Segmenting and tracking moving cells in time-lapse video sequences is a challenging task, required for many applications in both scientific and industrial settings. Properly characterizing how cells change shapes and move as they interact with their surrounding environment is key to understanding the mechanobiology of cell migration and its multiple implications in both normal tissue development and many diseases. In this challenge, we objectively compare and evaluate state-of-the-art whole-cell and nucleus segmentation and tracking methods using both real (2D and 3D) time-lapse microscopy videos of cells and nuclei, along with computer-generated (2D and 3D) video sequences simulating whole cells and nuclei moving in realistic environments.
The first edition of Cell Tracking Challenge was held under the auspices of the IEEE International Symposium on Biomedical Imaging (ISBI) in San Francisco in April 2013. The second and third editions were hosted by ISBI 2014 in Beijing and ISBI 2015 in New York. The report on the three challenge editions was published in Nature Methods. Since February 21st, 2017 the challenge is open for online submissions that are monthly evaluated and ranked.
One Challenge, Two Benchmarks: In October 2018 a new “spin-off” time-lapse cell segmentation benchmark was launched to address numerous requests for benchmarking only cell segmentation methods. This activity was initially hosted by ISBI 2019 in Venice in April 2019. After this launching event, both the Cell Tracking Benchmark and the Cell Segmentation Benchmark continue running online and share the same datasets. To take part in one or both of these benchmarks, you can freely download the Datasets but you need to register to submit your results for evaluation.
5th Challenge Edition at ISBI 2020: The fifth challenge edition is being organized as part of ISBI 2020, taking place in Iowa City in April 2020. In this edition, the scope of the challenge has been broadened by adding two bright-field microscopy datasets and one new fully 3D+time dataset of developing Tribolium Castaneum embryo. Furthermore, silver reference segmentation annotations have been released for the training videos of nine existing datasets to facilitate the tuning of competing methods. The submissions will be evaluated and announced at the corresponding ISBI 2020 challenge workshop according to the ISBI 2020 challenge schedule, with a paper that reports on the results collected since the third edition being published in a top-tier journal afterward.
Please note that participants, not interested in the fifth challenge edition, can submit their results for evaluation at any time. However, in the case of analyzing any of the BF-C2DL-HSC, BF-C2DL-MuSC, and Fluo-N3DL-TRIF datasets or exploiting the silver reference segmentation annotations, the scores achieved will be provided after ISBI 2020.