Phase contrast time-lapse microscopy datasets with automated and manual cell tracking annotations.

Area of Science:

• Cell Biology
• Biomedical Imaging
• Computational Biology

Background:

• Phase contrast time-lapse microscopy enables non-destructive, high-volume data generation for cell behavior quantification.
• Understanding individual and population cell dynamics is crucial for biomedical research.
• Development of advanced algorithms for cell tracking and analysis is an ongoing need.

Purpose of the Study:

• To create a comprehensive, validated dataset for guiding the development of computer-aided cell tracking and analysis algorithms.
• To provide a benchmark dataset for evaluating cell tracking algorithm performance.
• To facilitate deeper understanding of cell dynamics under various culture conditions.

Main Methods:

• Generated 48 time-lapse image sequences of C2C12 myoblast cells over approximately 3.5 days.
• Cultured cells under four distinct media conditions: control, fibroblast growth factor 2 (FGF2), bone morphogenetic protein 2 (BMP2), and combined FGF2+BMP2.
• Created and manually curated ground truths for tracking parent cells and their descendants, ensuring data reliability.

Main Results:

• A comprehensive dataset with validated ground truths for cell tracking was successfully generated.
• The dataset captures C2C12 myoblast cell behavior across different growth factor conditions.
• The data includes tracking information for multiple parent cells and their progeny.

Conclusions:

• The validated dataset serves as a valuable resource for advancing computer-aided cell tracking algorithms.
• This benchmark dataset will accelerate progress in quantitative cell behavior analysis.
• The findings support enhanced understanding of cell dynamics in biomedical research.