融合注意力机制的多尺度残差Unet的磁共振图像重建

李奕洁,杨馨雨,杨晓梅

Magnetic Resonance Image Reconstruction of Multi-scale Residual Unet Fused with Attention Mechanism

Li Yijie,YANG Xinyu,YANG Xiaomei

表3 消融实验网络模型的平均性能

Table 3 Average performance of networks in ablation experiments

网络模型 PSNR SSIM ×2 ×3 ×4 ×2 ×3 ×4 Unet 32.5193±1.0901 31.3347±1.0899 30.8267±1.0921 0.7771±0.0761 0.6829±0.0770 0.6475±0.0769 Att-Unet 32.9367±1.1096 31.5930±1.2019 30.9052±1.1099 0.7777±0.0799 0.6887±0.0811 0.6485±0.0787 MRes-Unet 33.0847±0.9998 31.6665±1.0621 30.9085±1.2260 0.7849±0.0814 0.6959±0.0816 0.6445±0.0813 SAMRes-Unet 33.1018±1.3921 31.6770±1.2998 30.9095±1.2975 0.7852±0.0824 0.6953±0.0827 0.6466±0.0825 CAMRes-Unet 33.1115±1.3001 31.6801±1.2645 30.9106±1.2301 0.7856±0.0831 0.6960±0.0829 0.6476±0.0833 AttMRes-Unet 33.2185±1.2759 31.7255±1.1794 30.9175±1.2376 0.7862±0.0862 0.6972±0.0859 0.6497±0.0865