An Objective Comparison of Cell Tracking Algorithms

By V. Ulman, Martin Maška, Klas E. G. Magnusson, Olaf Ronneberger, Carsten Haubold, N. Harder, P. Matula, P. Matula, David Svoboda, M. Radojević and 29 more. 2017

542 citations recorded by the source corpus.

We present a combined report on the results of three editions of the Cell Tracking Challenge, an ongoing initiative aimed at promoting the development and objective evaluation of cell segmentation and tracking algorithms. With 21 participating algorithms and a data repository consisting of 13 data sets from various microscopy modalities, the challenge displays today's state-of-the-art methodology in the field. We analyzed the challenge results using performance measures for segmentation and tracking that rank all participating methods. We also analyzed the performance of all of the algorithms in terms of biological measures and practical usability. Although some methods scored high in all technical aspects, none obtained fully correct solutions. We found that methods that either take prior information into account using learning strategies or analyze cells in a global spatiotemporal video context performed better than other methods under the segmentation and tracking scenarios included in the challenge.

Subfields: Biomedical Engineering, Biophysics, Molecular Biology, Evaluation & Benchmarks, Computational Biology & Bioinformatics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Biophysics

In Molecular Biology

In Evaluation & Benchmarks

In Computational Biology & Bioinformatics

Citations in the corpus

Cell Detection with Star-convex Polygons (2018, background): “Examples include high-content screens of variations in cell phenotypes [2], or the identification of developmental lineages of dividing cells [1,17].”
Metrics Reloaded: Recommendations for image analysis validation (2022, background): “48) • Cell nuclei instance segmentation in time-lapse light microscopy with a subsequent goal of cell tracking [87] • MS lesion segmentation in multi-modal brain MRI images [30, 53]”
Star-convex Polyhedra for 3D Object Detection and Segmentation in Microscopy (2019, background): “Detection and segmentation of cell nuclei in volumetric (3D) fluorescence microscopy images is a ubiquitous problem in developmental biology and often constitutes the first step when studying cellular expression patterns, or when tracing cell lineages in developing organisms [17, 22].”
Evaluation of Deep Learning Strategies for Nucleus Segmentation in Fluorescence Images (2018, background): “Also, a recent cell tracking challenge analysis noted that thresholding approaches are still the top solutions for segmenting cells (19); their ranking score is also the Jaccard index.”
TrackMate 7: integrating state-of-the-art segmentation algorithms into tracking pipelines (2022, methodology): “Confocal images of Arabidopsis thaliana floral meristem 44 and light-sheet images of a developing Drosophila melanogaster embryo 45,46 were automatically segmented using cellpose (Cyto2 model) implemented in the ZeroCostDL4Mic platform 12,15 .”