Cell Segmentation in Time-Lapse Phase Contrast Data

The quantitative analysis of cellular migration has found many clinical applications as it can be used in the study of a large spectrum of biological processes such as tumor development and wound healing. These studies are commonly conducted on datasets that consists of a large number of time lapse images, a fact that rendered the application of human assisted procedures as unfeasible, especially when applied to large datasets. In the development of automatic tracking strategies the problem of robust cell segmentation plays a central role as the segmentation errors have adverse effects on the performance of the overall tracking process. While the phase contrast image data is often characterized by low contrast, changes in the morphology of the cells over time and cell agglomeration, the cell segmentation process is far from a trivial task. In this paper we present a new cell segmentation approach that maximizes the information related to the local contrast between the cells and the background in each image of the dataset. The proposed method has been evaluated on MDCK and HUVEC cellular datasets and experimental results are reported.