Spatial Bias in Multi-Atlas Based Segmentation.
Spatial Bias in Multi-Atlas Based Segmentation.
复制标题
DOI：
10.1109/cvpr.2012.6247765
复制
发表时间：
2012-06-24
期刊：
影响因子：
--
通讯作者：
Yushkevich PA
中科院分区：
文献类型：
--
作者：
Wang H;Yushkevich PA
多图谱分割在医学图像分析中有着广泛的应用。该技术通过可变形配准，实现了从预先标记的地图集到未知图像的标签传递。当可变形配准产生误差时，结合多个地图集的结果进行标签融合是减少分割误差的有效方法。在现有的标签融合策略中，具有空间变化的权重分布的相似度加权投票策略尤为成功。我们发现，基于加权投票的标签融合产生了低于凸形结构分割的空间偏向。偏差可以近似为将空间卷积应用于地面真实空间标签概率图，其中卷积核结合了残余配准误差的分布和产生基于相似性的投票权重的函数。为了减少这种偏差，我们将标准的空间反卷积应用于通过加权投票获得的空间概率图。在脑图像分割实验中，我们演示了这种空间偏差，并表明我们的技术大大减少了这种空间偏差。
Multi-atlas segmentation has been widely applied in medical image analysis. With deformable registration, this technique realizes label transfer from pre-labeled atlases to unknown images. When deformable registration produces error, label fusion that combines results produced by multiple atlases is an effective way for reducing segmentation errors. Among the existing label fusion strategies, similarity-weighted voting strategies with spatially varying weight distributions have been particularly successful. We show that, weighted voting based label fusion produces a spatial bias that under-segments structures with convex shapes. The bias can be approximated as applying spatial convolution to the ground truth spatial label probability maps, where the convolution kernel combines the distribution of residual registration errors and the function producing similarity-based voting weights. To reduce this bias, we apply a standard spatial deconvolution to the spatial probability maps obtained from weighted voting. In a brain image segmentation experiment, we demonstrate the spatial bias and show that our technique substantially reduces this spatial bias.