Skip to main content

Table 3 Performance metrics for the Faster R-CNN model, assessed on single filed images selected from the test dataset

From: Automatic model for cervical cancer screening based on convolutional neural network: a retrospective, multicohort, multicenter study

  ASCUS LISL HSIL
True-positive 541 422 576
False-negative 65 168 193
Total 606 590 779
Sensitivity 89.3% 71.5% 73.9%