Table 3 Performance of the trained neural network in the validation set and in the set with scans from a different vendor (ROC analysis; AUC: Area-under-the-curve, Criterion: associated criterion) with consensus from two experienced radiologists as standard of reference
From: Improving workflow in prostate MRI: AI-based decision-making on biparametric or multiparametric MRI
AUC (95% CI) | Criterion | Sensitivity (%) | Specificity (%) | |
|---|---|---|---|---|
AI validation set | 0.881 (0.801–0.937) | > 0.221 | 94.4 | 68.8 |
AI different vendor set | 0.726 (0.537–0.870) | > 0.171 | 100.0 | 42.1 |