Structure-based level set method for automatic retinal vasculature segmentation

EURASIP Journal on Image and Video Processing

Table 4 Statistical results of our method for test images of 1 to 20 from our dataset

Dataset	Image number	Se	Sp	Ppv	Npv	Acc	κ
Ours	1	0.4821	0.9905	0.7483	0.9702	0.9623	0.5676
	2	0.3471	0.9887	0.6680	0.9586	0.9494	0.4330
	3	0.5745	0.9786	0.5802	0.9781	0.9589	0.5557
	4	0.5617	0.9695	0.5911	0.9657	0.9398	0.5437
	5	0.5699	0.9872	0.7537	0.9708	0.9602	0.6284
	6	0.3527	0.9879	0.6416	0.9613	0.9511	0.4318
	7	0.8109	0.9566	0.5234	0.9885	0.9485	0.6098
	8	0.3134	0.9887	0.6280	0.9594	0.9499	0.3950
	9	0.3966	0.9857	0.5666	0.9719	0.9591	0.4461
	10	0.4290	0.9878	0.5958	0.9764	0.9654	0.4814
	11	0.2789	0.9901	0.6119	0.9607	0.9523	0.3619
	12	0.5497	0.9840	0.6101	0.9796	0.9651	0.5602
	13	0.6942	0.9783	0.6056	0.9852	0.9653	0.6288
	14	0.4028	0.9844	0.5128	0.9759	0.9616	0.4316
	15	0.5848	0.9849	0.5977	0.9840	0.9700	0.5756
	16	0.3300	0.9877	0.6573	0.9539	0.9440	0.4133
	17	0.7426	0.9731	0.5785	0.9870	0.9622	0.6308
	18	0.5550	0.9762	0.5149	0.9797	0.9578	0.5122
	19	0.7238	0.9712	0.6101	0.9826	0.9567	0.6392
	20	0.6576	0.9680	0.4891	0.9838	0.9542	0.5373