Table 5 Comparison with the state-of-the-art methods on the BraTS2018 validation dataset
From: A lightweight hierarchical convolution network for brain tumor segmentation
Methods | Dice (%) | HD95 (mm) | Params (M) | FLOPs (G) | ||||
|---|---|---|---|---|---|---|---|---|
ET | WT | TC | ET | WT | TC | |||
Kao et al. [37] | 78.75 | 90.47 | 81.35 | 3.81 | 4.32 | 7.56 | 9.45 | 203.96 |
3D U-Net | 75.26 | 88.69 | 80.55 | 4.51 | 11.34 | 8.07 | 5.89 | 148.17 |
S3D- UNet [28] | 74.93 | 89.35 | 83.09 | 4.43 | 4.72 | 7.75 | 3.32 | 75.20 |
3D-ESPNet [27] | 73.70 | 88.30 | 81.40 | 5.30 | 5.46 | 7.85 | 3.63 | 76.51 |
LHC-Net (Ours) | 76.82 | 90.21 | 83.79 | 4.36 | 5.56 | 6.79 | 1.65 | 35.58 |