Structure-based level set method for automatic retinal vasculature segmentation

EURASIP Journal on Image and Video Processing

Table 5 Statistical results of our method for test images of 1 to 20 from STARE dataset

Dataset	Image number	Se	Sp	Ppv	Npv	Acc	κ
STARE	1	0.6449	0.9731	0.7455	0.9574	0.9374	0.6570
	2	0.5754	0.9836	0.7795	0.9584	0.9464	0.6336
	3	0.8036	0.9519	0.5973	0.9820	0.9398	0.6527
	4	0.3117	0.9972	0.9275	0.9271	0.9271	0.4376
	5	0.8084	0.9466	0.6803	0.9723	0.9296	0.6985
	6	0.7759	0.9666	0.6912	0.9781	0.9498	0.7035
	7	0.8567	0.9631	0.7412	0.9820	0.9514	0.7674
	8	0.7758	0.9644	0.7125	0.9742	0.9451	0.7121
	9	0.7814	0.9698	0.7569	0.9736	0.9495	0.7406
	10	0.7568	0.9722	0.7711	0.9700	0.9485	0.7349
	11	0.8000	0.9629	0.7004	0.9780	0.9470	0.7175
	12	0.8446	0.9665	0.7490	0.9814	0.9537	0.7679
	13	0.7743	0.9710	0.7881	0.9687	0.9470	0.7510
	14	0.7611	0.9739	0.8055	0.9663	0.9474	0.7528
	15	0.6239	0.9796	0.8031	0.9512	0.9376	0.6680
	16	0.4445	0.9916	0.8961	0.9165	0.9150	0.5528
	17	0.7238	0.9803	0.8372	0.9621	0.9488	0.7477
	18	0.5669	0.9931	0.8594	0.9685	0.9635	0.6647
	19	0.4183	0.9934	0.8001	0.9646	0.9595	0.5304
	20	0.8035	0.9512	0.6234	0.9797	0.9377	0.6679