弹性的二维医学图像配准算法

提出了一个弹性二维医学图像配准算法,该算法将基于像素浓度值配准算法和基于特征点的配准算法相结合,采用自动的特征点定位算法,使用薄板样条算法来提高配准的精度,从而可以对二维医学图像进行自动、准确的配准。首先,用基于像素浓度值的全局仿射配准实现对鲁棒配准的初始估计;然后,通过使用基于特征点的迭代配准算法,使得全局仿射配准结果在第2步配准算法中得到进一步的细化而使其配准结果具有更高的准确性。对二维PHANTOM图像的实验结果表明,该算法具有鲁棒性。

Elastic registration algorithm for 2-D medical images

A novel elastic medical image registration approach is proposed. By combining intensity-based registration method with landmark-based registration method, the proposed algorithm can register 2D medical images automatically and accurately Firstly, the global affine registration method based on image intensity is used to initialize a starting estimation of the robust registration algorithm. Then, by using iterative landmark based algorithm, the affine registration results are registered with high accuracy in the second step. In the second registration step, the novel automatic landmark localization method is introduced and the thin-plate spline is used to refine the registration precision. Experimental results are presented for the registration of the 2D Phantom images to prove the robustness of our algorithm.