EURASIP Journal on Image and Video Processing

Table 2 Performance of proposed method on different datasets

From: Retinal vessel segmentation with constrained-based nonnegative matrix factorization and 3D modified attention U-Net

Datasets	Accuracy	Sensitivity	Specificity	Precision
STARE	0.9703	0.8881	0.9801	0.8408
DRIVE	0.9634	0.8434	0.9786	0.8626

Back to article page