Skip to main content

Table 7 P-values obtained from the post-hoc Nemenyi test after facility-specific training for all possible pairwise model comparisons. Significant results (p < 0.05) are denoted with an asterisk

From: Comparison of deep learning networks for fully automated head and neck tumor delineation on multi-centric PET/CT images

Comparison

DSC

HDavg

HD95

Model 1

Model 2

p-value

Regular Unet

2D Retina Unet

0.04*

0.9

0.09

Regular Unet

3D Retina Unet

0.03*

1e-3*

1e-3*

2D Retina Unet

3D Retina Unet

1e-3*

1e-3*

0.06