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

Table 1

Segmentation model on the data set ablation analysis results.

Model	Dice	Iou	Acc	Spec	Sens
BaseL	0.8338	0.7150	0.9913	0.9921	0.9615
BaseL + MS	0.8439	0.7300	0.9912	0.9922	0.9654
BaseL + PAM	0.8345	0.7160	0.9893	0.9825	0.9798
MSPAMUNet	0.8544	0.7457	0.9960	0.9927	0.9607

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