Image-to-patient space registration is to make the accurate alignment between the actual operating space and the image space. Although the image-to-patient space registration using paired-point is used in some image-guided neurosurgery systems, the current paired-point registration method has some drawbacks and usually cannot achieve the best registration result. Therefore, surface-matching registration is proposed to solve this problem. This paper proposes a surface-matching method that accomplishes image-to-patient space registration automatically. We represent the surface point clouds by the Gaussian Mixture Model (GMM), which can smoothly approximate the probability density distribution of an arbitrary point set. We also use mutual information as the similarity measure between the point clouds and take into account the structure information of the points. To analyze the registration error, we introduce a method for the estimation of Target Registration Error (TRE) by generating simulated data. In the experiments, we used the point sets of the cranium surface and the model of the human head determined by a CT and laser scanner. The TRE was less than 2mm, and the TRE had better accuracy in the front and the posterior region. Compared to the Iterative Closest Point algorithm, the surface registration based on GMM and the structure information of the points proved superior in registration robustness and accurate implementation of image-to-patient registration.

中文翻译：

---

基于图像引导神经外科系统结构信息的鲁棒表面匹配配准

图像到患者空间的配准是使实际操作空间和图像空间之间的精确对准。虽然在一些图像引导的神经外科系统中使用了使用配对点的图像到患者空间配准，但目前的配对点配准方法存在一些缺点，通常不能达到最佳配准效果。因此，提出了表面匹配配准来解决这个问题。本文提出了一种自动完成图像到患者空间配准的表面匹配方法。我们用高斯混合模型（GMM）表示表面点云，它可以平滑地近似任意点集的概率密度分布。我们还使用互信息作为点云之间的相似性度量，并考虑点的结构信息。为了分析配准误差，我们引入了一种通过生成模拟数据来估计目标配准误差（TRE）的方法。在实验中，我们使用了由CT和激光扫描仪确定的颅面点集和人头模型。TRE 小于 2mm，TRE在前部和后部区域具有更好的精度。与迭代最近点算法相比，基于GMM的表面配准和点的结构信息证明在配准鲁棒性和图像到患者配准的准确实现方面具有优势。