US 7,079,674 B2 · Variational approach for the segmentation of the left ventricle in MR cardiac images

Abstract

A system and method for segmenting cardiac images and, in particular, segmenting the left ventricle of the heart using a contour propagation model that integrates visual information and anatomical constraints. The visual information comprises a gradient vector flow-based boundary component and a region component that separates the cardiac contours/regions according to their global intensity properties that reflect the different tissue properties. The anatomical constraints couple the propagation of cardiac contours according to their relative distance. The propagation model comprises a weighted integration of a boundary segmentation model, a region model and coupling function.

Claims24

Dependent claims

A method for segmenting a cardiac image, comprising the steps of:

receiving a cardiac image;
determining boundary information for at least two contours in the cardiac image using a gradient vector flow boundary method;
determining region information to separate regions in the cardiac image according to their global intensity parameters;
and
applying a propagation model that combines the boundary and region information to propagate the at least two contours to respective target boundaries in the cardiac image while applying an anatomical constraint to couple the propagation of the at least two contours to their respective target boundaries in the cardiac image according to their relative distance between the at least two contours in which said their relative distance can be calculated with time and space.

2 more elements

Dependencies are inferred from the claim text.

Variational approach for the segmentation of the left ventricle in MR cardiac images

Life of this patent

Variational approach for the segmentation of the left ventricle in MR cardiac images

Life of this patent

Abstract

Claims24