期刊名称：Computational and Structural Biotechnology Journal
印刷版ISSN：2001-0370
出版年度：2012
卷号：1
期号：2
DOI：10.5936/csbj.201207004
语种：
出版社：Computational and Structural Biotechnology Journal
摘要：Motility studies of cells often rely on computer software that analyzes time-lapse recorded movies and establishes cell trajectories fully automatically. This raises the question of reproducibility of results, since different programs could yield significantly different results of such automated analysis. The fact that the segmentation routines of such programs are often challenged by nanostructured surfaces makes the question more pertinent. Here we illustrate how it is possible to track cells on bright field microscopy images with image analysis routines implemented in an open-source cell tracking program, PACT ( P rogram for A utomated C ell T racking). We compare the automated motility analysis of three cell tracking programs, PACT, Autozell, and TLA, using the same movies as input for all three programs. We find that different programs track overlapping, but different subsets of cells due to different segmentation methods. Unfortunately, population averages based on such different cell populations, differ significantly in some cases. Thus, results obtained with one software package are not necessarily reproducible by other software.
