Bivariate copula modeling reveals that higher radiologist-AI correlation for diseased cases boosts AUC of rule-out ROC curves, with opposite effects for rule-in, consistent with mammography data.
Multi-million Mammography Image Dataset and Population-Based Screening Cohort for the Training and Evaluation of Deep Neural Networks—the Cohort of Screen-Aged Women (CSAW),
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A theory of ROC analysis of rule-out and rule-in diagnostics with applications to mammography data
Bivariate copula modeling reveals that higher radiologist-AI correlation for diseased cases boosts AUC of rule-out ROC curves, with opposite effects for rule-in, consistent with mammography data.