Segmentation, tracking and cell cycle analysis of live-cell imaging data with Cell-ACDC

Abstract

Background High-throughput live-cell imaging is a powerful tool to study dynamic cellular processes in single cells but creates a bottleneck at the stage of data analysis, due to the large amount of data generated and limitations of analytical pipelines. Recent progress on deep learning dramatically improved cell segmentation and tracking. Nevertheless, manual data validation and correction is typically still required and tools spanning the complete range of image analysis are still needed. Results We present Cell-ACDC, an open-source user-friendly GUI-based framework written in Python, for segmentation, tracking and cell cycle annotations. We included state-of-the-art deep learning models for single-cell segmentation of mammalian and yeast cells alongside cell tracking methods and an intuitive, semi-automated workflow for cell cycle annotation of single cells. Using Cell-ACDC, we found that mTOR activity in hematopoietic stem cells is largely independent of cell volume. By contrast, smaller cells exhibit higher p38 activity, consistent with a role of p38 in regulation of cell size. Additionally, we show that, in S. cerevisiae, histone Htb1 concentrations decrease with replicative age. Conclusions Cell-ACDC provides a framework for the application of state-of-the-art deep learning models to the analysis of live cell imaging data without programming knowledge. Furthermore, it allows for visualization and correction of segmentation and tracking errors as well as annotation of cell cycle stages. We embedded several smart algorithms that make the correction and annotation process fast and intuitive. Finally, 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, tracking, and downstream image analysis. Source code: https://github.com/SchmollerLab/Cell_ACDC

Cellular enlargement - A new hallmark of aging?

“…For example, DNA damage incurred during replication ( Geiger et al, 2013 ; Flach et al, 2014 ; Walter et al, 2015 ) activates cell cycle checkpoints that transiently halt division until the DNA damage is repaired ( Sperka et al, 2012 ; Moehrle et al, 2015 ). During arrest phases, cell growth continues leading to increased HSC size ( Fingar et al, 2002 ; Neurohr et al, 2019 ; Padovani et al, 2022 ). The enlarged HSCs become dysfunctional.…”

LapTrack: linear assignment particle tracking with tunable metrics

“…For segmented images, we can also use the overlap between segmented regions to calculate the cost ( Chalfoun et al , 2010 ; Ershov et al , 2022 ; Padovani et al , 2022 ). The flexible implementation allows us to integrate the overlap metric in addition to the distance in the LAP framework.…”

“…Tools have been developed to provide similar LAP-based algorithms with splitting and merging detection; TrackMate ( Ershov et al , 2022 ; Tinevez et al , 2017 ), for example, provides distance-based LAP tracker with particle detection and segmentation workflow and a method to conduct manual correction, all within the Java-based framework in ImageJ ( Schindelin et al , 2012 ; Schneider et al , 2012 ). Cell-ACDC ( Padovani et al , 2022 ), which was originally designed for yeast analysis, also implements an overlap-based LAP tracker with splitting detection, as well as various functions ranging from image alignment to manual correction that support the entire analysis workflow in Python. In addition, TracX ( Cuny et al , 2022 ) employs a multi-round tracking and correction workflow using a LAP tracker and mistracking detector by matching image features.…”

LapTrack: Linear assignment particle tracking with tunable metrics

“…For segmented images, we can also use the overlap between segmented regions to calculate the cost [7,10,29]. The flexible implementation allows us to integrate the overlap metric in addition to the distance in the LAP framework.We defined l (with g and s analogously) as…”

“…Tools have been developed to provide similar LAPbased algorithms with splitting and merging detection; TrackMate [6,7], for example, provides distance-based LAP-based tracking with particle detection and segmentation workflow and a method to conduct manual correction, all within the Java-based framework in ImageJ [8,9]. Cell-ACDC [10], which was originally designed for yeast analysis, also implements an overlap-based LAP tracker with splitting detection, as well as various functions ranging from image alignment to manual correction that support the entire analysis workflow in Python.…”