Estimatingprobability Distributions in Mutual Information Using Empca Approach

Mutual information (MI) has been widely used as asimilarity measure in medical image registration (MIR) for morethan a decade. Preliminarily, a number of bins, which is used inevaluating the probability distribution of grey levels, haveinfluenced the performance of MI. Consequently, it can influence the precision of MIR and may prompt a wrong therapeutic conclusion. In an examination of pictures from various modalities, it is more tests to pick such an ideal number of receptacles. With a specific end goal to fulfill such a test, we propose another cross breed strategy in light of the procedure of a desire augmentation for primary segment examination (EMPCA) and the idea of Scott's manag. We have analyzed and evaluated our approachbased on MRI images: T1, T2 and PD. The experimental resultshave shown that this approach can find a more appropriate binnumber which can improve the performance of MI in terms of itsaccuracy compared to others.