Skip to main content
. 2021 Jun 5;16(9):1425–1434. doi: 10.1007/s11548-021-02418-w

Table 3.

Comparison of DUDA-Net and several existing works

References Years Method DSC IoU SEN SPE
Zhou et al. [23] 2020 U-Net using an attention mechanism 83.1% 86.7% 99.3%
Omar et al. [24] 2020 Region of interest extraction segmentation network 78.6% 71.1% 99.3%
Qiu et al. [9] 2020 MiniSeg segmentation network 77.28% 82.12% 83.62% 97.42%
Ours 2021 DUDA-Net 87.06% 77.09% 90.84% 99.58%

The bold figures in Table are the optimal performance