Creaseness-based computer tomography and magnetic resonance registration: Comparison with the mutual information method

This paper describes a method which uses the skull as a landmark for automa tic registration of computer tomography to magnetic resonance (MR) images. First, the skull is extracted from both images using a new creaseness opera tor. Then, the resulting creaseness images are used to build a hierarchic s tructure which permits a robust and fast search. We have justified experime ntally the performance of several choices of our algorithm, and we have tho roughly tested its accuracy and robustness against the well-known mutual in formation method for five different pairs of images. We have found both com parable, and for certain MR images the proposed method achieves better perf ormance. (C) 1999 SPIE and IS&T. [S1017-9909(99)00403-1].