TABLE 1.
The experimental results on the Synapse dataset include the average Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD) for each organ, as well as the individual DSC for each organ.
| mDSC | mHD | DSC of a single organ | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Model | Year | DSC | HD | Aorta | Gallbladder | Kidney(L) | Kidney(R) | Liver | Pancreas | Spleen | Stomach |
| U-Net (Ronneberger et al., 2015) | 2015 | 76.85% | 39.70 | 89.07 | 69.72 | 77.77 | 68.6 | 93.43 | 53.98 | 86.67 | 75.58 |
| U-Net++ (Zhou et al., 2018) | 2018 | 76.91% | 36.93 | 88.19 | 68.89 | 81.76 | 75.27 | 93.01 | 58.20 | 83.44 | 70.52 |
| Residual U-Net (Diakogiannis et al., 2020) | 2018 | 76.95% | 38.44 | 87.06 | 66.05 | 83.43 | 76.83 | 93.99 | 51.86 | 85.25 | 70.13 |
| Att-Unet (Oktay et al., 2018) | 2018 | 77.77% | 36.02 | 89.55 | 68.88 | 77.98 | 71.11 | 93.57 | 58.04 | 87.30 | 75.75 |
| MultiResUNet (Ibtehaz and Rahman, 2020) | 2020 | 77.42% | 36.84 | 87.73 | 65.67 | 82.08 | 70.43 | 93.49 | 60.09 | 85.23 | 75.66 |
| TransUNet (Chen et al., 2021) | 2021 | 77.48% | 31.69 | 87.23 | 63.13 | 81.87 | 77.02 | 94.08 | 55.86 | 85.08 | 75.62 |
| UCTransNet (Wang et al., 2022a) | 2022 | 78.23% | 26.75 | 84.25 | 64.65 | 82.35 | 77.65 | 94.36 | 58.18 | 84.74 | 79.66 |
| TransNorm (Azad et al., 2022) | 2022 | 78.40% | 30.25 | 86.23 | 65.1 | 82.18 | 78.63 | 94.22 | 55.34 | 89.50 | 76.01 |
| MT-UNet (Wang et al., 2022b) | 2022 | 78.59% | 26.59 | 87.92 | 64.99 | 81.47 | 77.29 | 93.06 | 59.46 | 87.75 | 76.81 |
| swin-unet (Cao et al., 2022) | 2022 | 79.13% | 21.55 | 85.47 | 66.53 | 83.28 | 79.61 | 94.29 | 56.58 | 90.66 | 76.60 |
| DA-TransUNet (Sun et al., 2023) | 2023 | 79.80% | 23.48 | 86.54 | 65.27 | 81.70 | 80.45 | 94.57 | 61.62 | 88.53 | 79.73 |
| MIPC-Net(Ours) | 80.00% | 19.32 | 87.30 | 66.43 | 83.24 | 80.37 | 94.48 | 59.45 | 89.20 | 79.55 | |
The bold values indicate the best performance among all the methods compared in each respective evaluation metric. For each row in a table, the bold number represents the method that achieves the highest score or lowest error on that particular metric, demonstrating its superior performance relative to the other approaches.