Cell-ACDC: a user-friendly toolset embedding state-of-the-art neural networks for segmentation, tracking and cell cycle annotations of live-cell imaging data

Abstract

Live-cell imaging is a powerful tool to study dynamic cellular processes on the level of single cells with quantitative detail. Microfluidics enables parallel high-throughput imaging, creating a downstream bottleneck at the stage of data analysis. Recent progress on deep learning image analysis dramatically improved cell segmentation and tracking. Nevertheless, manual data validation and correction is typically still required and broadly used tools spanning the complete range of live-cell imaging analysis, from cell segmentation to pedigree analysis and signal quantification, are still needed. Here, we present Cell-ACDC, a user-friendly graphical user-interface (GUI)-based framework written in Python, for segmentation, tracking and cell cycle annotation. We included two state-of-the-art and high-accuracy deep learning models for single-cell segmentation of yeast and mammalian cells implemented in the most used deep learning frameworks TensorFlow and PyTorch. Additionally, we developed and implemented a cell tracking method and embedded it into an intuitive, semi-automated workflow for label-free cell cycle annotation of single cells. The open-source and modularized nature of Cell-ACDC will enable simple and fast integration of new deep learning-based and traditional methods for cell segmentation or downstream image analysis. Source code: https://github.com/SchmollerLab/Cell_ACDC

Gal1 repression memory in budding yeast

“…We captured images from the microfluidics chambers every 3 min totaling 320 images per chamber during a 16-h experiment. The yeast cells were then semi-automatically segmented, mapped and the total Gal1-GFP fluorescence signal per cell and time point was extracted using Autotrack and PhyloCell ( 19 ), YeaZ ( 20 ) and Cell-ACDC ( 21 ) (see Materials and Methods), yielding over 2,500 single-cell Gal1 expression traces (Figure 2B). Asymmetric budding allowed us to identify mother-daughter relationships.…”

“…Due to low cell numbers, we pooled data from three and two independent experiments for wildtype and elp6Δ , totaling 13 and 23 positions, respectively. Using the software YeaZ ( 20 ) and Cell-ACDC ( 21 ) for cell segmentation, mapping and tracking, we extracted the relevant single-cell information of the live-cell images for both repressions r1 and r2. During glucose repression, the yeast cells proliferated, increasing the cell numbers within the microfluidic chambers.…”

“…The toolboxes used for segmentation, mapping, and tracking are available at https://github.com/gcharvin/phyloCell (PhyloCell ( 19 )), https://github.com/lpbsscientist/YeaZ-GUI (YeaZ ( 20 )), and https://github.com/SchmollerLab/Cell_ACDC (Cell-ACDC ( 21 )). The toolbox used for parameter estimation (PESTO ( 29 )) is available under https://github.com/ICB-DCM.…”

Regulation with cell size ensures mitochondrial DNA homeostasis during cell growth

“…Cell segmentation was performed using Cellpose v0.6 (Stringer et al, 2021) with the 'cell diameter' parameter set to 50 pixels, 'flow threshold' set to 0.4, and 'cell probability threshold' set to 0. Cell-ACDC (Padovani et al, 2021) was used to manually correct segmentation, annotate buds to their corresponding mother cells, and calculate cell volume.…”

“…These samples were analyzed by light microscopy and DIC images of living cells were taken using a Zeiss Axiophot microscope equipped with a Plan-Neofluar 100x/1.30 Oil objective (Carl Zeiss Lichtmikroskopie, Göttingen, Germany) and a Leica DFC360 FX camera operated with the Leica LAS AF software version 2.2.1 (Leica Microsystems, Wetzlar, Germany). Cell segmentation and volume estimation were performed using Cell-ACDC (Padovani et al, 2021) as described above.…”