Classification of Computed Tomography Images in Different Slice Positions Using Deep Learning

Table 3

Accuracy and loss of validation for training models.

	CNN architecture	Dataset
		0.1K	0.5K	1K	2K	3K	4K	5K	6K	7K	8K	9K	10K
Accuracy of validation	AlexNet	0.27	0.77	0.87	0.92	0.93	0.95	0.95	0.96	0.97	0.97	0.97	0.97
	GoogLeNet	0.40	0.78	0.93	0.96	0.96	0.97	0.98	0.97	0.97	0.98	0.98	0.98
Loss of validation	AlexNet	2.00	0.57	0.36	0.21	0.21	0.15	0.14	0.12	0.11	0.11	0.10	0.09
	GoogLeNet	1.59	0.55	0.24	0.12	0.12	0.10	0.09	0.10	0.09	0.08	0.08	0.07
Time for training (min)	AlexNet	0.8	2.1	3.8	7.3	10.7	14.2	17.4	21.3	24.7	27.9	31.8	34.8
	GoogLeNet	1.1	4.9	9.5	18.7	28.9	38.5	48.3	45.7	67.6	76.5	86.4	95.0