Skip to main content

Table 3 Diagnostic performance of the VGGNet-16 model and gynecologists in the two-category classification task

From: Deep learning model for classifying endometrial lesions

Classifier Sensitivity (%) Specificity (%) Precision (%) F1-score (%) AUC Accuracy (%)
VGGNet-16 83.0 96.0 93.3 87.8 0.944 90.8
Gynecologist 1 84.0 88.7 83.2 83.6 0.863 86.8
Gynecologist 2 76.0 86.7 79.2 77.6 0.813 82.4
Gynecologist 3 81.0 87.3 81.0 81.0 0.842 84.8
  1. AUC area under the receiver operating characteristic (ROC) curve