Regional Appearance Modeling for Model-Based Image Segmentation

This thesis presents a novel appearance prior for model-based image segmentation. This appearance prior, denoted as Multimodal Prior Appearance Model (MPAM), is built upon an EM clustering of intensity profiles with model order selection to automatically select the number of profile classes. Unlike classical PCA-based approaches, the clustering is considered as regional because intensity profiles are classified for each mesh and not for each vertex. Comparative results on liver profiles from CT images show that MPAM outperforms PCA-based appearance models. Finally, methods for the analysis of lower limb structures from MR images are presented. A first part deals with the creation of subject-specific models for kinematic simulations of the lower limbs. In a second part, the performance of statistical models is compared in the context of lower limb bone segmentation when only a small number of datasets is available for training.