Table 3.

Performance metrics from each of the Logistic Regression and Random Forest classifier models, where low grade tumours have Gleason Score <  = 3 + 4 / Grade Group <  = 2 and high grade tumours have Gleason Score >  = 4 + 3 / Grade Group >  = 3. The best performing metrics when comparing the two classifiers are in bold. Ktrans and Ve were computed using the Parker AIF

MRI Parameters	Logistic Regression Models			Random Forest Models
Low Grade Tumours	Sensitivity	Specificity	Accuracy (%)	Sensitivity	Specificity	Accuracy (%)
T2w + ADC	0.21	0.89	60	0.40	0.70	58
T2w + ADC + Ktrans	0.25	0.88	63	0.44	0.77	63
T2w + ADC + Ktrans + Ve	0.38	0.84	65	0.57	0.81	71
T2w + ADC + TTP + IRE + AUC	0.48	0.79	66	0.63	0.83	74
T2w + ADC + Ktrans + Ve + TTP + AUC	0.47	0.79	66	0.68	0.86	78
High Grade Tumours	Sensitivity	Specificity	Accuracy (%)	Sensitivity	Specificity	Accuracy (%)
T2w + ADC	0.65	0.81	74	0.63	0.79	72
T2w + ADC + Ktrans	0.64	0.82	75	0.68	0.84	77
T2w + ADC + Ktrans + Ve	0.65	0.83	75	0.72	0.86	80
T2w + ADC + TTP + IRE + AUC	0.65	0.82	75	0.76	0.87	82
T2w + ADC + Ktrans + Ve + TTP + AUC	0.65	0.83	76	0.79	0.89	85
All Tumours	Sensitivity	Specificity	Accuracy (%)	Sensitivity	Specificity	Accuracy (%)
T2w + ADC	0.56	0.74	66	0.54	0.69	62
T2w + ADC + Ktrans	0.56	0.76	66	0.57	0.77	68
T2w + ADC + Ktrans + Ve	0.60	0.75	68	0.64	0.79	72
T2w + ADC + TTP + IRE + AUC	0.62	0.74	69	0.68	0.81	75
T2w + ADC + Ktrans + Ve + TTP + AUC	0.61	0.75	68	0.72	0.84	80