EllipTrack: A Global-Local Cell-Tracking Pipeline for 2D Fluorescence Time-Lapse Microscopy

• Published in: Cell reports (Cambridge) Vol. 32; no. 5; p. 107984
• Main Authors: Tian, Chengzhe, Yang, Chen, Spencer, Sabrina L.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 04.08.2020; Elsevier
• Subjects: Algorithms; automated cell tracking; CDK2 activity; cell heterogeneity; Cell Line; Cell Lineage; cell lineage tree; Cell Movement; cell proliferation; Cell Tracking; Humans; image processing; large-scale movies; Microscopy, Fluorescence; single-cell dynamics; single-cell tracking; Time Factors; Time-Lapse Imaging; image processing; cell heterogeneity; single-cell tracking; cell proliferation; cell lineage tree; time-lapse imaging; large-scale movies; CDK2 activity; single-cell dynamics; automated cell tracking
• ISSN: 2211-1247; 2211-1247
• DOI: 10.1016/j.celrep.2020.107984

Time-lapse microscopy provides an unprecedented opportunity to monitor single-cell dynamics. However, tracking cells for long periods remains a technical challenge, especially for multi-day, large-scale movies with rapid cell migration, high cell density, and drug treatments that alter cell morphology/behavior. Here, we present EllipTrack, a global-local cell-tracking pipeline optimized for tracking such movies. EllipTrack first implements a global track-linking algorithm to construct tracks that maximize the probability of cell lineages. Tracking mistakes are then corrected with a local track-correction module in which tracks generated by the global algorithm are systematically examined and amended if a more probable alternative can be found. Through benchmarking, we show that EllipTrack outperforms state-of-the-art cell trackers and generates nearly error-free cell lineages for multiple large-scale movies. In addition, EllipTrack can adapt to time- and cell-density-dependent changes in cell migration speeds and requires minimal training datasets. EllipTrack is available at https://github.com/tianchengzhe/EllipTrack. [Display omitted] •EllipTrack applies ellipse fitting to separate partially overlapped cells•EllipTrack utilizes a global-local hybrid algorithm to map cells between frames•EllipTrack can track cell lineages in long-term movies with minimal errors•EllipTrack accelerates discovery in cell biological and pharmacological research Tian et al. present a cell-tracking pipeline called EllipTrack that is optimized for modern, multi-day, high-throughput 2D fluorescent time-lapse movies. EllipTrack produces nearly error-free cell lineages for the cell lines tested and represents an improvement over existing tools for hard-to-track cells such as cancer cells.