Dual-Path Attention Compensation U-Net for Stroke Lesion Segmentation

Table 4

The segmentation performance of the DPAC-UNet using different hyperparameter configurations.

Loss functions	Weights		Metrics (%)
			FPR^∗	DSC	F2	PRE	RE	FPR
Tolerance loss,	1.		0.438	54.8	54.1	63.6	55.1	0.111
	2.		0.508	53.0	52.4	61.5	53.3	0.101
	3.		0.573	55.2	54.7	64.4	55.7	0.120
	4.		0.607	54.1	54	62.2	55.1	0.117
	5.		0.689	55.9	56.6	63	57.4	0.124
	6.		0.743	55.3	56	61.1	58.1	0.173
	7.		0.898	53.8	54.1	62.8	55.7	0.142
	8.		1.091	54.9	55.4	61.2	56.9	0.140
	9.		1.27	55.5	55.6	63.7	57	0.126
	10.		1.335	55.8	55.8	64.8	57.2	0.133
	11.		1.888	53.6	53	64.4	53.9	0.111
	12.		2.006	56.9	57.7	61.6	59.6	0.149
	13.		2.143	56.7	57.3	61.9	59.1	0.157
	14.		2.744	56.7	56	65.8	56.8	0.103
	15.		4.093	59.3	59.8	65.6	59.9	0.106
	16.		4.44	58.2	58.6	62.6	60.3	0.151
	17.		4.57	57.5	57.5	64	58.8	0.137
	18.		4.99	56.5	56.9	62.5	61.6	0.153
	19.		5.634	56.2	57.5	63	59.3	0.132
	20.		18.97	52.8	51.5	65.9	52.1	0.196