Cardiac MR image segmentation using deformable models

Describes efficient and robust deformable model based techniques for segmentation of ventricular boundaries in cardiac MR images. Starting with a user specified approximate boundary or an interior point of the left ventricle for one ED slice, the authors' algorithms generate contours for inner and outer walls, and automatically propagate them to other slices in the ED phase (spatial propagation) and to slices in all the phases (temporal propagation) of the cardiac study. The algorithms are based on steepest descent as well as dynamic programming strategies integrated via multiscale analysis. The ventricular boundaries are used to construct a 3-D model for visualization and to compute volume based diagnostic quantities. The algorithms have been incorporated into a user interface which can load, sort, visualize, and analyze a cardiac study an less than 10 minutes. The system has been tested on a dozen volunteers and patients (1000+ images) with excellent results.<<ETX>>