EJNMMI Research

Table 6 Mann Whitney U pairwise comparisons between image sets

From: Post-reconstruction enhancement of [¹⁸F]FDG PET images with a convolutional neural network

Pairwise comparisons	p values
Pairwise comparisons	Reader 1 noise	Reader 1 contrast	Reader 2 noise	Reader 2 contrast	Reader 3 noise	Reader 1 contrast
4 min–1.5 min	< 0.001	< 0.001	< 0.001	< 0.001	< 0.001	< 0.001
4 min–1.5 min CNN	0.002	0.728	0.184	0.368	0.080	0.161
4 min–1 min	< 0.001	< 0.001	< 0.001	< 0.001	< 0.001	< 0.001
4 min–1 min CNN	0.015	0.031	0.716	0.009	0.706	0.005
1.5 min–1.5 min CNN	< 0.001	< 0.001	< 0.001	< 0.001	< 0.001	0.001
1.5 min–1 min	< 0.001	< 0.001	< 0.001	0.004	< 0.001	0.015
1.5 min–1 min CNN	0.009	< 0.001	< 0.001	0.013	< 0.001	0.009
1.5 min CNN–1 min	< 0.001	< 0.001	< 0.001	< 0.001	< 0.001	< 0.001
1.5 min CNN–1 min CNN	< 0.001	0.006	0.114	0.078	0.65	0.192
1 min–1 min CNN	< 0.001	< 0.001	< 0.001	< 0.001	< 0.001	< 0.001

Significant p value is < 0.005 after Bonferroni correction

Back to article page