LFCT: A Benchmark Dataset for Low-Frame-Rate Cell Tracking in Long-Term Live-Cell Microscopy

Authors

Gachloo, M., Biswas, T., Lu, X., Greene, C. M., Hargett, C. K., Simancik, K. R., Birtwistle, M. R., Iuricich, F.

Abstract

Cell tracking in time-lapse microscopy is essential for studying dynamic biological processes such as migration, proliferation, and lineage formation. Existing benchmarks primarily focus on high-frame-rate imaging, where short temporal intervals simplify correspondence between cells across consecutive frames. We present the Low Frame-rate Cell Tracking dataset (LCFT), a benchmark dataset designed specifically for evaluating cell tracking methods under low-frame-rate conditions. The dataset contains multi-day live-cell microscopy sequences from four human cell lines (MCF10A, MDA-MB-231, HEK293T, and U87), acquired at 10 and 20 magnifications using phase-contrast and fluorescence imaging (nucleus). Ground-truth annotations include cell identifications, temporal linking, lineage relationships, and mitosis events. To generate reliable annotations, automated segmentation and tracking were combined with extensive manual curation. LCFT provides a comprehensive resource for developing and benchmarking robust cell tracking algorithms capable of handling sparse temporal sampling and large inter-frame motion in long-term live-cell imaging experiments.

Preprint server: bioRxiv
The authors list and abstract were imported from bioRxiv on 04 Jun 2026.

Stats

1-terrible, 9-excellent. How would you rate this preprint? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.