Machine learning enhanced cell tracking

Quantifying cell biology in space and time requires computational methods to detect cells, measure their properties, assemble these into meaningful trajectories. In this aspect, machine learning (ML) is having a transformational effect on bioimage analysis, now enabling robust detection multidimensional image data. However, the task of tracking, or constructing accurate multi-generational lineages from imaging data, remains an open challenge. Most tracking algorithms are largely based our prior knowledge behaviors, as such, difficult generalize new unseen types datasets. Here, we propose that ML provides framework learn aspects behavior using be learned. We suggest advances representation learning, datasets, metrics, for evaluating solutions can all form part end-to-end ML-enhanced pipeline. These developments will lead way used understand complex, time-evolving biological systems.