Table 4 Comparison of different algorithms on the STARE dataset.
From: Enhanced feature dynamic fusion gated UNet for robust retinal vessel segmentation
Methods | Date | ACC | SE | SP | AUC | F1 |
|---|---|---|---|---|---|---|
U-Net1 | 2015 | 0.9738 | 0.7814 | 0.9897 | 0.9892 | 0.8138 |
Attention U-Net17 | 2018 | 0.9719 | 0.8009 | 0.9859 | 0.9886 | 0.8084 |
ResUNet++ 19 | 2019 | 0.968 | 0.8173 | 0.9803 | 0.9854 | 0.7906 |
HRNet20 | 2019 | 0.9731 | 0.8159 | 0.986 | 0.9885 | 0.8159 |
UNet3+ 22 | 2020 | 0.9731 | 0.8064 | 0.9869 | 0.9889 | 0.8153 |
SCS-Net27 | 2021 | 0.9736 | 0.8207 | 0.9839 | 0.9877 | – |
MMDC-Net28 | 2022 | 0.9591 | 0.8509 | 0.9689 | 0.9687 | – |
D-MNet31 | 2022 | 0.9732 | 0.8272 | 0.9847 | – | 0.8196 |
MBSNet32 | 2023 | 0.9739 | 0.8125 | 0.9871 | 0.9898 | 0.8213 |
DCSAU-Net33 | 2023 | 0.9726 | 0.819 | 0.9852 | 0.9872 | 0.8162 |
SDDC-Net34 | 2023 | 0.9669 | 0.8268 | 0.9789 | 0.9845 | 0.7965 |
BCU-Net35 | 2023 | 0.9701 | 0.8500 | 0.9807 | 0.9807 | 0.8223 |
GDF-Net36 | 2023 | 0.9653 | 0.7616 | 0.9957 | 0.9889 | 0.8022 |
CFFANet37 | 2024 | 0.9630 | – | 0.9800 | – | 0.8400 |
TCDDU-Net38 | 2024 | 0.9740 | 0.7920 | 0.9884 | 0.9856 | 0.8163 |
MVM-UNet40 | 2025 | 0.9715 | 0.8178 | 0.9839 | – | – |
EFDG-UNet | 2025 | 0.9637 | 0.8575 | 0.9769 | 0.9842 | 0.8376 |
