Two-Stage Hybrid Approach of Deep Learning Networks for Interstitial Lung Disease Classification

Table 2

Comparative performance assessment of average DSC and for c-GAN and existing methods for lung segmentation.

Disease	Performance	Present study	NMF [34]	UNet [35]	ResNet [31]	VGG16 [10]	MobileNet [36]
Fibrosis	DSC	0.9566	0.7681	0.9485	0.9126	0.9295	0.9040
		0.9290	0.6600	0.9117	0.8681	0.8742	0.8330
Ground glass	DSC	0.9558	0.8335	0.9534	0.9351	0.9444	0.9291
		0.9282	0.7473	0.9191	0.8987	0.8975	0.8706
Emphysema	DSC	0.9378	0.9214	0.9629	0.9261	0.9452	0.9380
		0.9204	0.8917	0.9340	0.8975	0.8963	0.8841
Consolidation	DSC	0.9712	0.8775	0.9500	0.9440	0.9479	0.9436
		0.9466	0.7963	0.9148	0.9076	0.9031	0.8954
Micronodule	DSC	0.9812	0.9678	0.9807	0.9674	0.9751	0.9586
		0.9645	0.9391	0.9627	0.9379	0.9523	0.9210