Research Article

Joint Dense Residual and Recurrent Attention Network for DCE-MRI Breast Tumor Segmentation

Table 2

Comparison of experimental results of the different prediction models on the test set. All values in this table are averages from 32 test cases.

MethodJaccardDSCSENSPEPPVHD

U-net [8]0.63480.75570.80180.99890.768833.2948
Attention U-Net [22]0.63860.75940.80130.99900.778719.5235
Residual U-Net [20]0.63220.75550.82200.99880.752625.1890
Dense U-Net [21]0.65290.76670.80310.99910.778120.9375
V-net [25]0.63600.75870.81840.99890.755943.3051
Present model0.66490.78270.82960.99900.792817.0818

The best results for the segmentation metrics in the comparison experiment are shown in bold.