一种非刚性医学图像的点配准方法

A Novel Point-Based Method for Non-Rigid Medical Images Registration

提出了一种具有鲁棒性的进行非刚性医学图像点配准的新方法.为了更好地处理点配准中的冗余点问题,对冗余点进行了建模,在此基础上对点配准能量函数进行了改进.使用确定性退火优化算法对改进后的能量函数进行最优化从而得到配准的非刚性变换,避免了优化过程中出现的局部极小值解.该方法能有效地处理冗余点,抗噪声能力较强,可以很快地配准带有噪声且有冗余点的非刚性医学图像.使用薄板样条对三维腹部医学图像进行全局弹性配准,实验结果显示配准的精度可以达到亚像素精度.

A new algorithm was developed for the non-rigid point matching problem. A model is constructed for dealing with outliers within the two point sets. Based on the model, the energy function is improved. With the help of the deterministic annealing technique, the algorithm jointly estimates a one-to-one correspondence and a non-rigid transformation between the two sets of points. This new robust algorithm can overcome many local minima encountered in the matching process. Because of its capability to tolerate noise and to reject possible outliers existed within the data points, it can register multi-model medical images which are even spoild by noise. The algorithm was applied to the registration of 3D ventral images of CT and MR with thin-plate splines. The experimental results demonstrate that it can get sub-pixel registration precision.