Table 3.

Sensitivity, Specificity, and Accuracy of the CNN Model After Normalization

		False-	False-
		Positive	Negative		Recall
Image Category	Class	Rate	Rate	Precision	(Sensitivity)	F1 Score	Accuracy
Four-map selectable display	K	0	0.05	1.00	0.95	0.98	0.98
	N	0.01	0	0.99	1.00	0.99	0.99
	S	0.04	0	0.96	1.00	0.98	0.98
Front elevation map	K	0.04	0.08	0.96	0.92	0.94	0.94
	N	0	0	1.00	1.00	1.00	1.00
	S	0.08	0.04	0.92	0.96	0.94	0.94
Back elevation map	K	0.03	0.04	0.97	0.96	0.96	0.97
	N	0.03	0.02	0.97	0.98	0.98	0.98
	S	0.04	0.04	0.96	0.96	0.96	0.96
Pachymetry map	K	0	0	1.00	1.00	1.00	1.00
	N	0.01	0.01	0.99	0.99	0.99	0.99
	S	0.01	0.01	0.99	0.99	0.99	0.99
Front sagittal curvature map	K	0.01	0.02	0.99	0.98	0.99	0.99
	N	0.03	0.0	0.97	1.00	0.99	0.98
	S	0.02	0.04	0.98	0.96	0.97	0.97

The results show the average of 10 training/validation trials with random seeds.