Table 2.

Classification performance of the individual classifier for region (a), (b), (d), and (e) and the integrated using the selected feature set

Lung region	Training dataset				Test dataset
	AUC	Spe	Sen	Acc	AUC	Spe	Sen	Acc
(a)	0.986	0.832	0.894	0.852	0.879	0.753	0.844	0.786
(b)	0.997	0.996	0.737	0.910	0.939	0.934	0.738	0.866
(d)	0.953	0.811	0.724	0.782	0.835	0.762	0.623	0.711
(e)	0.994	0.971	0.800	0.913	0.889	0.880	0.697	0.817
Integrated	0.997	0.995	0.913	0.969	0.961	0.933	0.849	0.905

AUC = area under ROC curve; Spe = specificity; Sen = sensitivity; Acc = accuracy.

Lung regions (a) and (b) correspond to upper and middle lung field of the right lung, and region (d) and (e) correspond to upper and middle lung field of the left lung, respectively.