Model | Cohort | AUC (95% CI) | Sensitivity | Specificity | Accuracy | Cutoff |
---|---|---|---|---|---|---|
U radiomics signature | Training | 0.857 (0.803–0.911) | 0.726 | 0.892 | 0.846 | − 0.640 |
Validation | 0.846 (0.777–0.915) | 0.821 | 0.733 | 0.763 | − 0.910 | |
External testing | 0.801 (0.664–0.939) | 0.722 | 0.769 | 0.750 | − 0.746 | |
A radiomics signature | Training | 0.849 (0.795–0.904) | 0.726 | 0.866 | 0.828 | − 0.730 |
Validation | 0.832 (0.758–0.907) | 0.821 | 0.773 | 0.789 | − 0.870 | |
External testing | 0.803 (0.661–0.946) | 0.722 | 0.846 | 0.795 | − 0.717 | |
V radiomics signature | Training | 0.856 (0.804–0.909) | 0.753 | 0.845 | 0.820 | − 0.889 |
Validation | 0.832 (0.758–0.905) | 0.795 | 0.773 | 0.781 | − 1.004 | |
External testing | 0.823 (0.697–0.948) | 0.778 | 0.769 | 0.773 | − 1.215 | |
T radiomics signature | Training | 0.862 (0.809–0.914) | 0.753 | 0.866 | 0.835 | − 0.794 |
Validation | 0.853 (0.785–0.921) | 0.872 | 0.733 | 0.781 | − 0.999 | |
External testing | 0.837 (0.714–0.959) | 0.765 | 0.852 | 0.818 | − 0.589 |