Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

A growing number of screening applications require the automated monitoring of cell populations including cell segmentation, tracking, and measurement. We present general methods for cell segmentation and tracking that exploit the spatiotemporal nature of the task to constrain segmentation. The images are de-noised and segmented by combining wavelet coefficients at various levels, thus enabling extraction of cells in images with low contrast-to-noise ratios. Each track of clustered cells resulting from association of nearby cells in the spatio-temporal volume is then split into individual cells by evolving sets of contours from other slices. The hypothesis whether to split or merge objects making up the cluster is tested using learned features trained from single track cells. Due to the difficult nature of generating ground truth, we also present a framework for edit-based validation whereby the user corrects the edits made by the automatic system rather than generating the truth from scratch. The results show the promise of the approach and demonstrate the ability of the algorithms to provide meaningful measurements of cell response to drug treatment in low-dose Hoechst-stained cells. ©2008 IEEE.

Original publication




Journal article


2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI

Publication Date



376 - 379