Prediction of COVID-19 with Computed Tomography Images using Hybrid Learning Techniques

Table 8

Confusion matrix and classification report for various deep learning classifiers.

Confusion matrix						Classification report
Models	Category	COVID-19	CAP	Normal	Total	Category	Precision	Recall	F1Score	Specificity
CNN	COVID-19	100	5	6	111	COVID-19	0.90	0.90	0.90	0.95
	CAP	5	101	4	111	CAP	0.91	0.89	0.89	0.95
	Normal	5	7	99	111	Normal	0.89	0.90	0.89	0.95
	Total	111	113	109	333	Average	0.90	0.90	0.90	0.95
AlexNet	COVID-19	105	3	3	111	COVID-19	0.94	0.94	0.94	0.97
	CAP	2	106	3	111	CAP	0.95	0.95	0.95	0.97
	Normal	4	2	104	111	Normal	0.93	0.93	0.93	0.97
	Total	111	111	111	333	Average	0.94	0.94	0.94	0.97
VGG-16	COVID-19	104	4	3	111	COVID-19	0.93	0.93	0.93	0.96
	CAP	3	104	4	111	CAP	0.93	0.93	0.93	0.95
	Normal	4	3	104	111	Normal	0.93	0.93	0.93	0.96
	Total	111	111	111	333	Average	0.93	0.93	0.93	0.96
Resnet50	COVID-19	102	6	3	111	COVID-19	0.92	0.93	0.92	0.96
	CAP	5	101	5	111	CAP	0.91	0.90	0.90	0.95
	Normal	3	6	102	111	Normal	0.92	0.93	0.92	0.96
	Total	110	113	110	333	Average	0.92	0.92	0.92	0.96
Inception v3	COVID-19	100	4	7	111	COVID-19	0.90	0.89	0.89	0.94
	CAP	6	100	5	111	CAP	0.90	0.91	0.90	0.95
	Normal	6	6	99	111	Normal	0.89	0.89	0.89	0.95
	Total	112	110	111	333	Average	0.90	0.90	0.90	0.95