MAP-MRF based similarity measures for intensity-based 2D-3D registration

Similarity measure is one of the main factors that affect the accuracy of intensity-based 2D-3D registration of X-ray fluoroscopy to CT images This paper presents a unifying MAP-MRF framework for rationally deriving point similarity measures based on Bayes theorem. Three new similarity measures derived from this framework are presented and evaluated using a phantom and a human cadaveric specimen. Their behaviours are compared with other well-known similarity measures and the comparison results are reported. The optimization of each individual similarity measure derived from this framework leads to optimal registration. We report their capture ranges, converging speeds, and registration accuracies.