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

图4 应用于相同的滑膜磁共振图像数据集，采用不同激活函数的UNet模型的DSC和IOU曲线. (a) DSC曲线，使用ReLu激活函数；(b) DSC曲线，使用Swish激活函数；(c) IOU曲线，使用ReLu激活函数；(d) IOU曲线，使用Swish激活函数

Fig.4 The DSC and IOU curves of UNet model with different activation functions applied in the same synovial magnetic resonance data set. (a) DSC curves, UNet with ReLu; (b) DSC curves, UNet with Swish; (c) IOU curves, UNet with ReLu; (d) IOU curves, UNet with Swish