Skip to main content


Fig. 5 | Breast Cancer Research

Fig. 5

From: A whole slide image-based machine learning approach to predict ductal carcinoma in situ (DCIS) recurrence risk

Fig. 5

Univariate and multivariate analysis of the eight-feature DCIS recurrence risk prediction model on the training cohort. a Fivefold cross-validated Kaplan-Meier curves of the training cohort. Significance is measured using the log-rank test, and the gray line represents the unstratified full cohort. b Univariate and multivariate Cox regression analysis comparing the influence of common clinicopathological variables alongside the eight-feature recurrence risk prediction model for recurrence-free survival, on the training set (after fivefold cross-validation)

Back to article page