Skip to main content

Table 5 Comparison with the deep learning methods on DRISHITI-GS dataset

From: Joint optic disc and cup segmentation based on densely connected depthwise separable convolution deep network

Method \(DC_{disc}\,(mean)\) \(DC_{cup}\,(mean)\) \(JC_{disc}\,(mean)\) \(JC_{cup}\,(mean)\)
U-Net [15] 0.950 0.820
M-Net [16] 0.959 0.866
Stack-U-Net [30] 0.970 0.890
Sevastopolsky [10] 0.850 0.750
Yu et al. [34] 0.973 0.887
MULTI-MODEL-PRE-TRAINING [33] 0.960 0.902 0.924 0.823
WGAN [31] 0.954 0.840 0.912 0.724
pOSAL [31] 0.965 0.858
GL-Net [29] 0.971 0.905
Proposed 0.978 0.912 0.957 0.844
  1. Italics indicate the best results