The hidden messages of cell trajectories: how deep learning and time-lapse microscopy can improve the understanding of the biological systems.

The synergic integration of microfluidic devices, time-lapse microscopy and image analysis has attracted attention to the exploitation of the carried information content. Extracted cell motility descriptors may be considered a useful source of information to quantify and to discern relevant biological differences among diverse counterparts of the same scenario. In this talk, the potentialities of data analysis and in particular of the deep learning techniques will be highlighted in different experimental scenarios, such as for example in organ on chip, where the visualization of reconstituted complex biological processes such as multi-cell type migration and cell-cell interactions are possible.