Table 4.

Diagnostic performance of ADC-, IVIM- and DKI-derived parameters to detect RAS mutation.

	AUC	Sensitivity	Specificity	PPV	NPV	Accuracy	Cut-off
ADC Mean	0.61	0.52	0.76	0.45	0.81	0.70	1157.41
ADC STD	0.56	0.76	0.45	0.34	0.83	0.53	166.70
MK Mean	0.80	0.72	0.85	0.85	0.69	0.79	203.90
MK STD	0.27	0.06	1.00	1.00	0.46	0.48	3218.51
MD Mean	0.80	0.84	0.73	0.54	0.92	0.77	1694.30
MD STD	0.66	0.56	0.78	0.48	0.83	0.72	377.11
S0 Mean	0.45	0.32	0.78	0.35	0.75	0.65	117.10
S0 STD	0.59	0.48	0.76	0.43	0.80	0.68	19.60
FP Mean	0.77	0.84	0.73	0.54	0.92	0.75	148.30
FP STD	0.66	0.76	0.63	0.43	0.88	0.66	79.10
DT Mean	0.56	0.44	0.81	0.46	0.79	0.71	1100.62
DT STD	0.65	0.56	0.76	0.47	0.82	0.71	258.40
DP Mean	0.65	0.76	0.58	0.40	0.87	0.63	113.60
DP STD	0.60	0.68	0.58	0.38	0.83	0.61	69.30

Note. AUC = are under curve; PPV = positive predictive value; NPV = negative predictive value. In bold are reported the significant parameters in the detection of RAS mutation.