基于互信息的医学图像配准中互信息的计算

Computation of Mutual Information in Medical Image Registration Based on Mutual Information

基于互信息的配准方法是医学图像配准领域的重要方法。互信息是图像配准中常用的相似性度量,具有鲁棒、精度高等优点,但基于互信息的配准计算量大,制约了它的实际应用。我们采用基于多分辨率和混合优化策略的配准方法,在图像的不同灰度等级数下进行配准,分析了互信息的计算量与灰度等级数的关系,并用人头部的MRI图像和CT图像做了二维的单模模拟实验和多模实际配准实验,结果显示在灰度等级数为32和64时,与灰度等级数为256时相比,配准精度没有明显改变,而计算量下降显著。

Registration based on mutual information is a typical method in medical image registration. Mutual informarion is a common similarity measure in image registration, which has excellent robusmess and accuracy, but large calculation amount makes it difficult to be applied to clinics. In this paper, a registration algorithm based on multi-resolution and hybrid optimization is adopted to implement 2-dimension monomodal and multimodal registrations of MRI and CT images of human heads with different numbers of gray bins. Results of experiments show that registration precisions have not notable change with 32, 64 gray bins, compared with 256 gray bins, whereas the computation costs decrease remarkably.