Liu Zifeng, Yang Zhiyong, Jiang Shan, Zhou Zeyang
School of Mechanical Engineering, Tianjin University, Tianjin, China.
Int J Med Robot. 2024 Dec;20(6):e70030. doi: 10.1002/rcs.70030.
In order to achieve spatial registration for surgical navigation, a spatial registration method based on point cloud and deep learning is proposed.
Neural networks are used to register medical image point clouds and patient surface point clouds to complete spatial registration of surgical navigation. An image processing method is designed to convert medical images into point clouds, and a structured light robot is used to extract patient surface point clouds.
Coarse registration was conducted through a neural network, followed by fine registration using the ICP algorithm, achieving a rotational registration error (RRE) of 0.961° and a translational registration error (TRE) of 0.118 mm. In phantom experiments, the surface registration error was 0.622 mm, and the target registration error was 0.748 mm.
The proposed spatial registration method based on point cloud and deep learning improves the accuracy and efficiency of neurosurgical navigation.
为实现手术导航的空间配准，提出一种基于点云与深度学习的空间配准方法。
利用神经网络对医学图像点云与患者表面点云进行配准，以完成手术导航的空间配准。设计一种图像处理方法将医学图像转换为点云，并使用结构光机器人提取患者表面点云。
先通过神经网络进行粗配准，再使用ICP算法进行精配准，旋转配准误差（RRE）为0.961°，平移配准误差（TRE）为0.118毫米。在体模实验中，表面配准误差为0.622毫米，目标配准误差为0.748毫米。
所提出的基于点云与深度学习的空间配准方法提高了神经外科手术导航的准确性和效率。
