Analysis of segmentation and tracking algorithms for time lapse microscopic progenitor cell images

In this paper we analyze the neural progenitor cells in a time-lapse sequence to find position, shape, motility and ancestor of each cell in the frame. Because of the complex nature of cells, the ability to distinguish a cell from the background of an image for automatic quantification remains a challenging task. By using morphological techniques we are able to make a better selection of blob-like objects. The cells are detected using h-maxima transform and the cell contours are selected using watershed algorithm. The cells are tracked in an image sequence using multiple matching object method based on modified Mahalanobis distance algorithm. The proposed method has been successfully applied to a large number of images and showed promising results for tracking cells between consecutive images.