Table 2.

Validation between data sets

Feature Extraction	Data set	AUC		Sensitivity (%)	Specificity (%)		Mf
		AVG	STD		AVG	STD
IR & HE	Train	0.994	0.0006	90	98.30	0.68	13
				95	96.58	1.10
				99	91.55	2.55
	Test	0.956	0.0089	90	88.57	5.96
				95	81.92	5.28
				99	26.86	15.50
HE only	Train	0.986	0.0021	90	97.77	0.97	10
				95	91.56	2.49
				99	79.29	4.47
	Test	0.918	0.0100	90	65.51	8.37
				95	46.14	7.53
				99	13.29	6.94

A classifier is trained on Data1 and tested on Data2. AVG and STD denote the average and standard deviation. M_f is the median size of the optimal feature set. Column "Feature Extraction" indicates if features were obtained using H&E as well as IR data, or with H&E data alone. Column "Data set" indicates if the performance metrics are from training data (Data1) or from test data (Data2). The parameter γ of a radial basis kernel for SVM is set to 1.