基于互信息的医学图像配准技术研究进展

Advances in Medical Image Registration Based on Mutual Information

基于互信息的图像配准方法具有自动化程度高、配准精度高等优点,已被广泛应用于医学图像的配准。详细地介绍了互信息的基本概念、归一化互信息、互信息计算中常用的变换模型、插值方法、优化算法及提高配准速度策略等。同时对互信息在配准技术中存在的问题及解决方法进行了系统地介绍,最后对今后互信息的研究工作作了展望。

The matching algorithm based on mutual information, which has the advantages of high speed, good automation and superion accuracy, is widely used in medical image registration. In this paper are presented the basic conception of mutual information, the transform model, the insert value algorithm, the optimization algorithm and the strategy in computing mutual information. Furthermore, we introduce some efficient methods for solving the problems in registration technique based on mutual information, and look forward to the future research work.