Rigid multi-modality registration of medical images using point similarity measures
نویسندگان
چکیده
Rigid registration is usually performed as an optimization procedure that searches for an image transformation that gives best similarity between the registered images. Similarity is used as a measure of image correspondence. In this work we present an implementation of rigid multimodality registration based on point similarity measures, which were developed for non-rigid registration tasks. The system was evaluated by The retrospective registration evaluation project. The obtained results prove that point similarity measures are also suitable for various rigid registration tasks.
منابع مشابه
Optimized co-registration method of Spinal cord MR Neuroimaging data analysis and application for generating multi-parameter maps
Introduction: The purpose of multimodal and co-registration In MR Neuroimaging is to fuse two or more sets images (T1, T2, fMRI, DTI, pMRI, …) for combining the different information into a composite correlated data set in order to visualization, re-alignment and generating transform to functional Matrix. Multimodal registration and motion correction in spinal cord MR Neuroimag...
متن کاملPoint similarity measures for non-rigid registration of multi-modal data
High-dimensional non-rigid registration of multi-modal data requires similarity measures with two important properties: multi-modality and locality. Unfortunately all commonly used multi-modal similarity measures are inherently global and cannot operate on small image regions. In this paper we propose a new class of multi-modal similarity measures, which are constructed from information of the ...
متن کاملMulti-modal non-rigid registration of volumetric medical images
Due to recent advances in image guided surgery, the availability of efficient algorithms for the fusion of preand intra-operative image data is of increasing importance. Because of the unavoidable deformations in the anatomy the classical rigid registration techniques can only be used for very limited special cases. Hierarchical subdivision techniques allow, however, to decompose non-rigid matc...
متن کاملComparative evaluation of similarity measures for the rigid registration of multi-modal head images.
Image registrations that are based on similarity measures simply adjust the parameters of an appropriate spatial transformation model until the similarity measure reaches an optimum. The numerous similarity measures that have been proposed in the past are differently sensitive to imaging modality, image content and differences in the image content, selection of the floating and target image, pa...
متن کاملAn Algorithm for 3D Registration of Multi-Modality Medical Images by Use of Voxel-Similarity-Based Measures
0. Abstract This report describes work done within a practical training at the Philips Research Laboratories / Technical Systems Hamburg in 1995. My work was concerned with the development and implementation of a completely automatic image registration algorithm that uses a voxel-similarity-based measure as matching criterion. Both singleand multi-modality 3D medical images can be processed. Fu...
متن کامل