Fig. 2: ROC Curves for all kinds of PE detection on the RSPECT private dataset. | npj Digital Medicine

Fig. 2: ROC Curves for all kinds of PE detection on the RSPECT private dataset.

From: High performance with fewer labels using semi-weakly supervised learning for pulmonary embolism diagnosis

Fig. 2

Receiver operating characteristic (ROC) curves for models trained with varying proportions of labeled data (0 to 100%) are shown for a the RSPECT private dataset and b a pooled external validation dataset. The corresponding area under the curve (AUC) values are displayed in the legend for each panel.

Back to article page