Research Article
Automatic Recognition and Classification System of Thyroid Nodules in CT Images Based on CNN
Table 4
Classification performance results.
| Method | Accuracy | Recall | Precision | Specificity | F1-score | ROC |
| Unet (3) | 53.33 | 45.71 | 88.8 | 80.00 | 60.35 | 0.6394 | Unet + Vgg16 | 71.11 | 75.49 | 87.50 | 63.33 | 81.05 | 0.7413 | Unet + DenseNet | 79.26 | 83.81 | 88.89 | 63.33 | 86.28 | 0.7704 | Unet + CNN-1 | 80.74 | 86.67 | 88.35 | 60.00 | 86.51 | 0.7835 | Unet + CNN-2 | 82.22 | 84.76 | 91.75 | 73.33 | 88.12 | 0.7968 | Unet + CNN-F | 85.92 | 91.43 | 90.57 | 66.67 | 91.00 | 0.8253 |
|
|