The field of cell segmentation has evolved during the years with scientists researching upon it. The first and still one of the most predominant approaches to cell segmentation is intensity thresholding. The underlying assumption is that cells have significantly and consistently different intensities than the background. Approaches to automated threshold selection are usually based on statistical analysis of the global or local image intensities using the histogram. Rather than by their absolute intensities, cells may be segmented based on intensity derived features that can be easily detected using linear image filtering. Another popular class of filters are those from the field of mathematical morphology. An alternative approach to cell segmentation is to start from selected seed points in the image and to iteratively add connected points to form labeled regions. The final class of cell segmentation approaches consists of procedures that fit a deformable model to the image data.

Additional Metadata
Persistent URL,
Journal IEEE Signal Processing Magazine
Note no subscription
Meijering, E. (2012). Cell segmentation: 50 Years down the road [life Sciences]. IEEE Signal Processing Magazine, 29(5), 140–145. doi:10.1109/MSP.2012.2204190