DeLTA 2.0: A deep learning pipeline for quantifying single-cell spatial and temporal dynamics

Abstract

Improvements in microscopy software and hardware have dramatically increased the pace of image acquisition, making analysis a major bottleneck in generating quantitative, single-cell data. Although tools for segmenting and tracking bacteria within time-lapse images exist, most require human input, are specialized to the experimental set up, or lack accuracy. Here, we introduce DeLTA 2.0, a purely Python workflow that can rapidly and accurately analyze single cells on two-dimensional surfaces to quantify gene expression and cell growth. The algorithm uses deep convolutional neural networks to extract single-cell information from time-lapse images, requiring no human input after training. DeLTA 2.0 retains all the functionality of the original version, which was optimized for bacteria growing in the mother machine microfluidic device, but extends results to two-dimensional growth environments. Two-dimensional environments represent an important class of data because they are more straightforward to implement experimentally, they offer the potential for studies using co-cultures of cells, and they can be used to quantify spatial effects and multi-generational phenomena. However, segmentation and tracking are significantly more challenging tasks in two-dimensions due to exponential increases in the number of cells that must be tracked. To showcase this new functionality, we analyze mixed populations of antibiotic resistant and susceptible cells, and also track pole age and growth rate across generations. In addition to the two-dimensional capabilities, we also introduce several major improvements to the code that increase accessibility, including the ability to accept many standard microscopy file formats and arbitrary image sizes as inputs. DeLTA 2.0 is rapid, with run times of less than 10 minutes for complete movies with hundreds of cells, and is highly accurate, with error rates around 1%, making it a powerful tool for analyzing time-lapse microscopy data.

Omnipose: a high-precision morphology-independent solution for bacterial cell segmentation

“…DeLTA was not included in this study because it operates similarly to MiSiC and was designed specifically for mother machine microfluidics analysis. DeLTA 2.0 was recently released to additionally segment confluent cell growth on agarose pads, but it remains quite similar to MiSiC in implementation (55). PlantSeg could, in principle, be trained on bacterial micrographs, but we determined that its edge-focused design meant to segment bright plant cell wall features would not offer any advancements over the remaining U-Net methods that we tested.…”

DeepBacs for multi-task bacterial image analysis using open-source deep learning approaches

“…studying filamentation, irregularly shaped cells or biofilms. In such cases, we refer to DL networks developed for the particular segmentation task 28 – 32 .…”

“…Instance segmentations can subsequently be used for downstream applications such as tracking cell lineages or morphological changes. If this is not already included in the network 32 , 33 , segmentation masks can be used with TrackMate, which was recently updated for the use of DL technology 46 (Supplementary Video 3 ). The convenient use of StarDist and Cellpose segmentation models directly within TrackMate allows for integrative image analysis of time-lapse data.…”

“…2e/f , Supplementary Video 4 ). For very dense and exponentially growing cells, however, the use DL-based tracking approaches should be favoured, as they strongly reduce erroneous linking of neighbouring cells upon cell division 32 , 33 .…”

An Optogenetic Toolkit for Light-Inducible Antibiotic Resistance

“…Images were segmented and analyzed using the DeLTA 2.0 software and custom analysis scripts. 59 Statistical analysis OD600 values in MIC curves and bar plots are reported as the mean of three samples ± the standard deviation. Colony count values for CFU measurements are reported as the mean of six samples consisting of two dilutions and platings for each MIC data point.…”