Abstract
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.