Table 2 The results obtained over two scenarios
Dataset | Testing | Accuracy (%) | Precision (%) | Recall (%) | F1-Score (%) |
|---|---|---|---|---|---|
LIDC-IDRI (10-Fold Cross-Validation) | Scenario 1 (Validation Average) | 92.56 | 90.12 | 95.87 | 92.77 |
LIDC-IDRI (20% Testing Set) | Scenario 1 (Independent Testing) | 93.3 | 91.36 | 95.71 | 93.48 |
LIDC-IDRI (100% Training) | Scenario 2 (Test on LUNA16) | 72.6 | 72.3 | 73.82 | 73.39 |
LIDC-IDRI (100% Training) | Scenario 2 (Test on LUNGx) | 71.23 | 67.56 | 73.52 | 70.42 |