Table 2 Comparison of the performance for each method
Sensitivity | Specificity | Accuracy | Time cost (s) | |
|---|---|---|---|---|
Dual-input | 1:000 (0:832; 1:000) | 0.450 (0.231, 0.685) | 0.725 (0.561, 0.854) | 0:0366 ± 0:0001 |
Dual-input + RAGS | 0.960 (0.751, 0.999) | 0:910 (0:683; 0:988) | 0:935 (0:796; 0:984) | 0:0569 ± 0:0013 |
Rahmany et al. [15] | 0.950 (0.751, 0.999) | 0.300 (0.119, 0.543) | 0.625 (0.458, 0.773) | 62:5460 ± 23:222 |
YOLOv3 [22] | 0.850 (0.621, 0.968) | 0.700 (0.457, 0.881) | 0.775 (0.616, 0.892) | 0:0232 ± 0:0005 |
RetinaNet [31] | 1:000 (0:832; 1:000) | 0.420 (0.191, 0.639) | 0.710 (0.535, 0.834) | 0:0456 ± 0:0036 |
Physician | 0.900 (0.683, 0.988) | 0.900 (0.683, 0.988) | 0.900 (0.763, 0.972) | – |