Table 2.
Classification performance of the radiomics models in the validation cohort.
TN vs non-TN | HER2 vs non-HER2 | Luminal vs non-luminal | ||
---|---|---|---|---|
CC model | AUC | 0.819 | 0.520 | 0.659 |
Accuracy | 0.817 | 0.761 | 0.563 | |
Sensitivity | 0.750 | 0.222 | 0.440 | |
Specificity | 0.831 | 0.839 | 0.867 | |
MLO model | AUC | 0.791 | 0.645 | 0.627 |
Accuracy | 0.718 | 0.747 | 0.521 | |
Sensitivity | 0.917 | 0.111 | 0.480 | |
Specificity | 0.678 | 0.839 | 0.619 | |
CC + MLO model | AUC | 0.838 | 0.556 | 0.645 |
Accuracy | 0.803 | 0.704 | 0.507 | |
Sensitivity | 0.833 | 0.111 | 0.440 | |
Specificity | 0.797 | 0.790 | 0.667 |
TN triple-negative, AUC area under the receiver operating characteristic curve.