Research Article

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.

MethodsSESPACCROC_AUCPR_AUC

SD-GAN0.78930.97990.96460.95940.8698
SG-GAN0.79390.98250.96510.97360.8829
RA-GAN0.81260.98340.96480.97670.8927
SAD-GAN0.85030.98500.96710.98390.9002