Table 3.
Classification with ADASYN samples.
| Method | ReliefF optimal features with ADASYN samples | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Breast image categories | True positive | True negative | False positive | False negative | Recall rate | Precision | F1-score (%) | Misclassification rate | Accuracy |
| BI-RADS 1 | 220 | 1546 | 0 | 1 | 99.5 | 100 | 99.8 | 0.1 | 99.9 |
| BI-RADS 2 | 220 | 1552 | 1 | 0 | 100 | 99.5 | 99.8 | 0.1 | 99.9 |
| BI-RADS 3 | 214 | 1557 | 0 | 2 | 99.1 | 100 | 99.5 | 0.1 | 99.9 |
| BI-RADS 4A | 222 | 1549 | 0 | 0 | 100 | 100 | 100 | 0 | 100 |
| BI-RADS 4B | 215 | 1557 | 0 | 1 | 99.5 | 100 | 99.8 | 0.1 | 99.9 |
| BI-RADS 4C | 228 | 1317 | 2 | 0 | 100 | 99.1 | 99.6 | 0.1 | 99.9 |
| BI-RADS 5 | 226 | 1539 | 3 | 5 | 97.8 | 98.7 | 98.3 | 0.5 | 99.5 |
| BI-RADS 6 | 219 | 1551 | 3 | 0 | 100 | 98.6 | 99.3 | 0.2 | 99.8 |