EURASIP Journal on Image and Video Processing

Table 4 Performance analysis of all algorithms on DRIVE databases with respect to the measuring metrics

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

Methods	Accuracy	Specificity	Sensitivity	Precision
U-Net [1]	0.9491	0.9796	0.7071	0.8148
AG-UNet [35]	0.9599	0.9775	0.8201	0.8221
IterNet [26]	0.9574	0.9831	0.7791	0.8691
DenseNet [36]	0.9604	0.9750	0.8449	0.8106
V-GAN [37]	0.9560	0.9689	0.8541	0.7763
Ours	0.9634	0.9786	0.8434	0.8626

Back to article page