Generative Adversarial Network Combined with SE-ResNet and Dilated Inception Block for Segmenting Retinal Vessels

Table 3

The following table shows the segmentation results of different GAN models on CHASE_DB1 dataset in this paper.

Methods	SE	SP	ACC	ROC_AUC	PR_AUC
SD-GAN	0.7893	0.9799	0.9646	0.9594	0.8698
SG-GAN	0.7939	0.9825	0.9651	0.9736	0.8829
RA-GAN	0.8126	0.9834	0.9648	0.9767	0.8927
SAD-GAN	0.8503	0.9850	0.9671	0.9839	0.9002