为了准确、可靠地配准多模态医学图像，提出了一种基于互信息的全局优化配准算法。该算法首先提取出目标物体的外轮廓面，再用迭代最近点方法初步对齐图像；然后用确定性的全局优化方法—Dividing Rectangles搜索归一化互信息的全局最优解。该算法利用图像的特征信息，为Dividing Rectangles方法提供了一个较好的初始配准位置，并充分利用了Dividing Rectangles方法在小范围内的高效搜索能力。实验结果表明，对于3维人体脑部数据，该算法配准精度高、速度快，而且有效地避免了配准过程中出现的局部极值。

A global optimization method based on mutual information is proposed for multimodality medical image registration. First external surfaces are extracted from various image modalities and the ICP algorithm is adopted to initially align unregistered images. Then the registration is performed by maximization of normalized mutual information using a deterministic global optimization algorithm named Dividing Rectangles. The surface based matching is used to provide a good start point for Dividing Rectangles in order to fully utilize its high efficiency in small search space. The results of experiment on three dimensional human brain data show that this method is accurate, fast, and avoids local minimums efficiently.