Skip to main content

Table 3 Accuracy, AUC, precision*, sensitivity*, and specificity* from all images (i.e. using a 5-fold cross-validation) in both networks, SW-net and U-net

From: Fully convolutional architecture vs sliding-window CNN for corneal endothelium cell segmentation

 

Acc

AUC

PRE*

SEN*

SPE*

SW-net

95.48

0.9921

0.9585

0.9906

0.9914

U-net

97.33

0.9938

0.9855

0.9892

0.9971