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

Table 5

The results of SAD-GAN and other algorithms on CHASE_DB1 dataset.

Methods	Year	SE	SP	ACC	ROC_AUC	PR_AUC
Wu et al. [40]	2018	0.7538	0.9847	0.9637	0.9825	—
Wang et al. [41]	2019	0.8074	0.9821	0.9661	0.9812	—
Cheng et al. [42]	2019	0.8967	0.9540	0.9488	0.9785	—
Li et al. [44]	2020	0.7798	0.9822	0.9620	0.9791	0.8291
Lin et al. [21]	2021	0.8488	0.9795	0.9668	0.9869
Yang et al. [22]	2022	0.8075	0.9841	0.9664	0.9872	—
Our proposed		0.8503	0.9850	0.9671	0.9839	0.9002