The Cell Tracking Challenge is an ongoing benchmarking initiative that has become a reference in cell segmentation and tracking algorithm development. Here, we present a significant number of improvements introduced in the challenge since our 2017 report. These include the creation of a new segmentation-only benchmark, the enrichment of the dataset repository with new datasets that increase its diversity and complexity, and the creation of a silver standard reference corpus based on the most competitive results, which will be of particular interest for data-hungry deep learning-based strategies. Furthermore, we present the up-to-date cell segmentation and tracking leaderboards, an in-depth analysis of the relationship between the performance of the state-of-the-art methods and the properties of the datasets and annotations, and two novel, insightful studies about the generalizability and the reusability of top-performing methods. These studies provide critical practical conclusions for both developers and users of traditional and machine learning-based cell segmentation and tracking algorithms.

No abstract

In recent years, there has been a surge in the development of methods for cell segmentation and tracking, with initiatives such as the Cell Tracking Challenge driving progress in the field. Most studies focus on regular cell population videos in which cells are segmented, cell tracks followed, and parental relationships annotated. However, DNA damage induced by genotoxic drugs or ionizing radiation provide additional abnormal cellular events of interest since they lead to aberrant behaviors such as abnormal cell divisions (i.e., resulting in a number of daughter cells different from two) and cell death. The dynamic development of those abnormal events can be followed using time lapse microscopy to be further analyzed. With this in mind, we developed an automatic mitosis classifier that categorizes small mitosis image sequences centered around a single cell as 'Normal' or 'Abnormal'. These mitosis sequences were extracted from videos of cell populations exposed to varying levels of radiation that affect the cell cycle's development. Such an approach can aid in detecting, tracking, and characterizing the behavior of the entire population. In this study, we explored several deep-learning architectures for working with 12-frame mitosis sequences. We found that a network with a ResNet50 backbone, modified to operate independently on each video frame and then combined using a Long Short-Term Memory (LSTM) layer, produced the best results in the classification (mean F1-score: 0.93 +/- 0.06). In future work, we plan to integrate the mitosis classifier in a cell segmentation and tracking pipeline to build phylogenetic trees of the entire cell population after genomic stress.