Tracking one-in-a-million: Large-scale benchmark for microbial single-cell tracking with experiment-aware robustness metrics

TL;DR

This paper introduces the largest annotated dataset for microbial live-cell imaging, generalizes tracking metrics to include experiment parameters, and demonstrates how these parameters affect tracking performance, enabling more robust cell tracking methods.

Contribution

It provides a large-scale benchmark dataset and experiment-aware metrics for microbial cell tracking, highlighting the impact of experiment parameters on tracking accuracy.

Findings

Tracking performance declines with increased imaging intervals.

Large cell colonies challenge existing tracking methods.

Experiment parameters significantly influence tracking quality.

Abstract

Tracking the development of living cells in live-cell time-lapses reveals crucial insights into single-cell behavior and presents tremendous potential for biomedical and biotechnological applications. In microbial live-cell imaging (MLCI), a few to thousands of cells have to be detected and tracked within dozens of growing cell colonies. The challenge of tracking cells is heavily influenced by the experiment parameters, namely the imaging interval and maximal cell number. For now, tracking benchmarks are not widely available in MLCI and the effect of these parameters on the tracking performance are not yet known. Therefore, we present the largest publicly available and annotated dataset for MLCI, containing more than 1.4 million cell instances, 29k cell tracks, and 14k cell divisions. With this dataset at hand, we generalize existing tracking metrics to incorporate relevant imaging and experiment parameters into experiment-aware metrics. These metrics reveal that current cell tracking methods crucially depend on the choice of the experiment parameters, where their performance deteriorates at high imaging intervals and large cell colonies. Thus, our new benchmark quantifies the influence of experiment parameters on the tracking quality, and gives the opportunity to develop new data-driven methods that generalize across imaging and experiment parameters. The benchmark dataset is publicly available at https://zenodo.org/doi/10.5281/zenodo.7260136.