Figure 4 | Scientific Reports

Figure 4

From: Stable and discriminating features are predictive of cancer presence and Gleason grade in radical prostatectomy specimens: a multi-site study

Figure 4

(a) PI-AUC plot for 242 features for 157 studies across four sites for Gleason 3 vs. Gleason 4 classification. Each feature is represented by a dot, color coded according to feature family. On the X-axis is the PI value for each feature in the non-cancerous regions of the four sites. On the Y-axis is the feature’s AUC averaged across 100 iterations of 3-fold cross validation across all patients from all four sites. Shown are 242 features from the global graph (blue), shape (red), disorder (green), sub-graph (yellow), and Haralick (purple) feature families. The optimal high-AUC, low-PI space comprises shape and sub-graph features while the low-AUC, high-PI space comprises chiefly Haralick and global graph features (b) ROIs corresponding to features occupying different regions in the PI-AUC space, see Table 4.

Back to article page