Research Article
A Benign and Malignant Breast Tumor Classification Method via Efficiently Combining Texture and Morphological Features on Ultrasound Images
Table 3
The classification results based on the methods of multiple features with single classifier.
| Features | Evaluation (%) | Classifier | SVM | LDA |
| LBP+ morphological | Accuracy | 80.00 | 76.67 | Sensitivity | 79.25 | 75.47 | Specificity | 81.08 | 78.38 |
| HOG+ morphological | Accuracy | 83.33 | 72.22 | Sensitivity | 81.13 | 71.70 | Specificity | 86.48 | 72.97 |
| GLCM+ morphological | Accuracy | 80.00 | 80.00 | Sensitivity | 69.81 | 81.13 | Specificity | 94.59 | 78.38 |
| LBP+HOG+GLCM+ morphological | Accuracy | 87.78 | 76.67 | Sensitivity | 88.68 | 75.47 | Specificity | 86.49 | 78.38 |
|
|