Research Article
A Selective Ensemble Classification Method Combining Mammography Images with Ultrasound Images for Breast Cancer Diagnosis
Table 7
The performance of the classifier-fusion method compared with the feature-fusion method.
| ā | Accuracy | Sensitivity | Specificity | NPV | PPV | AUC |
| Naive Bayes-feature-fusion | 69.01% | 80.65 | 60% | 80% | 60.98% | 0.6919 | SVM-feature -fusion | 76.06% | 64.52 | 85% | 75.56% | 76.92% | 0.7290 | KNN-feature -fusion | 67.61% | 61.29 | 72.50% | 70.73% | 63.33% | 0.6879 | The classifier- fusion method (C1) | 88.73% | 96.77% | 82.50% | 97.06% | 81.08% | 0.8968 |
|
|