Table 8.

Average correct rates and SDs in classifying chest CT images as COVID-19 positive/negative when Resnet-101 and each algorithm hyperparameter combination in Table 6 were used in five independent experimental runs

Model# experiment number	Dataset	Experimental runs
		1	2	3	4	5	Average	SD
Resnet-101#1	Training set	0.7124	0.7059	0.7075	0.7042	0.7026	0.7065	0.00376
	Validation set	0.6061	0.596	0.6263	0.6162	0.6263	0.6142	0.01317
Resnet-101#2	Training set	0.7876	0.781	0.7876	0.7876	0.7892	0.7866	0.00321
	Validation set	0.6566	0.6566	0.6566	0.6566	0.6566	0.6566	0
Resnet-101#3	Training set	0.9804	0.9755	0.982	0.9853	0.982	0.9810	0.00357
	Validation set	0.8788	0.8788	0.8788	0.8788	0.8788	0.8788	0
Resnet-101#4	Training set	0.4951	0.5065	0.4951	0.4951	0.4951	0.4974	0.0051
	Validation set	0.5051	0.4848	0.5051	0.5051	0.5051	0.5010	0.00908
Resnet-101#5	Training set	0.9085	0.8987	0.9101	0.9101	0.9101	0.9075	0.00497
	Validation set	0.7879	0.7273	0.7879	0.798	0.798	0.7798	0.02979
Resnet-101#6	Training set	0.8366	0.8758	0.8317	0.835	0.835	0.8428	0.01852
	Validation set	0.7475	0.7677	0.7475	0.7475	0.7475	0.7515	0.00903
Resnet-101#7	Training set	0.9918	0.9869	0.9853	0.9804	0.9869	0.9863	0.00409
	Validation set	0.8687	0.899	0.8889	0.8586	0.899	0.8828	0.01835