Reliably Tracking Partially Overlapping Neural Stem Cells in DIC Microscopy Image Sequences

Automated tracking of individual cells in populations aims at obtaining fine-grained measurements of cell behaviors, including migration (translocation), mitosis (division), apoptosis (death), shape deformation of individual cells, and their interactions among cells. Such detailed analysis of cell behaviors requires the capabilities to reliably track cells that may sometimes partially overlap, forming cell clusters, and to distinguish cellular mitosis/fusion from split and merge of cell clusters. Existing cell tracking algorithms are short of these capabilities. In this paper, we propose a cell tracking method based on partial contour matching that is capable of robustly tracking partially overlapping cells, while maintaining the identity information of individual cells throughout the process from their initial contact to eventual separation. The method has been applied to a task of tracking human central nervous system (CNS) stem cells in differential interference contrast (DIC) microscopy image sequences, and has achieved 97% tracking accuracy.