基于特征分类的MRI医学图像弹性配准  

Medical MRI Image Registration Based on the Feature Space

作　　者：李静[1,2] 杨烜[3,4] 喻建平[3,4] 

机构地区：[1]西安电子科技大学电子工程学院 [2]深圳大学信息工程学院,深圳518060 [3]深圳大学信息工程学院 [4]深圳大学ATR国防科技重点实验室,深圳518060

出　　处：《中国图象图形学报》2007年第6期1069-1078,共10页Journal of Image and Graphics

基　　金：国家自然科学基金项目(60572101);广东省自然科学基金项目(31789)

摘　　要：基于互信息的弹性图像配准是医学图像配准的重要方法之一。然而由于互信息在小样本图像配准中,会出现多局部极值和极值偏离问题,从而容易出现配准误差,进而造成整图的弹性配准误差。为减少这种配准误差,提出了一种基于特征分类的互信息医学图像弹性配准方法。该方法先采用图像的灰度和梯度特征训练自组织映射(self-organized mapping,SOM)神经网络特征分类器,将图像由高维灰度空间映射到低维特征类别空间;然后,在特征类别空间进行互信息图像弹性配准。实验结果表明,该方法大大提高了小样本图像配准的成功率,并可通用于有噪和无噪的医学图像弹性配准中。Mutual information registration based on pixel intensity has been widely used in recent years. However, its application to sub-images with small samples is questionable, because many local maximums may happen or the global maximum may be away from the actual maximum value which causes unnecessary registration error. A new approach, mutual information registration based on feature-label （ MIF ） , is proposed to solve such problem. This method first uses image＇s intensity and gradient features to train the self-organized mapping（SOM） neural network, and then builds up the feature classifier for each modal image. Using such a classifier, images are project into a feature space with decreased dimensions. Finally mutual information is evaluated in the feature space to match images. Our results demonstrate that this method increases the success rate of the sub-image registration, and is optimal for the whole images（ either with or without noise） elastic registration.

关 键 词：图像配准 弹性配准 互信息 特征分类 特征标识 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]