Table 2 Diagnostic performance of the VGGNet-16 model and gynecologists in the five-category classification task
From: Deep learning model for classifying endometrial lesions
Category | Sensitivity (%) | Specificity (%) | Precision (%) | F1-score (%) | AUC | Accuracy (%) |
|---|---|---|---|---|---|---|
VGGNet-16 | ||||||
EH | 84.0 | 92.5 | 73.7 | 78.5 | 0.926 | 80.8 |
AH | 68.0 | 95.5 | 79.1 | 73.1 | 0.916 | |
EC | 78.0 | 96.5 | 84.8 | 81.3 | 0.952 | |
EP | 94.0 | 95.0 | 82.5 | 87.9 | 0.981 | |
SM | 80.0 | 96.5 | 85.1 | 82.5 | 0.959 | |
Gynecologist 1 | ||||||
EH | 70.0 | 90.0 | 63.6 | 66.7 | 0.800 | 72.8 |
AH | 58.0 | 92.5 | 65.9 | 61.7 | 0.753 | |
EC | 74.0 | 90.0 | 64.9 | 69.2 | 0.820 | |
EP | 86.0 | 95.0 | 81.1 | 83.5 | 0.905 | |
SM | 76.0 | 98.5 | 92.7 | 83.5 | 0.873 | |
Gynecologist 2 | ||||||
EH | 64.0 | 94.5 | 74.4 | 68.8 | 0.792 | 69.2 |
AH | 54.0 | 90.0 | 57.4 | 55.7 | 0.720 | |
EC | 68.0 | 92.5 | 69.4 | 68.7 | 0.803 | |
EP | 90.0 | 87.0 | 63.4 | 74.4 | 0.885 | |
SM | 70.0 | 97.5 | 87.5 | 77.8 | 0.838 | |
Gynecologist 3 | ||||||
EH | 52.0 | 95.0 | 72.2 | 60.5 | 0.735 | 64.4 |
AH | 54.0 | 87.0 | 50.9 | 52.4 | 0.705 | |
EC | 66.0 | 93.0 | 70.2 | 68.0 | 0.795 | |
EP | 80.0 | 87.0 | 60.6 | 69.0 | 0.835 | |
SM | 70.0 | 93.5 | 72.9 | 71.4 | 0.818 | |