Author:

Keywords:

PSI_MIC

Abstract:

Image segmentation is the process of partitioning a digital image into r egions originating from different objects in the scene. The segmentation of anatomical objects is indispensable for the analysis of medical imag es. It enables the assessment of anatomical measurements and it is a pos sible means towards diagnosis, therapy planning and visualization. \\ As anatomical objects appear in medical images with high variability, th e construction of a model that incorporates prior knowledge about these objects is essential during segmentation. A popular and very effective a pproach is to represent the shape as a set of landmark points, and learn the shape variations from a set of example shapes. Whereas conventional methods build a global point distribution model that considers correlat ions between all points in the set, this thesis presents a localized mod el that captures statistical prior shape information as a concatenation of multiple local shape models into a deformable graph configuration. Th e method has a strong theoretical basis as the model construction and mo del fitting are formulated from a probability point of view. Its validit y and highly generic nature are illustrated for the segmentation of mult iple anatomical structures, both from two- as three-dimensional images. A comparison to methods that use a global model shows that the presented approach, thanks to its localized nature, is able to fit more accuratel y to unseen objects.