CellSium - Versatile Cell Simulator for Microcolony Ground Truth Generation
Keywords: cell simulation, synthetic image generation, microbial cell colonies, microfluidic live-cell imaging, training data
To train deep learning-based segmentation models, large ground truth datasets are needed. To address this need in microfluidic live-cell imaging, we developed CellSium, a flexibly configurable cell simulator built to synthesize realistic image sequences of bacterial microcolonies growing in monolayers. Simulated images are suitable for training neural networks. Generation of synthetic time-lapse videos with and without fluorescence, using programmable cell growth models, and simulation-ready 3D colony geometries suitable for computational fluid dynamics are also supported.
Publications
CellSium: versatile cell simulator for microcolony ground truth generation
Sachs C, Ruzaeva K, Seiffarth J, Wiechert W, Berkels B, Nöh K - Bioinformatics Advances - 2022
Helmholtz Imaging Projects
2020: SATOMI - Tackling the segmentation and tracking challenges of growing colonies and microbial diversity
