基于特征门控融合与小波增强的双编码器息肉分割

梁礼明,康婷,陈康泉,钟奕

Dual-encoder polyp segmentation with feature-gated fusion and wavelet enhancement

Liming LIANG,Ting KANG,Kangquan CHEN,Yi ZHONG

表 2 不同网络在CVC-ClinicDB和Kvasir上的对比

Tab.2 Comparison of different networks on CVC-ClinicDB and Kvasir

数据集 网络 Dice mIoU SE PC F2 MAE CVC- ClinicDB U-Net 0.823 0.755 0.834 0.839 0.827 0.019 Caranet 0.934 0.890 0.944 0.940 0.939 0.006 MEGANet 0.941 0.897 0.951 0.941 0.945 0.006 SSFormer-S 0.918 0.875 0.905 0.939 0.910 0.007 MSRAFormer 0.924 0.874 0.945 0.920 0.932 0.008 Polyp-PVT 0.937 0.889 0.949 0.936 0.945 0.006 SAM2-UNet 0.914 0.860 0.916 0.920 0.914 0.010 本研究 0.948 0.904 0.952 0.948 0.950 0.006 Kvasir U-Net 0.818 0.746 0.856 0.857 0.827 0.055 Caranet 0.922 0.872 0.915 0.941 0.921 0.019 MEGANet 0.916 0.866 0.913 0.939 0.912 0.025 SSFormer-S 0.925 0.877 0.914 0.944 0.917 0.018 MSRAFormer 0.923 0.873 0.915 0.952 0.917 0.024 Polyp-PVT 0.917 0.864 0.913 0.947 0.914 0.023 SAM2-UNet 0.902 0.847 0.904 0.931 0.901 0.029 本研究 0.933 0.885 0.923 0.955 0.926 0.019