DELINEATION OF ECT IMAGES USING GLOBAL CONSTRAINTS AND DYNAMIC-PROGRAMMING

A new model-based delineation algorithm is presented. It is a flexible model fitting algorithm, approaching contour detection as an optimization problem. An objective function is introduced, which depends not only on local contour features, such as the gradient in the contour points and local smoothness, but also on a global shape constraint. The latter is implemented as the similarity to the instance of a parametric shape model. The algorithm optimizes both the contour points and the parameters of the model. As a result, both global and local characteristics of the contour are determined as a compromise between photometric data and a priori knowledge. The method was applied to myocardial perfusion SPECT images, to delineate the entire left ventricle (endocardium and epicardium), including possible regions of reduced perfusion. By adapting the balance between the image data and the shape model, images with different characteristics can be processed, including Thallium-201 and MIBI scans. The objective function includes image gradients and local smoothness. The shape model consists of a series of elliptic curves. From the delineated myocardium, polar maps for count rate and volume are derived. Processing times on a typical workstation are less than three minutes. The method was tested with artificial images and is being validated on clinical data.