Table 2. Segmentation performance of different possible combinations of three enhancement methods (LP, WL, FR) and three segmentation methods (GC, TV, LS) on the DRIVE dataset.

LP, WL and FR denote local phase, wavelet and Frangi’s eigenvalue based enhancement filters respectively. GC, TV and LS denote graph cut, total variation and level set based segmentation methods respectively. Se: sensitivity; Sp: specificity; Acc: accuracy; AUC: area under the curve.

Enhancement	Segmentation	Se	Sp	Acc	AUC	Seg. Time (s)	Entire Time (s)
LP	GC	0.744	0.978	0.953	0.861	0.6	4.6
	TV	0.702	0.949	0.930	0.816	16.1	20.1
	LS	0.679	0.924	0.921	0.802	22.1	26.1
WL	GC	0.744	0.923	0.921	0.833	0.6	5.6
	TV	0.687	0.930	0.912	0.800	16.1	21.1
	LS	0.691	0.934	0.914	0.805	22.1	27.1
FR	GC	0.667	0.921	0.881	0.776	0.6	20.6
	TV	0.722	0.921	0.893	0.807	16.1	36.1
	LS	0.694	0.939	0.927	0.811	22.1	42.1