Perfect snap for bioimage analysis

In recent years, there has been an increasing interest in getting a proper quantitative understanding of cellular and molecular processes [1], [2]. One of the major challenges of current biomedical research is to characterize not only the spatial organization of these complex systems but also their spatiotemporal relationships [3], [4]. Microscopy has matured to the point that it enables sensitive time-lapse imaging of cells in vivo and even of single molecules [5], [6]. Making microscopy more quantitative brings important scientific benefits in the form of improved performance and reproducibility. This has been fostered by the development of technological achievements such as high-throughput microscopy. A direct consequence is that the size and complexity ofimage data are increasing. Time-lapse experiments commonly generate hundreds to thousands of images, each containing hundreds of objects to be analyzed [7].

These data often cannot be analyzed manually because the manpower required would be too extensive, which calls for automated methods for the analysis of biomedical images. Such computerized extraction of quantitative information out of the rapidly expanding amount of acquired data remains a major challenge. The development of the related algorithms is nontrivial and is one of the most active fronts in the new field of bioimage informatics [8]?[11]. Segmenting thousands of individual biological objects and tracking them over time is remarkably difficult. A typical algorithm will need to be tuned to theimaging modality and will have to cope with the fact that cells can be tightly packed and may appear in various configurations, making them difficult to segregate