A framework for automated cell tracking in phase contrast microscopic videos based on normal velocities

• We propose a new two step cell tracking framework for phase contrast microscopic videos.
• The first step uses normal velocities, while the second refinement step uses a level set approach on a Marr–Hildreth filtered image.
• We apply topology preservation techniques to a Chan–Vese model with volume constraint.
• Comparisons to manual trackings show that the cell’s centroid position is extracted accurately.
• The accuracy with respect to the difference between different manual trackings on the same data set is evaluated.

This paper introduces a novel framework for the automated tracking of cells, with a particular focus on the challenging situation of phase contrast microscopic videos. Our framework is based on a topology preserving variational segmentation approach applied to normal velocity components obtained from optical flow computations, which appears to yield robust tracking and automated extraction of cell trajectories. In order to obtain improved trackings of local shape features we discuss an additional correction step based on active contours and the image Laplacian which we optimize for an example class of transformed renal epithelial (MDCK-F) cells. We also test the framework for human melanoma cells and murine neutrophil granulocytes that were seeded on different types of extracellular matrices. The results are validated with manual tracking results.