基于Dense-UNet++的关节滑膜磁共振图像分割

王振宇,王颖珊,毛瑾玲,马伟伟,路青,石洁,汪红志

Magnetic Resonance Images Segmentation of Synovium Based on Dense-UNet++

Zhen-yu WANG,Ying-shan WANG,Jin-ling MAO,Wei-wei MA,Qing LU,Jie SHI,Hong-zhi WANG

表1 应用于相同滑膜磁共振图像测试集，采用不同激活函数的UNet模型的结果对比

Table 1 Comparison of different activation functions applied in the same test set of synovial magnetic resonance image with UNet model

网络结构 激活函数 Batch size 平均DSC 平均IOU 训练耗时 UNet ReLu 8 0.4432 0.5109 47 h UNet Swish 8 0.5369 0.6495 22 h