A method for segmenting cardiac magnetic resonance images using active contours

This paper presents a method for segmenting the endocardium and epicardium of the left ventricle in cardiac magnetic resonance images using active contours. It first proposes an external force for active contours, which is called as generalized normally biased GVF (GNBGVF). As an improvement on gradient vector flow, the GNBGVF external force keeps the diffusion along the tangential direction of the isophotes and biases that along the normal direction simultaneously. Consequently, it possesses the advantages of enlarged capture range, noise resistance and weak boundary preserving. Considering that the left ventricle is roughly a circle, a shape constraint based on circle is adopted for segmentation of the endocardium, which conquers the unexpected local minimum stemming form image inhomogeneity and papillary muscle. As to segmentation of the epicardium, the gradient vector components are reconfigured to generate the external force field, namely, taking the final contour for endocardium as initialization. This external force can overcome the demerits of the original GVF and NGVF forces and maintain the epicardium boundaries even if the contrast between the myocardium and neighbor organs is very low. With these strategies, the Snake contour is reactivated to locate the epicardium automatically and accurately. The results show its effectiveness.