Microscopic imaging of living cells, automatic tracking and the description of the kinetics of the cells for image- mining

Live-cell assays are used to study the dynamic functional cellular processes in High-Content Screening (HCA) of drug discovery processes or in computational biology experiments. The large amount of image data created during the screening requires automatic image-analysis procedures that can describe these dynamic processes. One class of tasks in this application is the tracking of cells. We describe in this paper a fast and robust cell tracking algorithm applied to High-Content Screening in drug discovery or computational biology experiments. We developed a similarity-based tracking algorithm that can track the cells without an initialization phase of the parameters of the tracker. The similarity-based detection algorithm is robust enough to find similar cells although small changes in the cell morphology have been occurred. The cell tracking algorithm can track normal cells as well as mitotic cells by classifying the cells based on our previously developed texture classifier. Results for the cell path are given on a test series from a real drug discovery process. We present the path of the cell and the low-level features that describe the path of the cell. This information can be used for further image mining of high-level descriptions of the kinetics of the cells. Introduction The utilization of dynamic High-Content Analysis approaches during preclinical drug research will permit to gain a more specified and detailed insight into complex sub-cellular processes by the use of living cell culture systems. This will effectively support future drug discoveries leading to a great outcome of highly specific and most effective drugs that come along with a well improved compliance. Livecell assays are therefore used to study the dynamic functional cellular processes in High-Content Screening of drug-discovery processes or in computational biology experiments. The large amount of image data created during the screening requires automatic image analysis procedures that can automatically describe these dynamic processes. One class of tasks in this application is the tracking of the cells, the description of the events and the changes in the cell characteristics, so that the desired information can be extracted from it based on datamining and knowledge-discovery methods. There are several tracking approaches known that track a cell by detection in each single frame and associate the detected cells in each frame by optimizing a certain probabilistic function [1]. Other approaches track cells by model evolution [2]. This approach seems to be able to handle touching and overlapping cells well but is computational expensive [3]. We propose in this paper a similarity-based approach for motion detection of cells that is robust and fast enough to be used in real world applications. The algorithm is based on a specific similarity measure that can detect cells although small changes in morphology appeared. The algorithm can track normal cells as well as mitotic cells. In Section 2 we review related work. The material is given in Section 3 and the basic constraints of the algorithm resulting from microscopic life-cell images are explained. The algorithm is described in Section 4. Results are given on a test series from a real drug-discovery process in Section 5. The features that describe the extracted path are explained in Section 6. Finally, we give conclusions in Section 7. Related work Li et al. [4] proposes a system that combines bottom-up and topdown image analysis by integrating multiple collaborative modules, which exploit a fast geometric active contour tracker in conjunction with adaptive interacting multiple models motion filtering and spatiotemporal trajectory optimization. The system needs ten frames to initialize its parameters. If the numbers of frames in a video are high this is expectable otherwise it is not. Cells that have not been recognized in the initial frame are not considered anymore. The system cannot track new appearing cells and it has a high computation time. The evaluation of the categorical analysis shows that it has a high rate of false detection of mitosis and new cells. Swapping of cell identities occurred mostly in densely populated regions, where the boundaries between cells are highly blurred. This arises the question why to use snakes for tracking the cells. In Sacan et al. [5], a software package is described for cell tracking and motility analysis based on active contours. Since snakes relies on the assumption that the movement and deformation of the tracked *Correspondence to: Petra Perner, Institute of Computer Vision and applied Computer Sciences, Leipzig, IBaI, Germany, E-mail: TUpperner@ibai-institut. deUT, Website: www.ibai-institut.deUT