Table 5. Segmentation performance of different possible combinations of three enhancement methods (LP, WL, FR) and three segmentation methods (GC, TV, LS) on the VAMPIRE 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	0.721	0.984	0.976	0.853	2.5	12.5
	TV	0.701	0.985	0.976	0.843	30.2	40.2
	LS	0.715	0.984	0.976	0.850	48.3	58.3
WL	GC	0.708	0.975	0.967	0.842	2.5	15.5
	TV	0.687	0.981	0.957	0.813	30.2	43.2
	LS	0.722	0.981	0.960	0.851	48.3	61.3
FR	GC	0.665	0.967	0.957	0.816	2.5	30.5
	TV	0.608	0.980	0.939	0.799	30.2	58.2
	LS	0.705	0.986	0.950	0.846	48.3	76.3