Abstract: A technique for analyzing images for a feature of interest includes generating gradients for a characteristic of an image, such as pixel intensity value, initiating a candidate boundary, and evolving the candidate boundary to the feature boundary. The gradients may be calculated at the outset and referred to through iterative steps in expansion of the candidate boundary to improve the computational efficiency of the processing. The candidate boundary is evolved, either inwardly or outwardly, by reference to mean curvature-weighted normals, resulting in very rapid convergence on the feature. The evolution naturally stops at the feature. The gradients may be diffused or smoothed to improve tolerance to artifacts and noise, while preserving original image definition and resolution. In a cardiac application, the endocardial and myocardial boundaries are analyzed and used to generate composite images, calculate ejection fractions and so forth.

Abstract: A technique for analyzing images for a feature of interest includes generating gradients for a characteristic of an image, such as pixel intensity value, initiating a candidate boundary, and evolving the candidate boundary to the feature boundary. The gradients may be calculated at the outset and referred to through iterative steps in expansion of the candidate boundary to improve the computational efficiency of the processing. The candidate boundary is evolved, either inwardly or outwardly, by reference to mean curvature-weighted normals, resulting in very rapid convergence on the feature. The evolution naturally stops at the feature. The gradients may be diffused or smoothed to improve tolerance to artifacts and noise, while preserving original image definition and resolution. In a cardiac application, the endocardial and myocardial boundaries are analyzed and used to generate composite images, calculate ejection fractions and so forth.