Fotios M Andreopoulos

We present a hybrid framework for segmenting structures consisting of distinct inter-connected parts. We combine the robustness of Conditional Random Fields in appearance classification with the shape constraints of geometric models and the relative part topology constraints that multi-compartment modeling provides. We demonstrate the performance of our method in cell segmentation from fluorescent microscopic images, where the compartments of interest are the cell nucleus, cytoplasm, and the negative hypothesis (background). We compare our results with the most relevant model- and appearance-based segmentation methods.

We describe a cell segmentation approach based on a probabilistic formulation of multi-compartment level set-based deformable model. We aim at the simultaneous cell partitioning into nucleus and membrane. We consider relative topology of the two distinct cell compartments, while we constrain our solution using shape prior information. Our method integrates geometric models with learning-based classification in a simple graphical model, such that it captures not only the cell compartments but also their topological relationship. We apply our framework to (static) fluorescent microscopy images, where the cultured cells are stained with calcein AM.