Mean Divergence Measures for Multimodality Medical Image Registration

The mean divergence measures are used as the similarity measure of medical image registration. The square root arithmetic mean divergence (SAM), square root geometric mean divergence (SGM), square root harmonic mean divergence (SHM), arithmetic geometric mean divergence (AGM), and arithmetic harmonic mean divergence (AHM) are applied to rigid registration of computed tomography (CT)/positron emission tomography (PET) and magnetic resonance (MR)/PET images. The performance of these measures is studied in comparison with mutual information. The proposed registration measures have similar function curves with mutual information. Experimental results show that the AHM measure has significant improvement in registration speed.