SERR-U-Net: Squeeze-and-Excitation Residual and Recurrent Block-Based U-Net for Automatic Vessel Segmentation in Retinal Image

Table 8

Comparative results with state-of-the-art methods on DRIVE databases.

DRIVE	Methods	ACC	SE	SP	AUC
Unsupervised learning	Lam [29]	0.9472	\	\	0.9614
	You [30]	0.9434	0.7410	0.9751	\
	Azzopardi [31]	0.9442	0.7655	0.9704	0.9614
Supervised learning	Roychowdhury [32]	0.9520	0.7250	0.9830	0.9620
	Liskowsk [33]	0.9495	0.7763	0.9768	0.9720
	Qiaoliang [34]	0.9527	0.7569	0.9816	0.9738
	Ours	0.9552	0.7792	0.9813	0.9784