Accurately tracking single-cell movement trajectories in microfluidic cell sorting devices

Dynamic video recognition for cell-encapsulating microfluidic droplets

Droplet microfluidics is a highly sensitive and high-throughput technology extensively utilized in biomedical applications, such as single-cell sequencing and cell screening. However, its performance is highly influenced by the droplet size and single-cell encapsulation rate (following random distribution), thereby creating an urgent need for quality control. Machine learning has the potential to revolutionize droplet microfluidics, but it requires tedious pixel-level annotation for network training. This paper investigates the application software of the weakly supervised cell-counting network (WSCApp) for video recognition of microdroplets. We demonstrated its real-time performance in video processing of microfluidic droplets and further identified the locations of droplets and encapsulated cells. We verified our methods on droplets encapsulating six types of cells/beads, which were collected from various microfluidic structures. Quantitative experimental results showed that our approach can not only accurately distinguish droplet encapsulations (micro-F1 score > 0.94), but also locate each cell without any supervised location information. Furthermore, fine-tuning transfer learning on the pre-trained model also significantly reduced (>80%) annotation. This software provides a user-friendly and assistive annotation platform for the quantitative assessment of cell-encapsulating microfluidic droplets.

Tutorial on compressed ultrafast photography

Significance

Compressed ultrafast photography (CUP) is currently the world's fastest single-shot imaging technique. Through the integration of compressed sensing and streak imaging, CUP can capture a transient event in a single camera exposure with imaging speeds from thousands to trillions of frames per second, at micrometer-level spatial resolutions, and in broad sensing spectral ranges.

Aim

This tutorial aims to provide a comprehensive review of CUP in its fundamental methods, system implementations, biomedical applications, and prospect.

Approach

A step-by-step guideline to CUP's forward model and representative image reconstruction algorithms is presented with sample codes and illustrations in Matlab and Python. Then, CUP's hardware implementation is described with a focus on the representative techniques, advantages, and limitations of the three key components-the spatial encoder, the temporal shearing unit, and the two-dimensional sensor. Furthermore, four representative biomedical applications enabled by CUP are discussed, followed by the prospect of CUP's technical advancement.

Conclusions

CUP has emerged as a state-of-the-art ultrafast imaging technology. Its advanced imaging ability and versatility contribute to unprecedented observations and new applications in biomedicine. CUP holds great promise in improving technical specifications and facilitating the investigation of biomedical processes.

iCLOTS: open-source, artificial intelligence-enabled software for analyses of blood cells in microfluidic and microscopy-based assays

While microscopy-based cellular assays, including microfluidics, have significantly advanced over the last several decades, there has not been concurrent development of widely-accessible techniques to analyze time-dependent microscopy data incorporating phenomena such as fluid flow and dynamic cell adhesion. As such, experimentalists typically rely on error-prone and time-consuming manual analysis, resulting in lost resolution and missed opportunities for innovative metrics. We present a user-adaptable toolkit packaged into the open-source, standalone Interactive Cellular assay Labeled Observation and Tracking Software (iCLOTS). We benchmark cell adhesion, single-cell tracking, velocity profile, and multiscale microfluidic-centric applications with blood samples, the prototypical biofluid specimen. Moreover, machine learning algorithms characterize previously imperceptible data groupings from numerical outputs. Free to download/use, iCLOTS addresses a need for a field stymied by a lack of analytical tools for innovative, physiologically-relevant assays of any design, democratizing use of well-validated algorithms for all end-user biomedical researchers who would benefit from advanced computational methods.

WSCNet: Biomedical Image Recognition for Cell Encapsulated Microfluidic Droplets

Microfluidic droplets accommodating a single cell as independent microreactors are frequently demanded for single-cell analysis of phenotype and genotype. However, challenges exist in identifying and reducing the covalence probability (following Poisson's distribution) of more than two cells encapsulated in one droplet. It is of great significance to monitor and control the quantity of encapsulated content inside each droplet. We demonstrated a microfluidic system embedded with a weakly supervised cell counting network (WSCNet) to generate microfluidic droplets, evaluate their quality, and further recognize the locations of encapsulated cells. Here, we systematically verified our approach using encapsulated droplets from three different microfluidic structures. Quantitative experimental results showed that our approach can not only distinguish droplet encapsulations (F1 score > 0.88) but also locate each cell without any supervised location information (accuracy > 89%). The probability of a "single cell in one droplet" encapsulation is systematically verified under different parameters, which shows good agreement with the distribution of the passive method (Residual Sum of Squares, RSS < 0.5). This study offers a comprehensive platform for the quantitative assessment of encapsulated microfluidic droplets.

Microfluidic Platform to Transduce Cell Viability to Distinct Flow Pathways for High-Accuracy Sensing

Mechanical properties of cells such as stiffness can act as biomarkers to sort or detect cell functional properties such as viability. In this study, we report the use of a microfluidic device as a high-sensitivity sensor that transduces cell biomechanics to cell separation to accurately detect viability. Cell populations are flowed and deflected at a number of skew ridges such that deflection per ridge, cell-ridge interaction time, and cell size can all be used as sensor inputs to accurately determine the cell state. The angle of the ridges was evaluated to optimize the differences in cell translation between viable and nonviable cells while allowing continuous flow. In the first mode of operation, we flowed viable and nonviable cells through the device and conducted a sensitivity analysis by recording the cell's total deflection as a binary classifier that differentiates viable from nonviable cells. The performance of the sensor was assessed using an area under the curve (AUC) analysis to be 0.97. By including additional sensor inputs in the second mode of operation, we conducted a principal component analysis (PCA) to further improve the identification of the cell state by clustering populations with little overlap between viable and nonviable cells. We therefore found that microfluidic separation devices can be used to efficiently sort cells and accurately sense viability in a label-free manner.

A graph-based cell tracking algorithm with few manually tunable parameters and automated segmentation error correction

Automatic cell segmentation and tracking enables to gain quantitative insights into the processes driving cell migration. To investigate new data with minimal manual effort, cell tracking algorithms should be easy to apply and reduce manual curation time by providing automatic correction of segmentation errors. Current cell tracking algorithms, however, are either easy to apply to new data sets but lack automatic segmentation error correction, or have a vast set of parameters that needs either manual tuning or annotated data for parameter tuning. In this work, we propose a tracking algorithm with only few manually tunable parameters and automatic segmentation error correction. Moreover, no training data is needed. We compare the performance of our approach to three well-performing tracking algorithms from the Cell Tracking Challenge on data sets with simulated, degraded segmentation—including false negatives, over- and under-segmentation errors. Our tracking algorithm can correct false negatives, over- and under-segmentation errors as well as a mixture of the aforementioned segmentation errors. On data sets with under-segmentation errors or a mixture of segmentation errors our approach performs best. Moreover, without requiring additional manual tuning, our approach ranks several times in the top 3 on the 6^th edition of the Cell Tracking Challenge.

FastTrack: An open-source software for tracking varying numbers of deformable objects

Analyzing the dynamical properties of mobile objects requires to extract trajectories from recordings, which is often done by tracking movies. We compiled a database of two-dimensional movies for very different biological and physical systems spanning a wide range of length scales and developed a general-purpose, optimized, open-source, cross-platform, easy to install and use, self-updating software called FastTrack. It can handle a changing number of deformable objects in a region of interest, and is particularly suitable for animal and cell tracking in two-dimensions. Furthermore, we introduce the probability of incursions as a new measure of a movie’s trackability that doesn’t require the knowledge of ground truth trajectories, since it is resilient to small amounts of errors and can be computed on the basis of an ad hoc tracking. We also leveraged the versatility and speed of FastTrack to implement an iterative algorithm determining a set of nearly-optimized tracking parameters—yet further reducing the amount of human intervention—and demonstrate that FastTrack can be used to explore the space of tracking parameters to optimize the number of swaps for a batch of similar movies. A benchmark shows that FastTrack is orders of magnitude faster than state-of-the-art tracking algorithms, with a comparable tracking accuracy. The source code is available under the GNU GPLv3 at https://github.com/FastTrackOrg/FastTrack and pre-compiled binaries for Windows, Mac and Linux are available at http://www.fasttrack.sh.

Many researchers and engineers face the challenge of tracking objects from very different systems across several fields of research. We observed that despite this diversity the core of the tracking task is very general and can be formalized. We thus introduce the notion of incursions—i.e. to what extent an object can enter a neighbor’s space—which can be defined on a statistical basis and captures the interplay between the acquisition rate, the objects’ dynamics and the geometrical characteristics of the scene, including density. To validate this approach, we compiled a dataset from various fields of Physics, Biology and human activities to serve as a benchmark for general-purpose tracking softwares. This dataset is open and accepts new submissions. We also developped a software called FastTrack that is able to track most of the movies in the dataset by proposing standard image processing tools and state-of-the-art implementation of the matching algorithm, which is at the core of the tracking task. Besides, it is open-source, simple to install and use and has an ergonomic interface to obtain fast and reliable results. FastTrack is particularly convenient for small-scale research projects, typically when the development of a dedicated software is overkill.

Compressive Coded Rotating Mirror Camera for High-Speed Imaging

We develop a novel compressive coded rotating mirror (CCRM) camera to capture events at high frame rates in passive mode with a compact instrument design at a fraction of the cost compared to other high-speed imaging cameras. Operation of the CCRM camera is based on amplitude optical encoding (grey scale) and a continuous frame sweep across a low-cost detector using a motorized rotating mirror system which can achieve single pixel shift between adjacent frames. Amplitude encoding and continuous frame overlapping enable the CCRM camera to achieve a high number of captured frames and high temporal resolution without making sacrifices in the spatial resolution. Two sets of dynamic scenes have been captured at up to a 120 Kfps frame rate in both monochrome and colored scales in the experimental demonstrations. The obtained heavily compressed data from the experiment are reconstructed using the optimization algorithm under the compressive sensing (CS) paradigm and the highest sequence depth of 1400 captured frames in a single exposure has been achieved with the highest compression ratio of 368 compared to other CS-based high-speed imaging technologies. Under similar conditions the CCRM camera is 700× faster than conventional rotating mirror based imaging devices and could reach a frame rate of up to 20 Gfps.

A novel automatic segmentation and tracking method to measure cellular dielectrophoretic mobility from individual cell trajectories for high throughput assay

BACKGROUND AND OBJECTIVE

The dielectrophoresis (DEP) technique is increasingly being recognised as a potentially valuable tool for non-contact manipulation of numerous cells as well as for biological single cell analysis with non-invasive characterisation of a cell's electrical properties. Several studies have attempted to track multiple cells to characterise their cellular DEP mobility. However, they encountered difficulties in simultaneously tracking the movement of a large number of individual cells in a bright-field image sequence because of interference from the background electrode pattern. Consequently, this present study aims to develop an automatic system for imaging-based characterisation of cellular DEP mobility, which enables the simultaneous tracking of several hundred of cells inside a microfluidic device.

METHODS

The proposed method for segmentation and tracking of cells consists of two main stages: pre-processing and particle centre localisation. In the pre-processing stage, background subtraction and contrast enhancement were performed to distinguish the cell region from the background image. In the particle centre localisation stage, the unmarked cell was automatically detected via graph-cut algorithm-based K-means clustering.

RESULTS

Our algorithm enabled segmentation and tracking of numerous Michigan Cancer Foundation-7 (MCF-7) cell trajectories while the DEP force was oscillated between positive and negative. The cell tracking accuracy and cell count capability was at least 90% of the total number of cells with the newly developed algorithm. In addition, the cross-over frequency was measured by analysing the segmented and tracked trajectory data of the cellular movements caused by the positive and negative DEP force. The measured cross-over frequency was compared with previous results. The multi-cellular movements investigation based on the measured cross-over frequency was repeated until the viability of cells was unchanged in the same environment as in a microfluidic device. The results were statistically consistent, indicating that the developed algorithm was reliable for the investigation of DEP cellular mobility.

CONCLUSION

This study developed a powerful platform to simultaneously measure the DEP-induced trajectories of numerous cells, and to investigate in a robust, efficient, and accurate manner the DEP properties at both the single cell and cell ensemble level.

Label-free microfluidic enrichment of photoreceptor cells

Inherited retinal degenerative disorders such as retinitis pigmentosa and Usher syndrome are characterized by progressive death of photoreceptor cells. To restore vision to patients blinded by these diseases, a stem cell-based photoreceptor cell replacement strategy will likely be required. Although retinal stem cell differentiation protocols suitable for generating photoreceptor cells exist, they often yield a rather heterogenous mixture of cell types. To enrich the donor cell population for one or a few cell types, scientists have traditionally relied upon the use of antibody-based selection approaches. However, these strategies are quite labor intensive and require animal derived reagents and equipment that are not well suited to current good manufacturing practices (cGMP). The purpose of this study was to develop and evaluate a microfluidic cell sorting device capable of exploiting the physical and mechanical differences between retinal cell types to enrich specific donor cell populations such as Retinal Pigment Epithelial (RPE) cells and photoreceptor cells. Using this device, we were able to separate a mixture of RPE and iPSC-derived photoreceptor precursor cell lines into two substantially enriched fractions. The enrichment factor of the RPE fraction was 2 and that of the photoreceptor precursor cell fraction was 2.7. Similarly, when human retina, obtained from 3 independent donors, was dissociated and passed through the sorting device, the heterogeneous mixture could be reliably sorted into RPE and photoreceptor cell rich fractions. In summary, microfluidic cell sorting is a promising approach for antibody free enrichment of retinal cell populations.

FluoroCellTrack: An algorithm for automated analysis of high-throughput droplet microfluidic data

High-throughput droplet microfluidic devices with fluorescence detection systems provide several advantages over conventional end-point cytometric techniques due to their ability to isolate single cells and investigate complex intracellular dynamics. While there have been significant advances in the field of experimental droplet microfluidics, the development of complementary software tools has lagged. Existing quantification tools have limitations including interdependent hardware platforms or challenges analyzing a wide range of high-throughput droplet microfluidic data using a single algorithm. To address these issues, an all-in-one Python algorithm called FluoroCellTrack was developed and its wide-range utility was tested on three different applications including quantification of cellular response to drugs, droplet tracking, and intracellular fluorescence. The algorithm imports all images collected using bright field and fluorescence microscopy and analyzes them to extract useful information. Two parallel steps are performed where droplets are detected using a mathematical Circular Hough Transform (CHT) while single cells (or other contours) are detected by a series of steps defining respective color boundaries involving edge detection, dilation, and erosion. These feature detection steps are strengthened by segmentation and radius/area thresholding for precise detection and removal of false positives. Individually detected droplet and contour center maps are overlaid to obtain encapsulation information for further analyses. FluoroCellTrack demonstrates an average of a ~92-99% similarity with manual analysis and exhibits a significant reduction in analysis time of 30 min to analyze an entire cohort compared to 20 h required for manual quantification.