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.

Methods	SE	SP	ACC	ROC_AUC	PR_AUC
SD-GAN	0.7782	0.9811	0.9542	0.9585	0.8322
SG-GAN	0.7812	0.9779	0.9553	0.9711	0.8694
RA-GAN	0.8276	0.9802	0.9548	0.9737	0.9003
SAD-GAN	0.8422	0.9825	0.9567	0.9813	0.8928