Table 6 Performance indicators of EfficientNet classification
From: The value of deep neural networks in the pathological classification of thyroid tumors
Classification | Recall | Precision | NPV | Accuracy | Specificity | F1 | AUC | Kappa coefficient |
|---|---|---|---|---|---|---|---|---|
PTC | 93.39% | 91.13% | 93.28% | 92.18% | 90.98% | 92.24% | 0.977 | 0.7870 |
MTC | 76.19% | 69.57% | 97.73% | 95.06% | 96.85% | 72.73% | 0.981 | |
FTC | 53.33% | 72.73% | 96.98% | 95.88% | 98.68% | 61.54% | 0.972 | |
Adenoma | 63.64% | 73.68% | 96.43% | 94.65% | 97.74% | 68.29% | 0.950 | |
Adenomatous goiter | 50.00% | 66.67% | 97.44% | 96.30% | 98.70% | 57.14% | 0.906 | |
Normal thyroid | 98.08% | 89.47% | 99.46% | 97.12% | 96.86% | 93.58% | 0.994 |