CellSium – Versatile Cell Simulator for Microcolony Ground Truth Generation

Abstract

To address the need for ground truth data for deep learning based segmentation algorithms in microfluidic live-cell imaging, we present CellSium, a cell simulator primarily aimed at synthesizing realistic image sequences of bacterial microcolonies suitable for training neural networks. Availability and Implementation: CellSium is free and open source software under the BSD license, implemented in Python, available at https://github.com/modsim/cellsium (DOI: 10.5281/zenodo.6193033), along with documentation, usage examples and Docker images.

ObiWan-Microbi: OMERO-based integrated workflow for annotating microbes in the cloud

“…The combination of the three components forms the platform ObiWan-Microbi , used to segment microbial organisms including E. coli, C. glutamicum and B. subtilis (SI S.3). For semi-automated segmentation, four pre-trained DLS algorithms are provided out-of-the-box and accessible in SegUI including Cellpose (Stringer et al ., 2021), Omnipose (Cutler et al ., 2021), Mask R-CNN trained on simulated image data (Sachs et al ., 2022) and Yolov5 for general object detection in images. Using semi-automated segmentation, an annotation speed of more than 200 cells/minute was achieved (SI S.4).…”