Table 2.
Classification of images on patient level
| AI model versus Reader A | AI model versus Reader B | Reader B versus Reader A | |
|---|---|---|---|
| Correct classification of PET-CT image | 27 | 26 | 29 |
| True positive patient | 24 | 23 | 24 |
| True negative patient | 3 | 3 | 5 |
| False positive patient | 2 | 3 | 0 |
| False negative patient | 1 | 1 | 1 |
True positive, true negative, false positive and false negative classification of images on patient level when using manual segmentation or reference doctor as comparison. The results are presented for the entire test group (n = 30)