TrackRefiner: A tool for refinement of bacillus cell tracking data

Motivation Single-cell resolution time-lapse microscopy of bacterial populations is a powerful tool for assessing cellular behavior and interaction dynamics. Realizing the full potential of this approach requires accurate image analysis: segmentation of individual cell objects, tracking of persistent cells from frame to frame, and connecting of mother cells to daughters when division events occur. In particular, accurate tracking is needed to produce longitudinal datasets for analysis of interactions and features that develop through time. Tracking is challenging when populations are densely packed or when cells undergo significant motion between frames. The leading software packages struggle to provide accurate data in such cases. Result To address this problem, we present TrackRefiner, a tool for refinement of bacillus cell tracking data. This package was specifically designed to refine the tracking outputs of CellProfiler, a commonly used image processing tool. TrackRefiner is built with a modular and publicly accessible structure, making it adaptable for integration with other image processing software. To assess the package’s performance, we manually determined ground truth tracking results for eight datasets from four research groups, comprising a total of 159,349 object links. This curated dataset, the first of its kind, serves as a valuable benchmark for assessing the performance of bacillus cell tracking algorithms. For timelapses with frequent imaging, TrackRefiner consistently achieved, with one exception, over 98% detection accuracy and corrected 57-100% of tracking errors. Accuracy was reduced for images sampled at lower frequency. Availability and implementation For easy access, TrackRefiner has been published on PyPI and Anaconda. Source code and user manuals can be accessed via Github and OSF. The manually curated benchmark dataset is also posted at these sites.