Table 2.

Classification performances achieved on the training and test set of the hold-out validation scheme by the radiomic-based model trained using the slices selected by our radiologist.

	Training test (30 pz.)	Test set (8 pz.)
Number of selected features	7	7
AUC (%)	78.50 (68.50–82.50)	86.67
Accuracy (%)	80.00 (76.67–86.67)	87.50
Sensitivity (%)	87.50 (80.00–95.00)	80.00
Specificity (%)	75.00 (70.00–80.00)	100

The median value and the interquartile range (1st and 3rd quantile) of AUC, accuracy, sensitivity, and specificity are reported in percentage values.