SYSTEM AND METHOD FOR VASCULAR SEGMENTATION BY MONTE-CARLO SAMPLING

摘要

A method of segmenting tubular structures in digital images includes selecting (73) a point in an image of a tubular object to be segmented, defining (74) an initial state of the selected point, initializing (75) measurement weights, a conditional probability distribution and a prior probability distribution of a feature space of the initial state, sampling (76) the feature space from the prior probability distribution, estimating (77) a posterior probability distribution by summing sample measurements weighted by the measurement weights, and segmenting (79) a cross section of the tubular object from the posterior probability distribution.