Optimize the correspondence using Particle Swarm Optimization for medical image registration

The scope of this research is to propose a method for determining pairs of corresponding points between medical images, the method is based on the implementation of Particle Swarm Optimization (PSO) used as a function optimizer and Mutual Information used as a similarity measure. Firstly, Landmarks (LMs) were chosen manually specific to Braces Pty Ltd cephalometric analysis and used Thin Plate Spline (TPS) to provide a geometric representation for the relative locations of corresponding landmarks. Secondly, Mutual Information used as a cost-function to determine the degree of similarity between two images. Finally, PSO is used to maximize mutual information function and to improve the correspondence between the LMs. Experimental results demonstrate that the algorithm yields significant improvement in the registration accuracy.