Table 2.

Classification metrics for the test set. In bold, the best result among all models for each metric is marked.

	Precision	Sensitivity	Specificity	F1-Score	Accuracy
Clinical	0.87	0.69	0.44	0.77	0.65
Tumor Volume	0.89	0.74	0.52	0.81	0.70
Clinical-Volume-Combined	0.89	0.54	0.64	0.67	0.56
DL-T1FsGd	0.89	0.91	0.40	0.90	0.83
DL-T2Fs	0.92	0.62	0.72	0.74	0.64