Automated registration of live imaging stacks of Arabidopsis

For actively developing tissues, a computational platform capable of automatically registering, segmenting and tracking cells is very critical to obtaining high-throughput and quantitative measurements of a range of cell behaviors, and can lead to a better understanding of the underlying dynamics of morphogenesis. In this work, we present an automated landmark-based registration method to register shoot apical meristem of Arabidopsis Thaliana images obtained through the Confocal Laser Scanning Microscopy technique. The proposed landmark-based registration method uses local graph-based approach to automatically find corresponding landmark pairs. The registration algorithm combined with an existing tracking method is tested on multiple datasets and it significantly improves the accuracy of cell lineages and division statistics.