Skip to main content

Data from: The CellPhe toolkit for cell phenotyping using time-lapse imaging and pattern recognition


Wiggins, Laura (2023), Data from: The CellPhe toolkit for cell phenotyping using time-lapse imaging and pattern recognition, Dryad, Dataset,


With phenotypic heterogeneity in whole cell populations widely recognised, the demand for quantitative and temporal analysis approaches to characterise single cell morphology and dynamics has increased. We present CellPhe, a pattern recognition toolkit for the unbiased characterisation of cellular phenotypes within time-lapse videos. CellPhe imports tracking information from multiple segmentation and tracking algorithms to provide automated cell phenotyping from different imaging modalities, including fluorescence. To maximise data quality for downstream analysis, our toolkit includes automated recognition and removal of erroneous cell boundaries induced by inaccurate tracking and segmentation. We provide an extensive list of features extracted from individual cell time series, with custom feature selection to identify variables that provide the greatest discrimination for the analysis in question. Using ensemble classification for accurate prediction of cellular phenotype and clustering algorithms for the characterisation of heterogeneous subsets, we validate and prove adaptability using different cell types and experimental conditions.


Cells were placed onto the Phasefocus Livecyte 2 (Phasefocus Limited, Sheffield, UK) and incubated for 30 minutes prior to image acquisition to allow for temperature equilibration. One 500μm x 500μm field of view per well was imaged to capture as many cells as possible. Selected wells were imaged in parallel for 48 hours at 20x magnification with 6-minute intervals between frames, resulting in full time-lapses of 481 frames per imaged well. Phase and fluorescence images were acquired in parallel for each well. For phase images, Phasefocus’ Cell Analysis Toolbox® software was utilised for cell segmentation, cell tracking, and data exportation as feature tables. Segmentation thresholds were optimised for a range of image processing techniques such as rolling ball algorithm to remove background noise, image smoothing for cell edge detection, and local pixel maxima detection to identify seed points for final consolidation.

For fluorescence images, the TrackMate-Cellpose ImageJ plugin was used for cell segmentation and tracking. Cells were segmented using Cellpose’s pre-trained cytoplasm model and image contrast was enhanced prior to segmentation to improve the detection of cell boundaries. Once complete, TrackMate feature tables and individual cell ROIs were exported from ImageJ v2.9.0-153t. Prior to use with CellPhe, it was necessary to interpolate TrackMate-Cellpose ROIs to obtain a complete list of cell boundary coordinates. Interpolation of ROIs was performed using a custom ImageJ macro.

Usage notes

ROI files can be opened with ImageJ. Image .tif files can be opened with any imaging software including ImageJ. Feature tables are provided as comma separated files and can be opened with Excel, for example.


Biotechnology and Biological Sciences Research Council, Award: BB/S507416/1