Skip to main content

Table 3 Comparison of nuclear segmentation between the fused ENet with UNet, fused UNet, and multitask learning

From: Fusion of encoder-decoder deep networks improves delineation of multiple nuclear phenotypes

Input size Recall Precision F1-Score Standard Error
UNet 0.86 0.81 0.83 1.2786e-06
Fused-UNet 0.89 0.86 0.87 1.1921e-06
Multi-task UNet 0.87 0.77 0.81 1.3117e-06
ENet 0.83 0.88 0.84 1.1412e-06
Fused-ENet 0.94 0.88 0.91 1.1124e-06
Multi-task ENet 0.89 0.83 0.86 1.2690e-06
  1. The italic items illustrate the best results