Fig. 4: Performance of the MSI-H predictor on Gleason score and procedure type subgroups. | npj Precision Oncology

Fig. 4: Performance of the MSI-H predictor on Gleason score and procedure type subgroups.

From: Development and validation of a deep learning-based microsatellite instability predictor from prostate cancer whole-slide images

Fig. 4

Receiver operating characteristic (ROC) curves (a, b) and violin plots (c, d) of prediction scores for Gleason score (a, c) and procedure type (b, d) clinical subgroups in the pooled validation set that combines the internal scans of the paired validation set and the temporal validation set. The shared areas represent the 95% confidence intervals of the ROC curves. P-value annotation legend: ns: p ≤ 1, *: 0.01 < p ≤ 0.05, **: 0.001 < p ≤ 0.01, ***: 0.0001 < p ≤ 0.001, ****: p ≤ 0.0001.

Back to article page