Table 1. Experts’ discrimination performance on synthetic/real images.
TP represents the number of correctly identified synthetic images and TN represents the number of correctly identified real images.
| Pathologist 1 | Pathologist 2 | Pathologist 3 | Image Analyst 1 | Image Analyst 2 | Image Analyst 3 | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| TP | TN | TP+ TN | TP | TN | TP+ TN | TP | TN | TP+ TN | TP | TN | TN+ TP | TP | TN | TN+ TP | TP | TN | TN+ TP | |
| Dataset1 (10 synthetic) | 2 | 0 | 2 | 6 | 0 | 6 | 6 | 0 | 6 | 4 | 0 | 4 | 10 | 0 | 10 | 4 | 0 | 4 |
| Dataset2 (10 real) | 0 | 6 | 6 | 0 | 6 | 6 | 0 | 4 | 4 | 0 | 5 | 5 | 0 | 1 | 0 | 0 | 6 | 6 |
| Dataset3 (5 synthetic, 5 real) | 0 | 2 | 2 | 4 | 2 | 6 | 2 | 3 | 5 | 2 | 3 | 5 | 3 | 1 | 4 | 3 | 3 | 6 |
| Accuracy | 33.3% | 60.0% | 50.0% | 46.7% | 46.7% | 53.3% | ||||||||||||