Thorax multimodal medical image registration based on adaptive free-form deformation and gradient descent
基于自适应自由变形法和梯度下降法的胸部多模医学图像配准*

In order to realize the automatic registration of thorax multimodal medical images, this paper proposed an image registration method based on hierarchical adaptive free-form deformation and gradient descent. Firstly, extracted the edge of thorax by GVF Snake algorithm and Canny operator, and matched feature points automatically. Then, modeled the global coarse registration of thorax multimodal medical images by principal axes algorithm. Finally, realized the local fine registration of thorax multimodal medical images by a free-form deformation(FFD) based on hierarchical B-splines. Moreover, generated the FFD parameters apidly by gradient descent and maximization of mutual information. Experiments demonstrate the good performance of the proposed method.