Table 13 HyperFusion-Net’s Statistical Significance (p-values) in Relation to State-of-the-Art Models (ISIC-2018).

From: HyperFusionNet combines vision transformer for early melanoma detection and precise lesion segmentation

Compared Model

Dice difference

Jaccard difference

p-value (Dice)

p-value (Jaccard)

U-Net

 + 0.082

 + 0.091

p < 0.001

p < 0.001

Attention U-Net

 + 0.057

 + 0.066

p < 0.001

p < 0.001

DeepLabV3 + 

 + 0.062

 + 0.071

p < 0.001

p < 0.001

TransUNet

 + 0.042

 + 0.051

p = 0.004

p = 0.006

Swin-UNet

 + 0.027

 + 0.036

p = 0.018

p = 0.021

Back to article page