一种多模态医学影像鲁棒配准方法

为提高多模态医学影像配准的鲁棒性和精度,提出了一种基于主定序和混合熵的配准新方法.首先利用主成分分析方法定义了图像的主定序特征,描述图像邻域像素间的空间信息和微观结构特性;进而结合图像灰度信息构造了一种基于混合熵的配准测度,有效保证了配准测度函数的光滑性和收敛性.多组多模态医学影像测试结果表明,新方法能有效抑制噪声,具有很高的配准精度,鲁棒性强,优于现有的几种方法.

Robust registration of multimodality medical images based on the principal ordinal feature and hybrid entropy

To improve the robustness and precision of multimodality medical image registration,a principal ordinal feature and hybrid entropy based registration method is presented.A principal ordinal feature is defined and used to represent the spatial information between the neighboring pixels and the properties of the specified micro-structure in medical images.Integrating with pixel intensities,a similarity measure based on hybrid entropy is defined to register multimodality images.The proposed method is demonstra...