The article introduces OrganoidTracker 2.0, a novel cell-tracking algorithm designed to overcome the limitations of existing methods by providing accurate error prediction for cell trajectories. This advancement combines neural networks to estimate link and division probabilities with concepts from statistical physics (specifically, marginalization) to incorporate contextual information from surrounding cells, resulting in context-aware error rates. These error probabilities function like P values, enabling researchers to assess the statistical significance of tracking results for lineage features. The new method significantly reduces the need for manual curation by focusing correction efforts only on low-confidence links or allows for fully automated analysis by filtering out uncertain track segments, accelerating high-throughput screening of complex biological systems like organoids.
References:
