Table 2.

Class identification CNN_class performance.

	AlexNet			DenseNet			MobileNet			ResNet			ShuffleNet			SqueezeNet			VGG
	Precision	Recall	F1-score	Precision	Recall	F1-score	Precision	Recall	F1-score	Precision	Recall	F1-score	Precision	Recall	F1-score	Precision	Recall	F1-score	Precision	Recall	F1-score
2-chamber	0.998	0.993	0.996	0.998	1.000	0.999	0.997	1.000	0.998	0.998	1.000	0.999	0.993	1.000	0.997	0.986	0.991	0.989	0.993	1.000	0.997
3-chamber	0.991	0.953	0.972	1.000	1.000	1.000	1.000	0.996	0.998	0.996	0.996	0.996	1.000	0.983	0.991	0.987	0.979	0.983	0.987	0.987	0.987
4-chamber	1.000	0.990	0.995	1.000	0.998	0.999	0.990	0.995	0.992	0.998	0.995	0.997	0.997	1.000	0.998	0.987	0.992	0.989	0.993	0.997	0.995
Short axis	0.995	0.999	0.997	0.996	0.999	0.998	0.997	1.000	0.998	0.999	0.999	0.999	0.996	1.000	0.998	0.992	0.997	0.994	0.996	1.000	0.998
Other	0.973	0.985	0.979	0.998	0.990	0.994	0.996	0.984	0.990	0.994	0.995	0.994	0.996	0.984	0.990	0.984	0.969	0.976	0.995	0.978	0.986
Accuracy	0.992			0.998			0.996			0.998			0.996			0.989			0.994

Precision, recall, and F1 score for each CNN_class-determined class, and accuracy of each trained CNN_class.