Method for robust scale-space analysis of 3D local structures in medical images

摘要

A method for determining the location, shape and orientation of a tumor in a medical image includes finding a plurality of spatial extrema mu of a D-dimensional spatial signal f for a set of bandwidths H by performing mean shift-based gradient-ascent iterations for a set of bandwidths H and then determining a D-dimensional spread and orientation of the signal about each extrema mu by estimating a covariance Sigma of the signal f for each extrema mu. The optimal estimate of mu and Sigma is determined by performing a Jensen-Shannon divergence on the full set of mu and Sigma.