Abstract
Abstract
Traditional cell tracking methods focus on fully automated tracking. The quality of the generated tracks, however, is heavily influenced by factors such as cell speed and density. In complex scenarios where track correctness is essential, an efficient and reliable tool for manual track correction remains a key component of the cell tracking process. Most tracking tools that allow for such manual correction do so only as a post-processing step, using human feedback to correct one track error at a time – without improving the quality of other tracks in the dataset. This highlights the need for a more efficient track correction method that iteratively integrates human feedback into the automated tracking process.
In this paper we propose a human-in-the-loop approach to cell tracking and investigate the extent to which a tracking algorithm can learn from human input
during
the tracking process. We combine a graph representation of cell detections, Dijkstra’s shortest path algorithm, and a neural network that predicts cell displacement to generate initial track suggestions. We introduce a tool that enables human feedback on individual tracks suggested by the algorithm; this feedback is then propagated to improve subsequent track generation. Compared to the traditional approach of fully automated tracking with correction as a post-processing step, our human-in-the-loop tracking framework reduces the number of corrections required. Finally, we show how this approach can be integrated with existing state-of-the-art tracking algorithms by using pre-generated tracks as a prior, improving the quality of tracks suggested to the human annotator.
Author summary
We introduce a novel human-in-the-loop method to improve efficiency in cell tracking, crucial for immune cell motility analysis. Automated tracking methods often struggle in complex environments, while manual corrections are more accurate but very time-consuming. Our method integrates iterative human feedback directly into the tracking process using graph-based cell detection, Dijkstra’s shortest path algorithm, and neural network predictions for cell displacement. Using this method as a backbone, we created an interactive tool that efficiently incorporates user corrections of individual tracks to progressively improve the overall track quality. Testing on T cells and neutrophils in microfluidic channels demonstrates significant reductions in required corrections compared to traditional methods, offering a scalable and efficient solution suitable for high-throughput biological research.