Table 2 Comparison of computational complexity and number of parameters between MBSNet and each comparison model.

From: A novel medical image segmentation approach by using multi-branch segmentation network based on local and global information synchronous learning

Methods

Year

FLOPs (G)

Params (M)

UNet1

2015

102.56

34.53

AttU-Net6

2018

104.28

34.88

UNet++2

2018

216.55

36.63

UNeXt4

2022

0.87

1.47

MBSNet

2023

10.68

3.98

  1. Significant values are in [bold].
Back to article page