Three-dimensional (3D) segmentation of cells in microscopy images is crucial to accurately capture signals that extend across optical sections. Using brightfield images for segmentation has the advantage of being minimally phototoxic and leaving all other channels available for signals of interest. However, brightfield images only readily provide information for two-dimensional (2D) segmentation. In radially symmetric cells, such as fission yeast and many bacteria, this 2D segmentation can be computationally extruded into the third dimension. However, current methods typically make the simplifying assumption that cells are straight rods. Here, we report Pomegranate, a pipeline that performs the extrusion into 3D using spheres placed along the topological skeletons of the 2D-segmented regions. The diameter of these spheres adapts to the cell diameter at each position. Thus, Pomegranate accurately represents radially symmetric cells in 3D even if cell diameter varies and regardless of whether a cell is straight, bent or curved. We have tested Pomegranate on fission yeast and demonstrate its ability to 3D segment wild-type cells as well as classical size and shape mutants. The pipeline is available as a macro for the open-source image analysis software Fiji/ImageJ. 2D segmentations created within or outside Pomegranate can serve as input, thus making this a valuable extension to the image analysis portfolio already available for fission yeast and other radially symmetric cell types.
DeLTA 2.0: A deep learning pipeline for quantifying single-cell spatial and temporal dynamics
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 images of 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. 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 as inputs and the introduction of a Google Colab notebook so users can try the software without installing the code on their local machine. 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.
more »
« less
- Award ID(s):
- 2032357
- NSF-PAR ID:
- 10342637
- Editor(s):
- Coelho, Luis Pedro
- Date Published:
- Journal Name:
- PLOS Computational Biology
- Volume:
- 18
- Issue:
- 1
- ISSN:
- 1553-7358
- Page Range / eLocation ID:
- e1009797
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract -
Abstract This paper presents a method for time-lapse 3D cell analysis. Specifically, we consider the problem of accurately localizing and quantitatively analyzing sub-cellular features, and for tracking individual cells from time-lapse 3D confocal cell image stacks. The heterogeneity of cells and the volume of multi-dimensional images presents a major challenge for fully automated analysis of morphogenesis and development of cells. This paper is motivated by the pavement cell growth process, and building a quantitative morphogenesis model. We propose a deep feature based segmentation method to accurately detect and label each cell region. An adjacency graph based method is used to extract sub-cellular features of the segmented cells. Finally, the robust graph based tracking algorithm using multiple cell features is proposed for associating cells at different time instances. We also demonstrate the generality of our tracking method on C. elegans fluorescent nuclei imagery. Extensive experiment results are provided and demonstrate the robustness of the proposed method. The code is available on and the method is available as a service through the BisQue portal.more » « less
-
null (Ed.)Despite having widespread application in the biomedical sciences, flow cytometers have several limitations that prevent their application to point-of-care (POC) diagnostics in resource-limited environments. 3D printing provides a cost-effective approach to improve the accessibility of POC devices in resource-limited environments. Towards this goal, we introduce a 3D-printed imaging platform (3DPIP) capable of accurately counting particles and perform fluorescence microscopy. In our 3DPIP, captured microscopic images of particle flow are processed on a custom developed particle counter code to provide a particle count. This prototype uses a machine vision-based algorithm to identify particles from captured flow images and is flexible enough to allow for labeled and label-free particle counting. Additionally, the particle counter code returns particle coordinates with respect to time which can further be used to perform particle image velocimetry. These results can help estimate forces acting on particles, and identify and sort different types of cells/particles. We evaluated the performance of this prototype by counting 10 μm polystyrene particles diluted in deionized water at different concentrations and comparing the results with a commercial Beckman-Coulter Z2 particle counter. The 3DPIP can count particle concentrations down to ∼100 particles per mL with a standard deviation of ±20 particles, which is comparable to the results obtained on a commercial particle counter. Our platform produces accurate results at flow rates up to 9 mL h −1 for concentrations below 1000 particle per mL, while 5 mL h −1 produces accurate results above this concentration limit. Aside from performing flow-through experiments, our instrument is capable of performing static experiments that are comparable to a plate reader. In this configuration, our instrument is able to count between 10 and 250 cells per image, depending on the prepared concentration of bacteria samples ( Citrobacter freundii ; ATCC 8090). Overall, this platform represents a first step towards the development of an affordable fully 3D printable imaging flow cytometry instrument for use in resource-limited clinical environments.more » « less
-
more » « less
Abstract Quantitative phase microscopy (QPM) enables studies of living biological systems without exogenous labels. To increase the utility of QPM, machine-learning methods have been adapted to extract additional information from the quantitative phase data. Previous QPM approaches focused on fluid flow systems or time-lapse images that provide high throughput data for cells at single time points, or of time-lapse images that require delayed post-experiment analyses, respectively. To date, QPM studies have not imaged specific cells over time with rapid, concurrent analyses during image acquisition. In order to study biological phenomena or cellular interactions over time, efficient time-dependent methods that automatically and rapidly identify events of interest are desirable. Here, we present an approach that combines QPM and machine learning to identify tumor-reactive T cell killing of adherent cancer cells rapidly, which could be used for identifying and isolating novel T cells and/or their T cell receptors for studies in cancer immunotherapy. We demonstrate the utility of this method by machine learning model training and validation studies using one melanoma-cognate T cell receptor model system, followed by high classification accuracy in identifying T cell killing in an additional, independent melanoma-cognate T cell receptor model system. This general approach could be useful for studying additional biological systems under label-free conditions over extended periods of examination.
-
Obeid, Iyad ; Selesnick, Ivan ; Picone, Joseph (Ed.)The goal of this work was to design a low-cost computing facility that can support the development of an open source digital pathology corpus containing 1M images [1]. A single image from a clinical-grade digital pathology scanner can range in size from hundreds of megabytes to five gigabytes. A 1M image database requires over a petabyte (PB) of disk space. To do meaningful work in this problem space requires a significant allocation of computing resources. The improvements and expansions to our HPC (highperformance computing) cluster, known as Neuronix [2], required to support working with digital pathology fall into two broad categories: computation and storage. To handle the increased computational burden and increase job throughput, we are using Slurm [3] as our scheduler and resource manager. For storage, we have designed and implemented a multi-layer filesystem architecture to distribute a filesystem across multiple machines. These enhancements, which are entirely based on open source software, have extended the capabilities of our cluster and increased its cost-effectiveness. Slurm has numerous features that allow it to generalize to a number of different scenarios. Among the most notable is its support for GPU (graphics processing unit) scheduling. GPUs can offer a tremendous performance increase in machine learning applications [4] and Slurm’s built-in mechanisms for handling them was a key factor in making this choice. Slurm has a general resource (GRES) mechanism that can be used to configure and enable support for resources beyond the ones provided by the traditional HPC scheduler (e.g. memory, wall-clock time), and GPUs are among the GRES types that can be supported by Slurm [5]. In addition to being able to track resources, Slurm does strict enforcement of resource allocation. This becomes very important as the computational demands of the jobs increase, so that they have all the resources they need, and that they don’t take resources from other jobs. It is a common practice among GPU-enabled frameworks to query the CUDA runtime library/drivers and iterate over the list of GPUs, attempting to establish a context on all of them. Slurm is able to affect the hardware discovery process of these jobs, which enables a number of these jobs to run alongside each other, even if the GPUs are in exclusive-process mode. To store large quantities of digital pathology slides, we developed a robust, extensible distributed storage solution. We utilized a number of open source tools to create a single filesystem, which can be mounted by any machine on the network. At the lowest layer of abstraction are the hard drives, which were split into 4 60-disk chassis, using 8TB drives. To support these disks, we have two server units, each equipped with Intel Xeon CPUs and 128GB of RAM. At the filesystem level, we have implemented a multi-layer solution that: (1) connects the disks together into a single filesystem/mountpoint using the ZFS (Zettabyte File System) [6], and (2) connects filesystems on multiple machines together to form a single mountpoint using Gluster [7]. ZFS, initially developed by Sun Microsystems, provides disk-level awareness and a filesystem which takes advantage of that awareness to provide fault tolerance. At the filesystem level, ZFS protects against data corruption and the infamous RAID write-hole bug by implementing a journaling scheme (the ZFS intent log, or ZIL) and copy-on-write functionality. Each machine (1 controller + 2 disk chassis) has its own separate ZFS filesystem. Gluster, essentially a meta-filesystem, takes each of these, and provides the means to connect them together over the network and using distributed (similar to RAID 0 but without striping individual files), and mirrored (similar to RAID 1) configurations [8]. By implementing these improvements, it has been possible to expand the storage and computational power of the Neuronix cluster arbitrarily to support the most computationally-intensive endeavors by scaling horizontally. We have greatly improved the scalability of the cluster while maintaining its excellent price/performance ratio [1].more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1371/journal.pcbi.1009797
