Abstract: According to the feature that different organ has different deformation character，this paper presents a register algorithm based on local region constraints.The segmented bony structures in the two respective images are registered based on their boundary points，and then dense deformations in the entire images are interpolated by a thin plate spline interpolation technique.Bhattacharyya distance based B-Spline registration algorithm is used to iteratively refine the registration of soft tissues with different constraints，and at the same time keep the rigid transformation for each bony structure.The proposed registration algorithm has been applied to the clinical data with very encouraging results by two clinical radiologists.

Key words: image registration, free-form deformation, thin plate spline, B-Spline, Bhattacharyya distance

摘要： 根据人体不同器官具有不同的弹性这一特点构造了一种基于局部区域约束的图像配准算法。首先抽取骨骼边缘上的点作为标志点，利用软对应匹配算法计算出每一个骨骼与其对应骨骼的刚性变换；然后通过薄板样条插值得出整幅图像的变形场；由于同一器官的位移大小相近，将这一区域的均值作为区域内每一点的位移量；将更新后的初始位移场代入到基于B样条的自由形变模型中，得到新的位移场；以Bhattacharyya距离为目标函数，一直迭代下去直到目标函数值达到最优。通过对临床数据的实验表明该方法能够满足临床医生的要求。

关键词: 图像配准, 自由形变模型, 薄板样条, B样条, Bhattacharyya距离