TrackRefiner: A tool for refinement of bacillus cell tracking data
Bibliographic record
Abstract
Abstract 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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.023 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.005 | 0.004 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.021 | 0.023 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".