Research Article

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

Table 2

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

MethodsSESPACCROC_AUCPR_AUC

SD-GAN0.77820.98110.95420.95850.8322
SG-GAN0.78120.97790.95530.97110.8694
RA-GAN0.82760.98020.95480.97370.9003
SAD-GAN0.84220.98250.95670.98130.8928