Table 6.

Pattern recognition analysis with significant features.

The Best Classifier (KNN) Results with Significant Features Extracted by	Dataset	AUC	Accuracy	Sensitivity	Specificity	Training Time [s]	Model Type and Parameters
T2W SPACE	Training set	0.90	0.89	0.84	0.92	11.1	Decision Fine Tree; Maximum number of splits: 100; split criterion: Gini’s diversity index; optimizer options: Hyperparameter options disabled
	Validation set	0.88	0.86	0.86	0.86
arterial phase	Training set	0.97	0.91	0.91	0.91	2.34	Weighted KNN; number of neighbors: 10; distance metric: Euclidean; distance weight: squared inverse
	Validation set	0.96	0.89	0.85	0.91
portal phase	Training set	0.97	0.92	0.84	0.97	9.74
	Validation set	0.99	0.91	0.81	0.96
EOB-phase	Training set	0.96	0.90	0.91	0.89	13.4
	Validation set	0.95	0.80	0.67	1.00