Intelligent Image-Activated Cell Sorting.

A fundamental challenge of biology is to understand the vast heterogeneity of cells, particularly how cellular composition, structure, and morphology are linked to cellular physiology. Unfortunately, conventional technologies are limited in uncovering these relations. We present a machine-intelligence technology based on a radically different architecture that realizes real-time image-based intelligent cell sorting at an unprecedented rate. This technology, which we refer to as intelligent image-activated cell sorting, integrates high-throughput cell microscopy, focusing, and sorting on a hybrid software-hardware data-management infrastructure, enabling real-time automated operation for data acquisition, data processing, decision-making, and actuation. We use it to demonstrate real-time sorting of microalgal and blood cells based on intracellular protein localization and cell-cell interaction from large heterogeneous populations for studying photosynthesis and atherothrombosis, respectively. The technology is highly versatile and expected to enable machine-based scientific discovery in biological, pharmaceutical, and medical sciences.

Intelligent sort-timing prediction for image-activated cell sorting.

Intelligent image-activated cell sorting (iIACS) has enabled high-throughput image-based sorting of single cells with artificial intelligence (AI) algorithms. This AI-on-a-chip technology combines fluorescence microscopy, AI-based image processing, sort-timing prediction, and cell sorting. Sort-timing prediction is particularly essential due to the latency on the order of milliseconds between image acquisition and sort actuation, during which image processing is performed. The long latency amplifies the effects of the fluctuations in the flow speed of cells, leading to fluctuation and uncertainty in the arrival time of cells at the sort point on the microfluidic chip. To compensate for this fluctuation, iIACS measures the flow speed of each cell upstream, predicts the arrival timing of the cell at the sort point, and activates the actuation of the cell sorter appropriately. Here, we propose and demonstrate a machine learning technique to increase the accuracy of the sort-timing prediction that would allow for the improvement of sort event rate, yield, and purity. Specifically, we trained an algorithm to predict the sort timing for morphologically heterogeneous budding yeast cells. The algorithm we developed used cell morphology, position, and flow speed as inputs for prediction and achieved 41.5% lower prediction error compared to the previously employed method based solely on flow speed. As a result, our technique would allow for an increase in the sort event rate of iIACS by a factor of ~2.

Long-term effects of Pfizer-BioNTech COVID-19 vaccinations on platelets.

There is a global concern about the safety of COVID-19 vaccines associated with platelet function. However, their long-term effects on overall platelet activity remain poorly understood. Here we address this problem by image-based single-cell profiling and temporal monitoring of circulating platelet aggregates in the blood of healthy human subjects, before and after they received multiple Pfizer-BioNTech (BNT162b2) vaccine doses over a time span of nearly 1 year. Results show no significant or persisting platelet aggregation trends following the vaccine doses, indicating that any effects of vaccinations on platelet turnover, platelet activation, platelet aggregation, and platelet-leukocyte interaction was insignificant.

Label-free chemical imaging flow cytometry by high-speed multicolor stimulated Raman scattering.

Combining the strength of flow cytometry with fluorescence imaging and digital image analysis, imaging flow cytometry is a powerful tool in diverse fields including cancer biology, immunology, drug discovery, microbiology, and metabolic engineering. It enables measurements and statistical analyses of chemical, structural, and morphological phenotypes of numerous living cells to provide systematic insights into biological processes. However, its utility is constrained by its requirement of fluorescent labeling for phenotyping. Here we present label-free chemical imaging flow cytometry to overcome the issue. It builds on a pulse pair-resolved wavelength-switchable Stokes laser for the fastest-to-date multicolor stimulated Raman scattering (SRS) microscopy of fast-flowing cells on a 3D acoustic focusing microfluidic chip, enabling an unprecedented throughput of up to ∼140 cells/s. To show its broad utility, we use the SRS imaging flow cytometry with the aid of deep learning to study the metabolic heterogeneity of microalgal cells and perform marker-free cancer detection in blood.

Single-Cell Analysis of Morphological and Metabolic Heterogeneity in Euglena gracilis by Fluorescence-Imaging Flow Cytometry.

Microalgal biofuels and biomass have ecofriendly advantages as feedstocks. Improved understanding and utilization of microalgae require large-scale analysis of the morphological and metabolic heterogeneity within populations. Here, with Euglena gracilis as a model microalgal species, we evaluate how fluorescence- and brightfield-derived-image-based descriptors vary during environmental stress at the single-cell level. This is achieved with a new multiparameter fluorescence-imaging cytometric technique that allows the assaying of thousands of cells per experiment. We track morphological changes, including the intensity and distribution of intracellular lipid droplets, and pigment autofluorescence. The combined fluorescence-morphological analysis identifies new metrics not accessible with traditional flow cytometry, including the lipid-to-cell-area ratio (LCAR), which shows promise as an indicator of oil productivity per biomass. Single-cell metrics of lipid productivity were highly correlated ( R2 > 0.90, p < 0.005) with bulk oil extraction. Such chemomorphological atlases of algal species can help optimize growth conditions and selection approaches for large-scale biomass production.

Deep imaging flow cytometry.

Imaging flow cytometry (IFC) has become a powerful tool for diverse biomedical applications by virtue of its ability to image single cells in a high-throughput manner. However, there remains a challenge posed by the fundamental trade-off between throughput, sensitivity, and spatial resolution. Here we present deep-learning-enhanced imaging flow cytometry (dIFC) that circumvents this trade-off by implementing an image restoration algorithm on a virtual-freezing fluorescence imaging (VIFFI) flow cytometry platform, enabling higher throughput without sacrificing sensitivity and spatial resolution. A key component of dIFC is a high-resolution (HR) image generator that synthesizes "virtual" HR images from the corresponding low-resolution (LR) images acquired with a low-magnification lens (10×/0.4-NA). For IFC, a low-magnification lens is favorable because of reduced image blur of cells flowing at a higher speed, which allows higher throughput. We trained and developed the HR image generator with an architecture containing two generative adversarial networks (GANs). Furthermore, we developed dIFC as a method by combining the trained generator and IFC. We characterized dIFC using Chlamydomonas reinhardtii cell images, fluorescence in situ hybridization (FISH) images of Jurkat cells, and Saccharomyces cerevisiae (budding yeast) cell images, showing high similarities of dIFC images to images obtained with a high-magnification lens (40×/0.95-NA), at a high flow speed of 2 m s-1. We lastly employed dIFC to show enhancements in the accuracy of FISH-spot counting and neck-width measurement of budding yeast cells. These results pave the way for statistical analysis of cells with high-dimensional spatial information.

Massive image-based single-cell profiling reveals high levels of circulating platelet aggregates in patients with COVID-19.

A characteristic clinical feature of COVID-19 is the frequent incidence of microvascular thrombosis. In fact, COVID-19 autopsy reports have shown widespread thrombotic microangiopathy characterized by extensive diffuse microthrombi within peripheral capillaries and arterioles in lungs, hearts, and other organs, resulting in multiorgan failure. However, the underlying process of COVID-19-associated microvascular thrombosis remains elusive due to the lack of tools to statistically examine platelet aggregation (i.e., the initiation of microthrombus formation) in detail. Here we report the landscape of circulating platelet aggregates in COVID-19 obtained by massive single-cell image-based profiling and temporal monitoring of the blood of COVID-19 patients (n = 110). Surprisingly, our analysis of the big image data shows the anomalous presence of excessive platelet aggregates in nearly 90% of all COVID-19 patients. Furthermore, results indicate strong links between the concentration of platelet aggregates and the severity, mortality, respiratory condition, and vascular endothelial dysfunction level of COVID-19 patients.

Differential regulatory function of resting and preactivated allergen-specific CD4+ CD25+ regulatory T cells in Th2-type airway inflammation.

Although CD4(+)CD25(+) regulatory T (Treg) cells are known to suppress Th1 cell-mediated immune responses, their effect on Th2-type immune responses remains unclear. In this study we examined the role of Treg cells in Th2-type airway inflammation in mice. Depletion and reconstitution experiments demonstrated that the Treg cells of naive mice effectively suppressed the initiation and development of Th2-driven airway inflammation. Despite effective suppression of Th2-type airway inflammation in naive mice, adoptively transferred, allergen-specific Treg cells were unable to suppress airway inflammation in allergen-presensitized mice. Preactivated allergen-specific Treg cells, however, could suppress airway inflammation even in allergen-presensitized mice by accumulating in the lung, where they reduced the accumulation and proliferation of Th2 cells. Upon activation, allergen-specific Treg cells up-regulated CCR4, exhibited enhanced chemotactic responses to CCR4 ligands, and suppressed the proliferation of and cytokine production by polarized Th2 cells. Collectively, these results demonstrated that Treg cells are capable of suppressing Th2-driven airway inflammation even in allergen-presensitized mice in a manner dependent on their efficient migration into the inflammatory site and their regulation of Th2 cell activation and proliferation.

Intelligent image-activated cell sorting 2.0.

The advent of intelligent image-activated cell sorting (iIACS) has enabled high-throughput intelligent image-based sorting of single live cells from heterogeneous populations. iIACS is an on-chip microfluidic technology that builds on a seamless integration of a high-throughput fluorescence microscope, cell focuser, cell sorter, and deep neural network on a hybrid software-hardware data management architecture, thereby providing the combined merits of optical microscopy, fluorescence-activated cell sorting (FACS), and deep learning. Here we report an iIACS machine that far surpasses the state-of-the-art iIACS machine in system performance in order to expand the range of applications and discoveries enabled by the technology. Specifically, it provides a high throughput of ∼2000 events per second and a high sensitivity of ∼50 molecules of equivalent soluble fluorophores (MESFs), both of which are 20 times superior to those achieved in previous reports. This is made possible by employing (i) an image-sensor-based optomechanical flow imaging method known as virtual-freezing fluorescence imaging and (ii) a real-time intelligent image processor on an 8-PC server equipped with 8 multi-core CPUs and GPUs for intelligent decision-making, in order to significantly boost the imaging performance and computational power of the iIACS machine. We characterize the iIACS machine with fluorescent particles and various cell types and show that the performance of the iIACS machine is close to its achievable design specification. Equipped with the improved capabilities, this new generation of the iIACS technology holds promise for diverse applications in immunology, microbiology, stem cell biology, cancer biology, pathology, and synthetic biology.

Raman image-activated cell sorting.

The advent of image-activated cell sorting and imaging-based cell picking has advanced our knowledge and exploitation of biological systems in the last decade. Unfortunately, they generally rely on fluorescent labeling for cellular phenotyping, an indirect measure of the molecular landscape in the cell, which has critical limitations. Here we demonstrate Raman image-activated cell sorting by directly probing chemically specific intracellular molecular vibrations via ultrafast multicolor stimulated Raman scattering (SRS) microscopy for cellular phenotyping. Specifically, the technology enables real-time SRS-image-based sorting of single live cells with a throughput of up to ~100 events per second without the need for fluorescent labeling. To show the broad utility of the technology, we show its applicability to diverse cell types and sizes. The technology is highly versatile and holds promise for numerous applications that are previously difficult or undesirable with fluorescence-based technologies.

Comment on "Ghost cytometry".

Ota et al (Reports, 15 June 2018, p. 1246) report using pseudo-random optical masks and a spatial-temporal transformation to perform blur-free, high-frame rate imaging of cells in flow with a high signal-to-noise ratio. They also claim sorting at rates of 3000 cells per second, based on imaging data. The experiments conducted and results reported in their study are insufficient to support these conclusions.

A practical guide to intelligent image-activated cell sorting.

Intelligent image-activated cell sorting (iIACS) is a machine-intelligence technology that performs real-time intelligent image-based sorting of single cells with high throughput. iIACS extends beyond the capabilities of fluorescence-activated cell sorting (FACS) from fluorescence intensity profiles of cells to multidimensional images, thereby enabling high-content sorting of cells or cell clusters with unique spatial chemical and morphological traits. Therefore, iIACS serves as an integral part of holistic single-cell analysis by enabling direct links between population-level analysis (flow cytometry), cell-level analysis (microscopy), and gene-level analysis (sequencing). Specifically, iIACS is based on a seamless integration of high-throughput cell microscopy (e.g., multicolor fluorescence imaging, bright-field imaging), cell focusing, cell sorting, and deep learning on a hybrid software-hardware data management infrastructure, enabling real-time automated operation for data acquisition, data processing, intelligent decision making, and actuation. Here, we provide a practical guide to iIACS that describes how to design, build, characterize, and use an iIACS machine. The guide includes the consideration of several important design parameters, such as throughput, sensitivity, dynamic range, image quality, sort purity, and sort yield; the development and integration of optical, microfluidic, electrical, computational, and mechanical components; and the characterization and practical usage of the integrated system. Assuming that all components are readily available, a team of several researchers experienced in optics, electronics, digital signal processing, microfluidics, mechatronics, and flow cytometry can complete this protocol in ~3 months.

Author Correction: A practical guide to intelligent image-activated cell sorting.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

High-throughput imaging flow cytometry by optofluidic time-stretch microscopy.

The ability to rapidly assay morphological and intracellular molecular variations within large heterogeneous populations of cells is essential for understanding and exploiting cellular heterogeneity. Optofluidic time-stretch microscopy is a powerful method for meeting this goal, as it enables high-throughput imaging flow cytometry for large-scale single-cell analysis of various cell types ranging from human blood to algae, enabling a unique class of biological, medical, pharmaceutical, and green energy applications. Here, we describe how to perform high-throughput imaging flow cytometry by optofluidic time-stretch microscopy. Specifically, this protocol provides step-by-step instructions on how to build an optical time-stretch microscope and a cell-focusing microfluidic device for optofluidic time-stretch microscopy, use it for high-throughput single-cell image acquisition with sub-micrometer resolution at >10,000 cells per s, conduct image construction and enhancement, perform image analysis for large-scale single-cell analysis, and use computational tools such as compressive sensing and machine learning for handling the cellular 'big data'. Assuming all components are readily available, a research team of three to four members with an intermediate level of experience with optics, electronics, microfluidics, digital signal processing, and sample preparation can complete this protocol in a time frame of 1 month.

Quantitative analysis of eosinophil chemotaxis tracked using a novel optical device -- TAXIScan.

We have reported previously the development of an optically accessible, horizontal chemotaxis apparatus, in which migration of cells in the channel from a start line can be traced with time-lapse intervals using a CCD camera (JIM 282, 1-11, 2003). To obtain statistical data of migrating cells, we have developed quantitative methods to calculate various parameters in the process of chemotaxis, employing human eosinophil and CXCL12 as a model cell and a model chemoattractant, respectively. Median values of velocity and directionality of each cell within an experimental period could be calculated from the migratory pathway data obtained from time-lapse images and the data were expressed as Velocity-Directionality (VD) plot. This plot is useful for quantitatively analyzing multiple migrating cells exposed to a certain chemoattractant, and can distinguish chemotaxis from random migration. Moreover precise observation of cell migration revealed that each cell had a different lag period before starting chemotaxis, indicating variation in cell sensitivity to the chemoattractant. Thus lag time of each cell before migration, and time course of increment of the migrating cell ratio at the early stages could be calculated. We also graphed decrement of still moving cell ratio at the later stages by calculating the duration time of cell migration of each cell. These graphs could distinguish different motion patterns of chemotaxis of eosinophils, in response to a range of chemoattractants; PGD(2), fMLP, CCL3, CCL5 and CXCL12. Finally, we compared parameters of eosinophils from normal volunteers, allergy patients and asthma patients and found significant difference in response to PGD(2). The quantitative methods described here could be applicable to image data obtained with any combination of cells and chemoattractants and useful not only for basic studies of chemotaxis but also for diagnosis and for drug screening.

Label-free detection of aggregated platelets in blood by machine-learning-aided optofluidic time-stretch microscopy.

According to WHO, about 10 million new cases of thrombotic disorders are diagnosed worldwide every year. Thrombotic disorders, including atherothrombosis (the leading cause of death in the US and Europe), are induced by occlusion of blood vessels, due to the formation of blood clots in which aggregated platelets play an important role. The presence of aggregated platelets in blood may be related to atherothrombosis (especially acute myocardial infarction) and is, hence, useful as a potential biomarker for the disease. However, conventional high-throughput blood analysers fail to accurately identify aggregated platelets in blood. Here we present an in vitro on-chip assay for label-free, single-cell image-based detection of aggregated platelets in human blood. This assay builds on a combination of optofluidic time-stretch microscopy on a microfluidic chip operating at a high throughput of 10 000 blood cells per second with machine learning, enabling morphology-based identification and enumeration of aggregated platelets in a short period of time. By performing cell classification with machine learning, we differentiate aggregated platelets from single platelets and white blood cells with a high specificity and sensitivity of 96.6% for both. Our results indicate that the assay is potentially promising as predictive diagnosis and therapeutic monitoring of thrombotic disorders in clinical settings.

A novel optical assay system for the quantitative measurement of chemotaxis.

We have developed an optically accessible, horizontal chemotaxis apparatus consisting of an etched silicon substrate and a flat glass plate, both of which form two compartments with a 5-microm-deep microchannel in between. The device is held together with a stainless steel holder with holes for injecting cells and a chemoattractant to the different compartments. Migration of cells in the channel is traced with time-lapse intervals using a CCD camera. By developing a method for aligning cells at the edge of the channel, we could successfully reduce the number of cells required for a chemotactic assay, depending on the experiment, to 100 or less. To prevent ceaseless flow of contents between the adjacent compartments via the communicating microchannel, a space at the top end of the holder was filled with medium after aligning the cells. By using a fluorescent probe, we demonstrated experimentally that a stable concentration gradient could be maintained. Furthermore, we determined theoretical details of the gradient established using a model chemokine and a computational fluid dynamics code. Reproducible kinetic results of cell migration were obtained using human neutrophils and IL-8 as a model. Migration of other cells such as eosinophils, basophils and Jurkat lymphocytes toward the appropriate chemokines were also demonstrated.