AI)-assisted colposcopy workflow.
Figure 2.
↓  Figure 3. Multi-panel synthesis of diagnostic performance and functional roles of artificial intelligence (AI) in colposcopy. (a) Summary receiver operating characteristic (ROC) plot illustrating sensitivity and specificity trade-offs across representative studies evaluating AI-assisted detection of high-grade cervical lesions. Each point represents a study. (b) Flowchart illustrating major clinical task categories of AI in colposcopy, including detection, classification, triage, and clinical decision support.
Figure 3.

Table

↓  Table 1. Summary of Key Studies Evaluating Artificial Intelligence–Assisted Colposcopy
 
Study Year Study design Dataset AI method Target outcome Performance
AUC: area under the receiver operating characteristic curve; CNN: convolutional neural network.
Hu et al [5] 2019 Retrospective 9,406 images CNN CIN2+ vs. ≤ CIN1 Sensitivity 94.0%, specificity 88.0%, AUC 0.96
Song et al [6] 2020 Retrospective 7,531 images Deep CNN CIN2+ detection Sensitivity 91.3%, specificity 80.0%, AUC 0.93
Xue et al [7] 2020 Retrospective 6,763 images CNN + attention CIN2+ detection Sensitivity 98.0%, specificity 62.0%
Zhao et al [8] 2022 Retrospective 3,673 images CNN High-grade CIN Sensitivity 86.2%, specificity 78.6%
Liu et al [1] 2024 Meta-analysis 33 studies Multiple models CIN2+ detection Pooled sensitivity 93.0%, specificity 85.0%