A Medical Image Registration Method Based on Weighted Mutual Information

In this paper, a weighted mutual information (WMI) is proposed for medical image registration. Conventional information measures, for example Shannon´s entropy and mutual information (MI), are based on the statistical properties of intensity values of images, and float image and reference image are playing same role when calculating their MI. In fact, because the characteristics and the qualities of registration images are different, the float image and the reference image in registration should have different importance levels and should be treated unequally. In this paper, the WMI-based registration method considers the importance of the float image and the reference image. The experiments of the 2D and 3D rigid registration of clinical brain images show that the WMI-based registration method is much more robust and more accurate than the conventional Mi-based registration methods.