Table 3.
Model performances of deep learning models for binary classification discriminating advanced colorectal adenocarcinoma.
Model | Sensitivity (%) | Specificity (%) | PPV (%) | NPV (%) | F1 score (%) | AUC (95% CI) |
---|---|---|---|---|---|---|
DenseNet-161 | 97.1 (96.5–97.8) | 99.8 (99.4–100.0) | 99.1 (97.6–100.0) | 99.1 (98.8–99.5) | 98.1 (97.3–98.9) | 0.995 (0.988–1.000) |
EfficientNet-B7 | 98.5 (97.2–99.8) | 99.8 (99.4–100.0) | 99.1 (97.6–100.0) | 99.6 (99.2–99.9) | 98.8 (97.5–100.0) | 0.998 (0.995–1.000) |
PPV positive predictive value, NPV negative predictive value, AUC area under the receiver operating characteristic curve, CI confidence interval.