Automated acquisition of explainable knowledge from unannotated colposcopic images for predicting the natural course of CIN2

Key Points

• This research aims to develop machine learning models that predict the prognosis of CIN2 using unannotated colposcopic images.
• Utilized machine learning algorithms to analyze colposcopic images
• Assessed various staining modalities for complementary information
• Evaluated the model's predictive accuracy for CIN2 progression
• Machine learning models effectively predict CIN2 prognosis
• Complementary information from staining modalities aids in risk assessment
• Models balance progression risk reduction with overtreatment avoidance