Scientific publications
An objective comparison of cell-tracking algorithms. Scientific Publication
Vladimír Ulman 1 , Martin Maška 1 , Klas E G Magnusson 2 , Olaf Ronneberger 3 , Carsten Haubold 4 , Nathalie Harder 5 , Pavel Matula 1 , Petr Matula 1 , David Svoboda 1 , Miroslav Radojevic 6 , Ihor Smal 6 , Karl Rohr 5 , Joakim Jaldén 2 , Helen M Blau 7 , Oleh Dzyubachyk 8 , Boudewijn Lelieveldt 8 9 , Pengdong Xiao 10 , Yuexiang Li 11 , Siu-Yeung Cho 12 , Alexandre C Dufour 13 , Jean-Christophe Olivo-Marin 13 , Constantino C Reyes-Aldasoro 14 , Jose A Solis-Lemus 14 , Robert Bensch 3 , Thomas Brox 3 , Johannes Stegmaier 15 , Ralf Mikut 15 , Steffen Wolf 4 , Fred A Hamprecht 4 , Tiago Esteves 16 17 , Pedro Quelhas 16 , Ömer Demirel 18 , Lars Malmström 18 , Florian Jug 19 , Pavel Tomancak 19 , Erik Meijering 6 , Arrate Muñoz-Barrutia 20 21 , Michal Kozubek 1 , Carlos Ortiz-de-Solorzano 22 23
Abstract
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.
CITATION Nat Methods. 2017 Dec;14(12):1141-1152. doi: 10.1038/nmeth.4473. Epub 2017 Oct 30
![](/.resources/ModuloCUN/resources/img/publicaciones/icono-destacado-investigadores.png)