Title :
Automatic tracking of SPAMM grid in MR images
Author :
Kumar, Senthil ; Goldgof, Dmitry
Author_Institution :
Dept. of Comput. Sci. & Eng., Univ. of South Florida, FL, USA
Abstract :
A novel approach to the automatic tracking of the SPAMM (spatial modulation of magnetization) grid in cardiac MR (magnetic resonance) images is presented. The tracking is used to extract grid points from MR images and to establish correspondences between grid points belonging to images taken at consecutive frames. Such correspondences are useful for motion and deformation estimation. Spatio-temporal tracking of the SPAMM grid is achieved by using snakes-active contour models with an associated energy functional. A minimizing strategy suitable for tracking the SPAMM grid is presented. By continuously minimizing their energy functionals, their snakes lock on to and follow the 2-D motion and deformation of the grid. Point correspondences are automatically made available. No explicit matching is necessary
Keywords :
biomedical NMR; cardiology; magnetisation; medical image processing; active contour models; automatic grid tracking; cardiac MR; deformation estimation; diagnostic imaging; energy functional; grid points correspondences; magnetic resonance imaging; magnetization spatial modulation; spatio-temporal tracking; Active contours; Biomedical engineering; Biomedical imaging; Computer science; Computer vision; Feature extraction; Image motion analysis; Magnetization; Motion estimation; Tracking;
Conference_Titel :
Nuclear Science Symposium and Medical Imaging Conference, 1992., Conference Record of the 1992 IEEE
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-0884-0
DOI :
10.1109/NSSMIC.1992.301524