Image Segmentation of Triple-Negative Breast Cancer by Incorporating Multiscale and Parallel Attention Mechanisms

Table 2

Results of the comparative analysis of the different models on the dataset.

Model	Dice	Iou	Acc	Spec	Sens
UNet	0.8334	0.7144	0.9888	0.9897	0.9780
Att-UNet	0.8390	0.7227	0.9898	0.9902	0.9848
ResUNet	0.8423	0.7276	0.9912	0.9926	0.9531
SegNet	0.7579	0.6102	0.9852	0.9854	0.9842
MSPAMUNet	0.8544	0.7457	0.9960	0.9927	0.9607

Note: Bolded font is the optimal value for each line.