基于级联网络的膝关节图像分割与模型构建

马岩,邢藏菊,肖亮

Knee Joint Image Segmentation and Model Construction Based on Cascaded Network

Yan MA,Cang-ju XING,Liang XIAO

表2 5种自动分割模型和人工标注结果间最大SAR10g的相对误差的比较

Table 2 Comparison of the relative errors of maximum SAR10g between the 5 automatic segmentation methods and the manual segmentation

统计参数 U-Net U-Net (focal loss) U-Net (attention) U-Net++ 本文所提方法 Mean 0.0538 0.0433 0.4042 0.0547 0.0366 Std 0.0599 0.0424 0.3621 0.0520 0.0357