Motion Estimation in Gated Cardiac Emission Tomography by Optical Flow Techniques

The purpose of this work was to develop and test a new motion estimation algorithm for gated cardiac emission tomography that is designed to be more accurate than conventional methods particularly for relatively large frame-to-frame displacements. The proposed method consists of a sequential application of the conventional Horn-Schunck algorithm to quadratic approximations of the standard, non-rigid frame registration model (with a quadratic smoothing term). The method was tested on frames reconstructed from noisy and noise-free data generated from the 4D cardiac phantom. Our simulations indicated that the method improved motion estimation accuracy relative to the Horn-Schunck method, with increased improvement at lower noise levels.