Extraction and Segmentation of Structures in Image Sequences

The analysis of imaged anatomical or biological structures and of their dynamics is an important task in terms of application and therefore of diagnostics. Such an analysis involves in the first place the extraction of these structures from the acquired images according to a given modality, which corresponds, in image processing terminology, to a segmentation phase. Segmentation methods are conventionally qualified as “region-based approaches” or “contour-based approaches”. The two types of information – image properties and a priori constraints – must be integrated into a common formalism, itself numerically implemented as an algorithm. This chapter details more particularly two deformable model approaches: deformable templates (DTs) and variational active contours. It presents the implementation of variational active contour methods in cardiac imaging, describing the choices carried out. The chapter focuses on two examples of active contours, applied to the segmentation of cardiac ultrasound images in 2D and 3D ultrasound echography