Nonrigid Object Segmentation: Application to Four-Chamber Heart Segmentation

摘要: In this chapter, we present an automatic object detection and segmentation framework based on Marginal Space Learning (MSL), which integrates the components described in previous chapters into a complete system. addition, simple efficient methods mesh resampling are developed to establish point correspondence, required train mean shape for initialization build statistical model boundary delineation. We use four-chamber heart cardiac Computed Tomography (CT) data as example illustrate framework. Most of technologies chamber generic, therefore can be applied directly or adapted easily segment other anatomies different imaging modalities.