A Unifying MAP-MRF Framework for Deriving New Point 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-MFR 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 behaviors are compared to other well-known similarity measures and the comparison results are reported. Combining any one of the new similarity measures with a previously introduced spline-based multi-resolution 2D-3D registration scheme, we develop a fast and accurate registration algorithm. We report their capture ranges, converging speeds, and registration accuracies