Validation methods for cell cycle analysis algorithms in confocal fluorescence images

Automated analysis of live cells over extended time periods requires both novel assays and automated image analysis algorithms. Among other applications, this is necessary for studying the effect of inhibitor compounds that are designed to block the replication of cancerous cells. Due to their toxicity, fluorescent dyes that bind to the nuclear DNA cannot be used to mark nuclei, and traditional non-toxic nuclear markers do not yield information about the cell cycle phases. Instead, a non-toxic cell cycle phase marker can be used. We previously described a set of image analysis methods designed to automatically segment nuclei in such 2D time-lapse images. While the methods show promise, it is necessary to provide a validation framework for these methods. This paper introduces methods for validating the various stages of the algorithm in order to demonstrate their viability for automatic cell cycle analysis. © 2006 IEEE.