Motivation: In developmental biology, quantitative tools to extract features from fluorescence microscopy images are becoming essential to characterize organ morphogenesis at the cellular level. However, automated image analysis in this context is a challenging task, owing to perturbations induced by the acquisition process, especially in organisms where the tissue is dense and opaque.
Results: We propose an automated framework for the segmentation of 3D microscopy images of highly cluttered environments such as developing tissues. The approach is based on a partial differential equation framework that jointly takes advantage of the nuclear and cellular membrane information to enable accurate extraction of nuclei and cells in dense tissues. This framework has been used to study the developing mouse heart, allowing the extraction of quantitative information such as the cell cycle duration; the method also provides qualitative information on cell division and cell polarity through the creation of 3D orientation maps that provide novel insight into tissue organization during organogenesis.