将源图像Delaunay三角化,用弹簧分子系统模拟网格形变,网格点在系统力的作用下移动去拟合待配准的目标图像,力由互信息梯度定义,并利用已知解剖结构特征的对应关系对形变过程进行约束,经过一段时间,网格点停止运动,对每一个Delaunay三角形计算局部仿射变换.实验结果表明,该算法能够快速准确地实现弹性医学图像配准。
On medical image registration, the source image is first Delaunay triangulated, and then modeled as a spring mass system. The system deforms under the influence of forces derived from gradient of the mutual information registration criterion, while specific geometrical structures are restricted to predefined shapes. When the mesh vertices reach equilibrium, each Delaunay triangle undertakes a local affine transformation. Experimental results show that the algorithm may be used to register both intromodality and inter-modality images, and control the deformation rapidly and precisely.