Intelligent Image-Activated Cell Sorting

Low latency optical-based mode tracking with machine learning deployed on FPGAs on a tokamak

Active feedback control in magnetic confinement fusion devices is desirable to mitigate plasma instabilities and enable robust operation. Optical high-speed cameras provide a powerful, non-invasive diagnostic and can be suitable for these applications. In this study, we process high-speed camera data, at rates exceeding 100 kfps, on in situ field-programmable gate array (FPGA) hardware to track magnetohydrodynamic (MHD) mode evolution and generate control signals in real time. Our system utilizes a convolutional neural network (CNN) model, which predicts the n = 1 MHD mode amplitude and phase using camera images with better accuracy than other tested non-deep-learning-based methods. By implementing this model directly within the standard FPGA readout hardware of the high-speed camera diagnostic, our mode tracking system achieves a total trigger-to-output latency of 17.6 μs and a throughput of up to 120 kfps. This study at the High Beta Tokamak-Extended Pulse (HBT-EP) experiment demonstrates an FPGA-based high-speed camera data acquisition and processing system, enabling application in real-time machine-learning-based tokamak diagnostic and control as well as potential applications in other scientific domains.

Deep Learning-Based Identification of Intraocular Pressure-Associated Genes Influencing Trabecular Meshwork Cell Morphology

Purpose

Genome-wide association studies have recently uncovered many loci associated with variation in intraocular pressure (IOP). Artificial intelligence (AI) can be used to interrogate the effect of specific genetic knockouts on the morphology of trabecular meshwork cells (TMCs) and thus, IOP regulation.

Design

Experimental study.

Subjects

Primary TMCs collected from human donors.

Methods

Sixty-two genes at 55 loci associated with IOP variation were knocked out in primary TMC lines. All cells underwent high-throughput microscopy imaging after being stained with a 5-channel fluorescent cell staining protocol. A convolutional neural network was trained to distinguish between gene knockout and normal control cell images. The area under the receiver operator curve (AUC) metric was used to quantify morphological variation in gene knockouts to identify potential pathological perturbations.

Main Outcome Measures

Degree of morphological variation as measured by deep learning algorithm accuracy of differentiation from normal controls.

Results

Cells where LTBP2 or BCAS3 had been perturbed demonstrated the greatest morphological variation from normal TMCs (AUC 0.851, standard deviation [SD] 0.030; and AUC 0.845, SD 0.020, respectively). Of 7 multigene loci, 5 had statistically significant differences in AUC (P < 0.05) between genes, allowing for pathological gene prioritization. The mitochondrial channel most frequently showed the greatest degree of morphological variation (33.9% of cell lines).

Conclusions

We demonstrate a robust method for functionally interrogating genome-wide association signals using high-throughput microscopy and AI. Genetic variations inducing marked morphological variation can be readily identified, allowing for the gene-based dissection of loci associated with complex traits.

Financial Disclosures

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Enhancing microalgae classification accuracy in marine ecosystems through convolutional neural networks and support vector machines

Accurately classifying microalgae species is vital for monitoring marine ecosystems and managing the emergence of marine mucilage, which is crucial for monitoring mucilage phenomena in marine environments. Traditional methods have been inadequate due to time-consuming processes and the need for expert knowledge. The purpose of this article is to employ convolutional neural networks (CNNs) and support vector machines (SVMs) to improve classification accuracy and efficiency. By employing advanced computational techniques, including MobileNet and GoogleNet models, alongside SVM classification, the study demonstrates significant advancements over conventional identification methods. In the classification of a dataset consisting of 7820 images using four different SVM kernel functions, the linear kernel achieved the highest success rate at 98.79 %. It is followed by the RBF kernel at 98.73 %, the polynomial kernel at 97.84 %, and the sigmoid kernel at 97.20 %. This research not only provides a methodological framework for future studies in marine biodiversity monitoring but also highlights the potential for real-time applications in ecological conservation and understanding mucilage dynamics amidst climate change and environmental pollution.

Information-Distilled Generative Label-Free Morphological Profiling Encodes Cellular Heterogeneity

Image-based cytometry faces challenges due to technical variations arising from different experimental batches and conditions, such as differences in instrument configurations or image acquisition protocols, impeding genuine biological interpretation of cell morphology. Existing solutions, often necessitating extensive pre-existing data knowledge or control samples across batches, have proved limited, especially with complex cell image data. To overcome this, "Cyto-Morphology Adversarial Distillation" (CytoMAD), a self-supervised multi-task learning strategy that distills biologically relevant cellular morphological information from batch variations, is introduced to enable integrated analysis across multiple data batches without complex data assumptions or extensive manual annotation. Unique to CytoMAD is its "morphology distillation", symbiotically paired with deep-learning image-contrast translation-offering additional interpretable insights into label-free cell morphology. The versatile efficacy of CytoMAD is demonstrated in augmenting the power of biophysical imaging cytometry. It allows integrated label-free classification of human lung cancer cell types and accurately recapitulates their progressive drug responses, even when trained without the drug concentration information. CytoMAD  also allows joint analysis of tumor biophysical cellular heterogeneity, linked to epithelial-mesenchymal plasticity, that standard fluorescence markers overlook. CytoMAD can substantiate the wide adoption of biophysical cytometry for cost-effective diagnosis and screening.

Microfluidic Impedance Cytometry Enabled One-Step Sample Preparation for Efficient Single-Cell Mass Spectrometry

Single-cell mass spectrometry (MS) is significant in biochemical analysis and holds great potential in biomedical applications. Efficient sample preparation like sorting (i.e., separating target cells from the mixed population) and desalting (i.e., moving the cells off non-volatile salt solution) is urgently required in single-cell MS. However, traditional sample preparation methods suffer from complicated operation with various apparatus, or insufficient performance. Herein, a one-step sample preparation strategy by leveraging label-free impedance flow cytometry (IFC) based microfluidics is proposed. Specifically, the IFC framework to characterize and sort single-cells is adopted. Simultaneously with sorting, the target cell is transferred from the local high-salinity buffer to the MS-compatible solution. In this way, one-step sorting and desalting are achieved and the collected cells can be directly fed for MS analysis. A high sorting efficiency (>99%), cancer cell purity (≈87%), and desalting efficiency (>99%), and the whole workflow of impedance-based separation and MS analysis of normal cells (MCF-10A) and cancer cells (MDA-MB-468) are verified. As a standalone sample preparation module, the microfluidic chip is compatible with a variety of MS analysis methods, and envisioned to provide a new paradigm in efficient MS sample preparation, and further in multi-modal (i.e., electrical and metabolic) characterization of single-cells.

High-speed optical imaging with sCMOS pixel reassignment

Fluorescence microscopy has undergone rapid advancements, offering unprecedented visualization of biological events and shedding light on the intricate mechanisms governing living organisms. However, the exploration of rapid biological dynamics still poses a significant challenge due to the limitations of current digital camera architectures and the inherent compromise between imaging speed and other capabilities. Here, we introduce sHAPR, a high-speed acquisition technique that leverages the operating principles of sCMOS cameras to capture fast cellular and subcellular processes. sHAPR harnesses custom fiber optics to convert microscopy images into one-dimensional recordings, enabling acquisition at the maximum camera readout rate, typically between 25 and 250 kHz. We have demonstrated the utility of sHAPR with a variety of phantom and dynamic systems, including high-throughput flow cytometry, cardiomyocyte contraction, and neuronal calcium waves, using a standard epi-fluorescence microscope. sHAPR is highly adaptable and can be integrated into existing microscopy systems without requiring extensive platform modifications. This method pushes the boundaries of current fluorescence imaging capabilities, opening up new avenues for investigating high-speed biological phenomena.

Accessible high-speed image-activated cell sorting

Over the past six decades, fluorescence-activated cell sorting (FACS) has become an essential technology for basic and clinical research by enabling the isolation of cells of interest in high throughput. Recent technological advancements have started a new era of flow cytometry. By combining the spatial resolution of microscopy with high-speed cell sorting, new instruments allow cell sorting based on simple image-derived parameters or sophisticated image analysis algorithms, thereby greatly expanding the scope of applications. In this review, we discuss the systems that are commercially available or have been described in enough methodological and engineering detail to allow their replication. We summarize their strengths and limitations and highlight applications that have the potential to transform various fields in basic life science research and clinical settings.

Classification and counting of cells in brightfield microscopy images: an application of convolutional neural networks

Microscopy is integral to medical research, facilitating the exploration of various biological questions, notably cell quantification. However, this process's time-consuming and error-prone nature, attributed to human intervention or automated methods usually applied to fluorescent images, presents challenges. In response, machine learning algorithms have been integrated into microscopy, automating tasks and constructing predictive models from vast datasets. These models adeptly learn representations for object detection, image segmentation, and target classification. An advantageous strategy involves utilizing unstained images, preserving cell integrity and enabling morphology-based classification-something hindered when fluorescent markers are used. The aim is to introduce a model proficient in classifying distinct cell lineages in digital contrast microscopy images. Additionally, the goal is to create a predictive model identifying lineage and determining optimal quantification of cell numbers. Employing a CNN machine learning algorithm, a classification model predicting cellular lineage achieved a remarkable accuracy of 93%, with ROC curve results nearing 1.0, showcasing robust performance. However, some lineages, namely SH-SY5Y (78%), HUH7_mayv (85%), and A549 (88%), exhibited slightly lower accuracies. These outcomes not only underscore the model's quality but also emphasize CNNs' potential in addressing the inherent complexities of microscopic images.

Dramatic Changes in Mitochondrial Subcellular Location and Morphology Accompany Activation of the CO2 Concentrating Mechanism

Dynamic changes in intracellular ultrastructure can be critical for the ability of organisms to acclimate to environmental conditions. Microalgae, which are responsible for ~50% of global photosynthesis, compartmentalize their Rubisco into a specialized structure known as the pyrenoid when the cells experience limiting CO2 conditions; this compartmentalization appears to be a component of the CO2 Concentrating Mechanism (CCM), which facilitates photosynthetic CO2 fixation as environmental levels of inorganic carbon (Ci) decline. Changes in the spatial distribution of mitochondria in green algae have also been observed under CO2 limiting conditions, although a role for this reorganization in CCM function remains unclear. We used the green microalgae Chlamydomonas reinhardtii to monitor changes in the position and ultrastructure of mitochondrial membranes as cells transition between high CO2 (HC) and Low/Very Low CO2 (LC/VLC). Upon transferring cells to VLC, the mitochondria move from a central to a peripheral location, become wedged between the plasma membrane and chloroplast envelope, and mitochondrial membranes orient in parallel tubular arrays that extend from the cell's apex to its base. We show that these ultrastructural changes require protein and RNA synthesis, occur within 90 min of shifting cells to VLC conditions, correlate with CCM induction and are regulated by the CCM master regulator CIA5. The apico-basal orientation of the mitochondrial membrane, but not the movement of the mitochondrion to the cell periphery, is dependent on microtubules and the MIRO1 protein, which is involved in membrane-microtubule interactions. Furthermore, blocking mitochondrial electron transport in VLC acclimated cells reduces the cell's affinity for inorganic carbon. Overall, our results suggest that CIA5-dependent mitochondrial repositioning/reorientation functions in integrating cellular architecture and energetics with CCM activities and invite further exploration of how intracellular architecture can impact fitness under dynamic environmental conditions.

Imaging Flow Cytometry: Development, Present Applications, and Future Challenges

Imaging flow cytometry (ImFC) represents a significant technological advancement in the field of cytometry, effectively merging the high-throughput capabilities of flow analysis with the detailed imaging characteristics of microscopy. In our comprehensive review, we adopt a historical perspective to chart the development of ImFC, highlighting its origins and current state of the art and forecasting potential future advancements. The genesis of ImFC stemmed from merging the hydraulic system of a flow cytometer with advanced camera technology. This synergistic coupling facilitates the morphological analysis of cell populations at a high-throughput scale, effectively evolving the landscape of cytometry. Nevertheless, ImFC's implementation has encountered hurdles, particularly in developing software capable of managing its sophisticated data acquisition and analysis needs. The scale and complexity of the data generated by ImFC necessitate the creation of novel analytical tools that can effectively manage and interpret these data, thus allowing us to unlock the full potential of ImFC. Notably, artificial intelligence (AI) algorithms have begun to be applied to ImFC, offering promise for enhancing its analytical capabilities. The adaptability and learning capacity of AI may prove to be essential in knowledge mining from the high-dimensional data produced by ImFC, potentially enabling more accurate analyses. Looking forward, we project that ImFC may become an indispensable tool, not only in research laboratories, but also in clinical settings. Given the unique combination of high-throughput cytometry and detailed imaging offered by ImFC, we foresee a critical role for this technology in the next generation of scientific research and diagnostics. As such, we encourage both current and future scientists to consider the integration of ImFC as an addition to their research toolkit and clinical diagnostic routine.

On-the-fly Raman microscopy guaranteeing the accuracy of discrimination

Accelerating the measurement for discrimination of samples, such as classification of cell phenotype, is crucial when faced with significant time and cost constraints. Spontaneous Raman microscopy offers label-free, rich chemical information but suffers from long acquisition time due to extremely small scattering cross-sections. One possible approach to accelerate the measurement is by measuring necessary parts with a suitable number of illumination points. However, how to design these points during measurement remains a challenge. To address this, we developed an imaging technique based on a reinforcement learning in machine learning (ML). This ML approach adaptively feeds back "optimal" illumination pattern during the measurement to detect the existence of specific characteristics of interest, allowing faster measurements while guaranteeing discrimination accuracy. Using a set of Raman images of human follicular thyroid and follicular thyroid carcinoma cells, we showed that our technique requires 3,333 to 31,683 times smaller number of illuminations for discriminating the phenotypes than raster scanning. To quantitatively evaluate the number of illuminations depending on the requisite discrimination accuracy, we prepared a set of polymer bead mixture samples to model anomalous and normal tissues. We then applied a home-built programmable-illumination microscope equipped with our algorithm, and confirmed that the system can discriminate the sample conditions with 104 to 4,350 times smaller number of illuminations compared to standard point illumination Raman microscopy. The proposed algorithm can be applied to other types of microscopy that can control measurement condition on the fly, offering an approach for the acceleration of accurate measurements in various applications including medical diagnosis.

Deep model predictive control of gene expression in thousands of single cells

Gene expression is inherently dynamic, due to complex regulation and stochastic biochemical events. However, the effects of these dynamics on cell phenotypes can be difficult to determine. Researchers have historically been limited to passive observations of natural dynamics, which can preclude studies of elusive and noisy cellular events where large amounts of data are required to reveal statistically significant effects. Here, using recent advances in the fields of machine learning and control theory, we train a deep neural network to accurately predict the response of an optogenetic system in Escherichia coli cells. We then use the network in a deep model predictive control framework to impose arbitrary and cell-specific gene expression dynamics on thousands of single cells in real time, applying the framework to generate complex time-varying patterns. We also showcase the framework's ability to link expression patterns to dynamic functional outcomes by controlling expression of the tetA antibiotic resistance gene. This study highlights how deep learning-enabled feedback control can be used to tailor distributions of gene expression dynamics with high accuracy and throughput without expert knowledge of the biological system.

Light-field flow cytometry for high-resolution, volumetric and multiparametric 3D single-cell analysis

Imaging flow cytometry (IFC) combines flow cytometry and fluorescence microscopy to enable high-throughput, multiparametric single-cell analysis with rich spatial details. However, current IFC techniques remain limited in their ability to reveal subcellular information with a high 3D resolution, throughput, sensitivity, and instrumental simplicity. In this study, we introduce a light-field flow cytometer (LFC), an IFC system capable of high-content, single-shot, and multi-color acquisition of up to 5,750 cells per second with a near-diffraction-limited resolution of 400-600 nm in all three dimensions. The LFC system integrates optical, microfluidic, and computational strategies to facilitate the volumetric visualization of various 3D subcellular characteristics through convenient access to commonly used epi-fluorescence platforms. We demonstrate the effectiveness of LFC in assaying, analyzing, and enumerating intricate subcellular morphology, function, and heterogeneity using various phantoms and biological specimens. The advancement offered by the LFC system presents a promising methodological pathway for broad cell biological and translational discoveries, with the potential for widespread adoption in biomedical research.

Passive microfluidic devices for cell separation

The separation of specific cell populations is instrumental in gaining insights into cellular processes, elucidating disease mechanisms, and advancing applications in tissue engineering, regenerative medicine, diagnostics, and cell therapies. Microfluidic methods for cell separation have propelled the field forward, benefitting from miniaturization, advanced fabrication technologies, a profound understanding of fluid dynamics governing particle separation mechanisms, and a surge in interdisciplinary investigations focused on diverse applications. Cell separation methodologies can be categorized according to their underlying separation mechanisms. Passive microfluidic separation systems rely on channel structures and fluidic rheology, obviating the necessity for external force fields to facilitate label-free cell separation. These passive approaches offer a compelling combination of cost-effectiveness and scalability when compared to active methods that depend on external fields to manipulate cells. This review delves into the extensive utilization of passive microfluidic techniques for cell separation, encompassing various strategies such as filtration, sedimentation, adhesion-based techniques, pinched flow fractionation (PFF), deterministic lateral displacement (DLD), inertial microfluidics, hydrophoresis, viscoelastic microfluidics, and hybrid microfluidics. Besides, the review provides an in-depth discussion concerning cell types, separation markers, and the commercialization of these technologies. Subsequently, it outlines the current challenges faced in the field and presents a forward-looking perspective on potential future developments. This work hopes to aid in facilitating the dissemination of knowledge in cell separation, guiding future research, and informing practical applications across diverse scientific disciplines.

High-throughput microfluidic systems accelerated by artificial intelligence for biomedical applications

High-throughput microfluidic systems are widely used in biomedical fields for tasks like disease detection, drug testing, and material discovery. Despite the great advances in automation and throughput, the large amounts of data generated by the high-throughput microfluidic systems generally outpace the abilities of manual analysis. Recently, the convergence of microfluidic systems and artificial intelligence (AI) has been promising in solving the issue by significantly accelerating the process of data analysis as well as improving the capability of intelligent decision. This review offers a comprehensive introduction on AI methods and outlines the current advances of high-throughput microfluidic systems accelerated by AI, covering biomedical detection, drug screening, and automated system control and design. Furthermore, the challenges and opportunities in this field are critically discussed as well.

Integrating single-cell transcriptomics with cellular phenotypes: cell morphology, Ca2+ imaging and electrophysiology

I review recent technological advancements in coupling single-cell transcriptomics with cellular phenotypes including morphology, calcium signaling, and electrophysiology. Single-cell RNA sequencing (scRNAseq) has revolutionized cell type classifications by capturing the transcriptional diversity of cells. A new wave of methods to integrate scRNAseq and biophysical measurements is facilitating the linkage of transcriptomic data to cellular function, which provides physiological insight into cellular states. I briefly discuss critical factors of these phenotypical characterizations such as timescales, information content, and analytical tools. Dedicated sections focus on the integration with cell morphology, calcium imaging, and electrophysiology (patch-seq), emphasizing their complementary roles. I discuss their application in elucidating cellular states, refining cell type classifications, and uncovering functional differences in cell subtypes. To illustrate the practical applications and benefits of these methods, I highlight their use in tissues with excitable cell-types such as the brain, pancreatic islets, and the retina. The potential of combining functional phenotyping with spatial transcriptomics for a detailed mapping of cell phenotypes in situ is explored. Finally, I discuss open questions and future perspectives, emphasizing the need for a shift towards broader accessibility through increased throughput.

Mapping cancer biology in space: applications and perspectives on spatial omics for oncology

Technologies to decipher cellular biology, such as bulk sequencing technologies and single-cell sequencing technologies, have greatly assisted novel findings in tumor biology. Recent findings in tumor biology suggest that tumors construct architectures that influence the underlying cancerous mechanisms. Increasing research has reported novel techniques to map the tissue in a spatial context or targeted sampling-based characterization and has introduced such technologies to solve oncology regarding tumor heterogeneity, tumor microenvironment, and spatially located biomarkers. In this study, we address spatial technologies that can delineate the omics profile in a spatial context, novel findings discovered via spatial technologies in oncology, and suggest perspectives regarding therapeutic approaches and further technological developments.

Passive Focusing of Single Cells Using Microwell Arrays for High-Accuracy Image-Activated Sorting

Sorting single cells from a population was of critical importance in areas such as cell line development and cell therapy. Image-based sorting is becoming a promising technique for the nonlabeling isolation of cells due to the capability of providing the details of cell morphology. This study reported the focusing of cells using microwell arrays and the following automatic size sorting based on the real-time recognition of cells. The simulation first demonstrated the converged streamlines to the symmetrical plane contributed to the focusing effect. Then, the influence of connecting microchannel, flowing length, particle size, and the sample flow rate on the focusing effect was experimentally analyzed. Both microspheres and cells could be aligned in a straight line at the Reynolds number (Re) of 0.027-0.187 and 0.027-0.08, respectively. The connecting channel was proved to drastically improve the focusing performance. Afterward, a tapered microwell array was utilized to focus sphere/cell spreading in a wide channel to a straight line. Finally, a custom algorithm was employed to identify and sort the size of microspheres/K562 cells with a throughput of 1 event/s and an accuracy of 97.8/97.1%. The proposed technique aligned cells to a straight line at low Reynolds numbers and greatly facilitated the image-activated sorting without the need for a high-speed camera or flow control components with high frequency. Therefore, it is of enormous application potential in the field of nonlabeled separation of single cells.

Single-cell mapping of lipid metabolites using an infrared probe in human-derived model systems

Understanding metabolic heterogeneity is the key to uncovering the underlying mechanisms of metabolic-related diseases. Current metabolic imaging studies suffer from limitations including low resolution and specificity, and the model systems utilized often lack human relevance. Here, we present a single-cell metabolic imaging platform to enable direct imaging of lipid metabolism with high specificity in various human-derived 2D and 3D culture systems. Through the incorporation of an azide-tagged infrared probe, selective detection of newly synthesized lipids in cells and tissue became possible, while simultaneous fluorescence imaging enabled cell-type identification in complex tissues. In proof-of-concept experiments, newly synthesized lipids were directly visualized in human-relevant model systems among different cell types, mutation status, differentiation stages, and over time. We identified upregulated lipid metabolism in progranulin-knockdown human induced pluripotent stem cells and in their differentiated microglia cells. Furthermore, we observed that neurons in brain organoids exhibited a significantly lower lipid metabolism compared to astrocytes.

Graphene oxide aptasensor droplet assay for detection of metabolites secreted by single cells applied to synthetic biology

Synthetic biology harnesses the power of natural microbes by re-engineering metabolic pathways to manufacture desired compounds. Droplet technology has emerged as a high-throughput tool to screen single cells for synthetic biology, while the challenges in sensitive flexible single-cell secretion assay for bioproduction of high-value chemicals remained. Here, a novel droplet modifiable graphene oxide (GO) aptasensor was developed, enabling sensitive flexible detection of different target compounds secreted from single cells. Fluorophore-labeled aptamers were stably anchored on GO through π-π stacking interactions to minimize the non-specific interactions for low-background detection of target compounds with high signal-to-noise ratios. The assay's versatility was exhibited by adapting aptamer sequences to measure metabolic secretions like ATP and naringenin. To show the case, engineered E. coli were constructed for the bioproduction of naringenin. The high signal-to-noise ratio assay (∼2.72) was approached to precisely measure the naringenins secreted from single E. coli in the droplets. Consequently, secretory cells (Gib) were clearly distinguished from wild-type (WT) cells, with a low overlap in cell populations (∼0%) for bioproduction.

Culture-free identification of fast-growing cyanobacteria cells by Raman-activated gravity-driven encapsulation and sequencing

By directly converting solar energy and carbon dioxide into biobased products, cyanobacteria are promising chassis for photosynthetic biosynthesis. To make cyanobacterial photosynthetic biosynthesis technology economically feasible on industrial scales, exploring and engineering cyanobacterial chassis and cell factories with fast growth rates and carbon fixation activities facing environmental stresses are of great significance. To simplify and accelerate the screening for fast-growing cyanobacteria strains, a method called Individual Cyanobacteria Vitality Tests and Screening (iCyanVS) was established. We show that the 13C incorporation ratio of carotenoids can be used to measure differences in cell growth and carbon fixation rates in individual cyanobacterial cells of distinct genotypes that differ in growth rates in bulk cultivations, thus greatly accelerating the process screening for fastest-growing cells. The feasibility of this approach is further demonstrated by phenotypically and then genotypically identifying individual cyanobacterial cells with higher salt tolerance from an artificial mutant library via Raman-activated gravity-driven encapsulation and sequencing. Therefore, this method should find broad applications in growth rate or carbon intake rate based screening of cyanobacteria and other photosynthetic cell factories.

Opportunities and challenges for deep learning in cell dynamics research

The growth of artificial intelligence (AI) has led to an increase in the adoption of computer vision and deep learning (DL) techniques for the evaluation of microscopy images and movies. This adoption has not only addressed hurdles in quantitative analysis of dynamic cell biological processes but has also started to support advances in drug development, precision medicine, and genome-phenome mapping. We survey existing AI-based techniques and tools, as well as open-source datasets, with a specific focus on the computational tasks of segmentation, classification, and tracking of cellular and subcellular structures and dynamics. We summarise long-standing challenges in microscopy video analysis from a computational perspective and review emerging research frontiers and innovative applications for DL-guided automation in cell dynamics research.

Artificial intelligence-enabled quantitative phase imaging methods for life sciences

Quantitative phase imaging, integrated with artificial intelligence, allows for the rapid and label-free investigation of the physiology and pathology of biological systems. This review presents the principles of various two-dimensional and three-dimensional label-free phase imaging techniques that exploit refractive index as an intrinsic optical imaging contrast. In particular, we discuss artificial intelligence-based analysis methodologies for biomedical studies including image enhancement, segmentation of cellular or subcellular structures, classification of types of biological samples and image translation to furnish subcellular and histochemical information from label-free phase images. We also discuss the advantages and challenges of artificial intelligence-enabled quantitative phase imaging analyses, summarize recent notable applications in the life sciences, and cover the potential of this field for basic and industrial research in the life sciences.

Recent advances in deformation-assisted microfluidic cell sorting technologies

Cell sorting is an essential prerequisite for cell research and has great value in life science and clinical studies. Among the many microfluidic cell sorting technologies, label-free methods based on the size of different cell types have been widely studied. However, the heterogeneity in size for cells of the same type and the inevitable size overlap between different types of cells would result in performance degradation in size-based sorting. To tackle such challenges, deformation-assisted technologies are receiving more attention recently. Cell deformability is an inherent biophysical marker of cells that reflects the changes in their internal structures and physiological states. It provides additional dimensional information for cell sorting besides size. Therefore, in this review, we summarize the recent advances in deformation-assisted microfluidic cell sorting technologies. According to how the deformability is characterized and the form in which the force acts, the technologies can be divided into two categories: (1) the indirect category including transit-time-based and image-based methods, and (2) the direct category including microstructure-based and hydrodynamics-based methods. Finally, the separation performance and the application scenarios of each method, the existing challenges and future outlook are discussed. Deformation-assisted microfluidic cell sorting technologies are expected to realize greater potential in the label-free analysis of cells.

C1M2: a universal algorithm for 3D instance segmentation, annotation, and quantification of irregular cells

Cell instance segmentation is a fundamental task for many biological applications, especially for packed cells in three-dimensional (3D) microscope images that can fully display cellular morphology. Image processing algorithms based on neural networks and feature engineering have enabled great progress in two-dimensional (2D) instance segmentation. However, current methods cannot achieve high segmentation accuracy for irregular cells in 3D images. In this study, we introduce a universal, morphology-based 3D instance segmentation algorithm called Crop Once Merge Twice (C1M2), which can segment cells from a wide range of image types and does not require nucleus images. C1M2 can be extended to quantify the fluorescence intensity of fluorescent proteins and antibodies and automatically annotate their expression levels in individual cells. Our results suggest that C1M2 can serve as a tissue cytometry for 3D histopathological assays by quantifying fluorescence intensity with spatial localization and morphological information.

Is AI essential? Examining the need for deep learning in image-activated sorting of Saccharomyces cerevisiae

Artificial intelligence (AI) has become a focal point across a multitude of societal sectors, with science not being an exception. Particularly in the life sciences, imaging flow cytometry has increasingly integrated AI for automated management and categorization of extensive cell image data. However, the necessity of AI over traditional classification methods when extending imaging flow cytometry to include cell sorting remains uncertain, primarily due to the time constraints between image acquisition and sorting actuation. AI-enabled image-activated cell sorting (IACS) methods remain substantially limited, even as recent advancements in IACS have found success while largely relying on traditional feature gating strategies. Here we assess the necessity of AI for image classification in IACS by contrasting the performance of feature gating, classical machine learning (ML), and deep learning (DL) with convolutional neural networks (CNNs) in the differentiation of Saccharomyces cerevisiae mutant images. We show that classical ML could only yield a 2.8-fold enhancement in target enrichment capability, albeit at the cost of a 13.7-fold increase in processing time. Conversely, a CNN could offer an 11.0-fold improvement in enrichment capability at an 11.5-fold increase in processing time. We further executed IACS on mixed mutant populations and quantified target strain enrichment via downstream DNA sequencing to substantiate the applicability of DL for the proposed study. Our findings validate the feasibility and value of employing DL in IACS for morphology-based genetic screening of S. cerevisiae, encouraging its incorporation in future advancements of similar technologies.

COSMOS: a platform for real-time morphology-based, label-free cell sorting using deep learning

Cells are the singular building blocks of life, and a comprehensive understanding of morphology, among other properties, is crucial to the assessment of underlying heterogeneity. We developed Computational Sorting and Mapping of Single Cells (COSMOS), a platform based on Artificial Intelligence (AI) and microfluidics to characterize and sort single cells based on real-time deep learning interpretation of high-resolution brightfield images. Supervised deep learning models were applied to characterize and sort cell lines and dissociated primary tissue based on high-dimensional embedding vectors of morphology without the need for biomarker labels and stains/dyes. We demonstrate COSMOS capabilities with multiple human cell lines and tissue samples. These early results suggest that our neural networks embedding space can capture and recapitulate deep visual characteristics and can be used to efficiently purify unlabeled viable cells with desired morphological traits. Our approach resolves a technical gap in the ability to perform real-time deep learning assessment and sorting of cells based on high-resolution brightfield images.

Computer vision meets microfluidics: a label-free method for high-throughput cell analysis

In this paper, we review the integration of microfluidic chips and computer vision, which has great potential to advance research in the life sciences and biology, particularly in the analysis of cell imaging data. Microfluidic chips enable the generation of large amounts of visual data at the single-cell level, while computer vision techniques can rapidly process and analyze these data to extract valuable information about cellular health and function. One of the key advantages of this integrative approach is that it allows for noninvasive and low-damage cellular characterization, which is important for studying delicate or fragile microbial cells. The use of microfluidic chips provides a highly controlled environment for cell growth and manipulation, minimizes experimental variability and improves the accuracy of data analysis. Computer vision can be used to recognize and analyze target species within heterogeneous microbial populations, which is important for understanding the physiological status of cells in complex biological systems. As hardware and artificial intelligence algorithms continue to improve, computer vision is expected to become an increasingly powerful tool for in situ cell analysis. The use of microelectromechanical devices in combination with microfluidic chips and computer vision could enable the development of label-free, automatic, low-cost, and fast cellular information recognition and the high-throughput analysis of cellular responses to different compounds, for broad applications in fields such as drug discovery, diagnostics, and personalized medicine.

Accumulation of TERT in mitochondria exerts two opposing effects on apoptosis

Telomerase reverse transcriptase (TERT) is a protein that catalyzes the reverse transcription of telomere elongation. TERT is also expected to play a non-canonical role beyond telomere lengthening since it localizes not only in the nucleus but also in mitochondria, where telomeres do not exist. Several studies have reported that mitochondrial TERT regulates apoptosis induced by oxidative stress. However, there is still some controversy as to whether mitochondrial TERT promotes or inhibits apoptosis, mainly due to the lack of information on changes in TERT distribution in individual cells over time. Here, we simultaneously detected apoptosis and TERT localization after oxidative stress in individual HeLa cells by live-cell tracking. Single-cell tracking revealed that the stress-induced accumulation of TERT in mitochondria caused apoptosis, but that accumulation increased over time until cell death. The results suggest a new model in which mitochondrial TERT has two opposing effects at different stages of apoptosis: it predetermines apoptosis at the first stage of cell-fate determination, but also delays apoptosis at the second stage. As such, our data support a model that integrates the two opposing hypotheses on mitochondrial TERT's effect on apoptosis. Furthermore, detailed statistical analysis of TERT mutations, which have been predicted to inhibit TERT transport to mitochondria, revealed that these mutations suppress apoptosis independent of mitochondrial localization of TERT. Together, these results imply that the non-canonical functions of TERT affect a wide range of mitochondria-dependent and mitochondria-independent apoptosis pathways.

High-Throughput Single-Cell Analysis of Nanoparticle-Cell Interactions

Understanding nanoparticle-cell interactions at single-nanoparticle and single-cell resolutions is crucial to improving the design of next-generation nanoparticles for safer, more effective, and more efficient applications in nanomedicine. This review focuses on recent advances in the continuous high-throughput analysis of nanoparticle-cell interactions at the single-cell level. We highlight and discuss the current trends in continual flow high-throughput methods for analyzing single cells, such as advanced flow cytometry techniques and inductively coupled plasma mass spectrometry methods, as well as their intersection in the form of mass cytometry. This review further discusses the challenges and opportunities with current single-cell analysis approaches and provides proposed directions for innovation in the high-throughput analysis of nanoparticle-cell interactions.

Machine learning implementation strategy in imaging and impedance flow cytometry

Imaging and impedance flow cytometry is a label-free technique that has shown promise as a potential replacement for standard flow cytometry. This is due to its ability to provide rich information and archive high-throughput analysis. Recently, significant efforts have been made to leverage machine learning for processing the abundant data generated by those techniques, enabling rapid and accurate analysis. Harnessing the power of machine learning, imaging and impedance flow cytometry has demonstrated its capability to address various complex phenotyping scenarios. Herein, we present a comprehensive overview of the detailed strategies for implementing machine learning in imaging and impedance flow cytometry. We initiate the discussion by outlining the commonly employed setup to acquire the data (i.e., image or signal) from the cell. Subsequently, we delve into the necessary processes for extracting features from the acquired image or signal data. Finally, we discuss how these features can be utilized for cell phenotyping through the application of machine learning algorithms. Furthermore, we discuss the existing challenges and provide insights for future perspectives of intelligent imaging and impedance flow cytometry.

Advanced flow cytometry for biomedical applications

Flow cytometry (FC) is a versatile tool with excellent capabilities to detect and measure multiple characteristics of a population of cells or particles. Notable advancements in in vivo photoacoustic FC, coherent Raman FC, microfluidic FC, and so on, have been achieved in the last two decades, which endows FC with new functions and expands its applications in basic research and clinical practice. Advanced FC broadens the tools available to researchers to conduct research involving cancer detection, microbiology (COVID-19, HIV, bacteria, etc.), and nucleic acid analysis. This review presents an overall picture of advanced flow cytometers and provides not only a clear understanding of their mechanisms but also new insights into their practical applications. We identify the latest trends in this area and aim to raise awareness of advanced techniques of FC. We hope this review expands the applications of FC and accelerates its clinical translation.

Boosting the Brightness of Raman Tags Using Cyanostar Macrocycles

Raman probes have received growing attention for their potential use in super-multiplex biological imaging and flow cytometry applications that cannot be achieved using fluorescent probes. However, obtaining strong Raman scattering signals from small Raman probes has posed a challenge that holds back their practical implementation. Here, we present new types of Raman-active nanoparticles (Rdots) that incorporate ionophore macrocycles, known as cyanostars, to act as ion-driven and structure-directing spacers to address this problem. These macrocycle-enhanced Rdots (MERdots) exhibit sharper and higher electronic absorption peaks than Rdots. When combined with resonant broadband time-domain Raman spectroscopy, these MERdots show a ∼3-fold increase in Raman intensity compared to conventional Rdots under the same particle concentration. Additionally, the detection limit on the concentration of MERdots is improved by a factor of 2.5 compared to that of Rdots and a factor of 430 compared to that of Raman dye molecules in solution. The compact size of MERdots (26 nm in diameter) and their increased Raman signal intensity, along with the broadband capabilities of time-domain resonant Raman spectroscopy, make them promising candidates for a wide range of biological applications.

Revolutionizing microfluidics with artificial intelligence: a new dawn for lab-on-a-chip technologies

Keisuke Goda, Hang Lu, Peng Fei, and Jochen Guck introduce the AI in Microfluidics themed collection, on revolutionizing microfluidics with artificial intelligence: a new dawn for lab-on-a-chip technologies.

Real-time fluorescence imaging flow cytometry enabled by motion deblurring and deep learning algorithms

Fluorescence imaging flow cytometry (IFC) has been demonstrated as a crucial biomedical technique for analyzing specific cell subpopulations from heterogeneous cellular populations. However, the high-speed flow of fluorescent cells leads to motion blur in cell images, making it challenging to identify cell types from the raw images. In this study, we present a real-time single-cell imaging and classification system based on a fluorescence microscope and deep learning algorithm, which is able to directly identify cell types from motion-blur images. To obtain annotated datasets of blurred images for deep learning model training, we developed a motion deblurring algorithm for the reconstruction of blur-free images. To demonstrate the ability of this system, deblurred images of HeLa cells with various fluorescent labels and HeLa cells at different cell cycle stages were acquired. The trained ResNet achieved a high accuracy of 96.6% for single-cell classification of HeLa cells in three different mitotic stages, with a short processing time of only 2 ms. This technology provides a simple way to realize single-cell fluorescence IFC and real-time cell classification, offering significant potential in various biological and medical applications.

Continuous microfluidic flow-through protocol for selective and image-activated electroporation of single cells

Electroporation of cells is a widely-used tool to transport molecules such as proteins or nucleic acids into cells or to extract cellular material. However, bulk methods for electroporation do not offer the possibility to selectively porate subpopulations or single cells in heterogeneous cell samples. To achieve this, either presorting or complex single-cell technologies are required currently. In this work, we present a microfluidic flow protocol for selective electroporation of predefined target cells identified in real-time by high-quality microscopic image analysis of fluorescence and transmitted light. While traveling through the microchannel, the cells are focused by dielectrophoretic forces into the microscopic detection area, where they are classified based on image analysis techniques. Finally, the cells are forwarded to a poration electrode and only the target cells are pulsed. By processing a heterogenically stained cell sample, we were able to selectively porate only target cells (green-fluorescent) while non-target cells (blue-fluorescent) remained unaffected. We achieved highly selective poration with >90% specificity at average poration rates of >50% and throughputs of up to 7200 cells per hour.

High-precision, low-complexity, high-resolution microscopy-based cell sorting

Continuous flow cell sorting based on image analysis is a powerful concept that exploits spatially-resolved features in cells, such as subcellular protein localisation or cell and organelle morphology, to isolate highly specialised cell types that were previously inaccessible to biomedical research, biotechnology, and medicine. Recently, sorting protocols have been proposed that achieve impressive throughput by combining ultra-high flow rates with sophisticated imaging and data processing protocols. However, moderate image quality and high complex experimental setups still prevent the full potential of image-activated cell sorting from being a general-purpose tool. Here, we present a new low-complexity microfluidic approach based on high numerical aperture wide-field microscopy and precise dielectrophoretic cell handling. It provides high-quality images with unprecedented resolution in image-activated cell sorting (i.e., 216 nm). In addition, it also allows long image processing times of several hundred milliseconds for thorough image analysis, while ensuring reliable and low-loss cell processing. Using our approach, we sorted live T cells based on subcellular localisation of fluorescence signals and demonstrated that purities above 80% are possible while targeting maximum yields and sample volume throughputs in the range of μl min^-1. We were able to recover 85% of the target cells analysed. Finally, we ensure and quantify the full vitality of the sorted cells cultivating the cells for a period of time and through colorimetric viability tests.

Rapid Estimation of Size-Based Heterogeneity in Monoclonal Antibodies by Machine Learning-Enhanced Dynamic Light Scattering

Aggregation of monoclonal antibody therapeutics is a serious concern that is believed to impact product safety and efficacy. There is a need for analytical approaches that enable rapid estimation of mAb aggregates. Dynamic light scattering (DLS) is a well-established technique for estimating the average size of protein aggregates or for evaluating sample stability. It is usually used to measure the size and size distribution over a wide range of nano- to micro-sized particles using time-dependent fluctuations in the intensity of scattered light arising from the Brownian motion of particles. In this study, we present a novel DLS-based approach that allows us to quantify the relative percentage of multimers (monomer, dimer, trimer, and tetramer) in a monoclonal antibody (mAb) therapeutic product. The proposed approach uses a machine learning (ML) algorithm and regression to model the system and predict the amount of relevant species such as monomer, dimer, trimer, and tetramer of a mAb in the size range of 10-100 nm. The proposed DLS-ML technique compares favorably to all potential alternatives with respect to the key method attributes, including per sample cost of analysis, per sample time of data acquisition along with ML-based aggregate prediction (<2 min), sample requirements (<3 μg), and user-friendliness of analysis. The proposed rapid method can serve as an orthogonal tool to size exclusion chromatography, which is the current industry workhorse for aggregate assessment.

Dispersive phase microscopy incorporated with droplet-based microfluidics for biofactory-on-a-chip

Biomolecular imaging of intracellular structures of a single cell and subsequent screening of the cells are of high demand in metabolic engineering to develop strains with the desired phenotype. However, the capability of current methods is limited to population-scale identification of cell phenotyping. To address this challenge, we propose to utilize dispersive phase microscopy incorporated with a droplet-based microfluidic system that combines droplet volume-on-demand generation, biomolecular imaging, and droplet-on-demand sorting, to achieve high-throughput screening of cells with an identified phenotype. Particularly, cells are encapsulated in homogeneous environments with microfluidic droplet formation, and the biomolecule-induced dispersive phase can be investigated to indicate the biomass of a specific metabolite in a single cell. The retrieved biomass information consequently guides the on-chip droplet sorting unit to screen cells with the desired phenotype. To demonstrate the proof of concept, we showcase the method by promoting the evolution of the Haematococcus lacustris strain toward a high production of natural antioxidant astaxanthin. The validation of the proposed system with on-chip single-cell imaging and droplet manipulation functionalities reveals the high-throughput single-cell phenotyping and selection potential that applies to many other biofactory scenarios, such as biofuel production, critical quality attribute control in cell therapy, etc.

Microsystem Advances through Integration with Artificial Intelligence

Microfluidics is a rapidly growing discipline that involves studying and manipulating fluids at reduced length scale and volume, typically on the scale of micro- or nanoliters. Under the reduced length scale and larger surface-to-volume ratio, advantages of low reagent consumption, faster reaction kinetics, and more compact systems are evident in microfluidics. However, miniaturization of microfluidic chips and systems introduces challenges of stricter tolerances in designing and controlling them for interdisciplinary applications. Recent advances in artificial intelligence (AI) have brought innovation to microfluidics from design, simulation, automation, and optimization to bioanalysis and data analytics. In microfluidics, the Navier-Stokes equations, which are partial differential equations describing viscous fluid motion that in complete form are known to not have a general analytical solution, can be simplified and have fair performance through numerical approximation due to low inertia and laminar flow. Approximation using neural networks trained by rules of physical knowledge introduces a new possibility to predict the physicochemical nature. The combination of microfluidics and automation can produce large amounts of data, where features and patterns that are difficult to discern by a human can be extracted by machine learning. Therefore, integration with AI introduces the potential to revolutionize the microfluidic workflow by enabling the precision control and automation of data analysis. Deployment of smart microfluidics may be tremendously beneficial in various applications in the future, including high-throughput drug discovery, rapid point-of-care-testing (POCT), and personalized medicine. In this review, we summarize key microfluidic advances integrated with AI and discuss the outlook and possibilities of combining AI and microfluidics.

Algal cell viability assessment: The role of environmental factors in phytoplankton population dynamics

The viability of algal cells is one of the most fundamental issues in marine ecological research. In this work, a method was designed to identify algal cell viability based on digital holography and deep learning, which divided algal cells into three categories: active, weak, and dead cells. This method was applied to measure algal cells in surface waters of the East China Sea in spring, revealing about 4.34 %-23.29 % weak cells and 3.98 %-19.47 % dead cells. Levels of nitrate and chlorophyll a were the main factors affecting the viability of algal cells. Furthermore, algal viability changes during the heating and cooling were observed in laboratory experiments: high temperatures led to an increase in weak algal cells. This may provide an explanation for why most harmful algal blooms occur in warming months. This study provided a novel insight into how to identify the viability of algal cells and understand their significance in the ocean.

A method for real-time mechanical characterisation of microcapsules

Characterising the mechanical properties of flowing microcapsules is important from both fundamental and applied points of view. In the present study, we develop a novel multilayer perceptron (MLP)-based machine learning (ML) approach, for real-time simultaneous predictions of the membrane mechanical law type, shear and area-dilatation moduli of microcapsules, from their camera-recorded steady profiles in tube flow. By MLP, we mean a neural network where many perceptrons are organised into layers. A perceptron is a basic element that conducts input-output mapping operation. We test the performance of the present approach using both simulation and experimental data. We find that with a reasonably high prediction accuracy, our method can reach an unprecedented low prediction latency of less than 1 millisecond on a personal computer. That is the overall computational time, without using parallel computing, from a single experimental image to multiple capsule mechanical parameters. It is faster than a recently proposed convolutional neural network-based approach by two orders of magnitude, for it only deals with the one-dimensional capsule boundary instead of the entire two-dimensional capsule image. Our new approach may serve as the foundation of a promising tool for real-time mechanical characterisation and online active sorting of deformable microcapsules and biological cells in microfluidic devices.

Constructing an In Vitro and In Vivo Flow Cytometry by Fast Line Scanning of Confocal Microscopy

Composed of a fluidic and an optical system, flow cytometry has been widely used for biosensing. The fluidic flow enables its automatic high-throughput sample loading and sorting while the optical system works for molecular detection by fluorescence for micron-level cells and particles. This technology is quite powerful and highly developed; however, it requires a sample in the form of a suspension and thus only works in vitro. In this study, we report a simple scheme to construct a flow cytometry based on a confocal microscope without any modifications. We demonstrate that line scanning of microscopy can effectively excite fluorescence of flowing microbeads or cells in a capillary tube in vitro and in blood vessels of live mice in vivo. This method can resolve microbeads at several microns and the results are comparable to a classic flow cytometer. The absolute diameter of flowing samples can be indicated directly. The sampling limitations and variations of this method is carefully analyzed. This scheme can be easily accomplished by any commercial confocal microscope systems, expands the function of them, and is of promising potential for simultaneous confocal microscopy and in vivo detection of cells in blood vessels of live animals by a single system.

Virtual-freezing fluorescence imaging flow cytometry with 5-aminolevulinic acid stimulation and antibody labeling for detecting all forms of circulating tumor cells

Circulating tumor cells (CTCs) are precursors to cancer metastasis. In blood circulation, they take various forms such as single CTCs, CTC clusters, and CTC-leukocyte clusters, all of which have unique characteristics in terms of physiological function and have been a subject of extensive research in the last several years. Unfortunately, conventional methods are limited in accurately analysing the highly heterogeneous nature of CTCs. Here we present an effective strategy for simultaneously analysing all forms of CTCs in blood by virtual-freezing fluorescence imaging (VIFFI) flow cytometry with 5-aminolevulinic acid (5-ALA) stimulation and antibody labeling. VIFFI is an optomechanical imaging method that virtually freezes the motion of fast-flowing cells on an image sensor to enable high-throughput yet sensitive imaging of every single event. 5-ALA stimulates cancer cells to induce the accumulation of protoporphyrin (PpIX), a red fluorescent substance, making it possible to detect all cancer cells even if they show no expression of the epithelial cell adhesion molecule, a typical CTC biomarker. Although PpIX signals are generally weak, VIFFI flow cytometry can detect them by virtue of its high sensitivity. As a proof-of-principle demonstration of the strategy, we applied cancer cells spiked in blood to the strategy to demonstrate image-based detection and accurate classification of single cancer cells, clusters of cancer cells, and clusters of a cancer cell(s) and a leukocyte(s). To show the clinical utility of our method, we used it to evaluate blood samples of four breast cancer patients and four healthy donors and identified EpCAM-positive PpIX-positive cells in one of the patient samples. Our work paves the way toward the determination of cancer prognosis, the guidance and monitoring of treatment, and the design of antitumor strategies for cancer patients.

Typing of acute leukemia by intelligent optical time-stretch imaging flow cytometry on a chip

Acute leukemia (AL) is one of the top life-threatening diseases. Accurate typing of AL can significantly improve its prognosis. However, conventional methods for AL typing often require cell staining, which is time-consuming and labor-intensive. Furthermore, their performance is highly limited by the specificity and availability of fluorescent labels, which can hardly meet the requirements of AL typing in clinical settings. Here, we demonstrate AL typing by intelligent optical time-stretch (OTS) imaging flow cytometry on a microfluidic chip. Specifically, we employ OTS microscopy to capture the images of cells in clinical bone marrow samples with a spatial resolution of 780 nm at a high flowing speed of 1 m s^-1 in a label-free manner. Then, to show the clinical utility of our method for which the features of clinical samples are diverse, we design and construct a deep convolutional neural network (CNN) to analyze the cellular images and determine the AL type of each sample. We measure 30 clinical samples composed of 7 acute lymphoblastic leukemia (ALL) samples, 17 acute myelogenous leukemia (AML) samples, and 6 samples from healthy donors, resulting in a total of 227 620 images acquired. Results show that our method can distinguish ALL and AML with an accuracy of 95.03%, which, to the best of our knowledge, is a record in label-free AL typing. In addition to AL typing, we believe that the high throughput, high accuracy, and label-free operation of our method make it a potential solution for cell analysis in scientific research and clinical settings.

"SMART" cytology: The next generation cytology for precision diagnosis

Cytology plays an important role in diagnosing and managing human diseases, especially cancer, as it is often a simple, low cost yet effective, and non-invasive or minimally invasive diagnostic tool. However, traditional morphology-based cytology practice has limitations, especially in the era of precision diagnosis. Recently there have been tremendous efforts devoted to apply computational tools and to perform molecular analysis on cytological samples for a variety of clinical purposes. Now is probably the appropriate juncture to integrate morphology, machine learning, and molecular analysis together and transform cytology from a morphology-driven practice to the next level - "SMART" Cytology. In this article we will provide a rather brief review of the relevant works for computational analysis on cytology samples, focusing on single-cell-based multiplex quantitative analysis of biomarkers, and introduce the conceptual framework of "SMART (Single cell, Multiplex, AI-driven, and Real Time)" Cytology.

On monocytes and lymphocytes biolens clustering by in flow holographic microscopy

Live cells act as biological lenses and can be employed as real-world optical components in bio-hybrid systems. Imaging at nanoscale, optical tweezers, lithography and also photonic waveguiding are some of the already proven functionalities, boosted by the advantage that cells are fully biocompatible for intra-body applications. So far, various cell types have been studied for this purpose, such as red blood cells, bacterial cells, stem cells and yeast cells. White Blood Cells (WBCs) play a very important role in the regulation of the human body activities and are usually monitored for assessing its health. WBCs can be considered bio-lenses but, to the best of our knowledge, characterization of their optical properties have not been investigated yet. Here, we report for the first time an accurate study of two model classes of WBCs (i.e., monocytes and lymphocytes) by means of a digital holographic microscope coupled with a microfluidic system, assuming WBCs bio-lens characteristics. Thus, quantitative phase maps for many WBCs have been retrieved in flow-cytometry (FC) by achieving a significant statistical analysis to prove the enhancement in differentiation among sphere-like bio-lenses according to their sizes (i.e., diameter d) exploiting intensity parameters of the modulated light in proximity of the cell optical axis. We show that the measure of the low intensity area (S: I z < I th z ) in a fixed plane, is a feasible parameter for cell clustering, while achieving robustness against experimental misalignments and allowing to adjust the measurement sensitivity in post-processing. 2D scatterplots of the identified parameters (d-S) show better differentiation respect to the 1D case. The results show that the optical focusing properties of WBCs allow the clustering of the two populations by means of a mere morphological analysis, thus leading to the new concept of cell-optical-fingerprint avoiding fluorescent dyes. This perspective can open new routes in biomedical sciences, such as the chance to find optical-biomarkers at single cell level for label-free diagnosis.

Optofluidic imaging meets deep learning: from merging to emerging

Propelled by the striking advances in optical microscopy and deep learning (DL), the role of imaging in lab-on-a-chip has dramatically been transformed from a silo inspection tool to a quantitative "smart" engine. A suite of advanced optical microscopes now enables imaging over a range of spatial scales (from molecules to organisms) and temporal window (from microseconds to hours). On the other hand, the staggering diversity of DL algorithms has revolutionized image processing and analysis at the scale and complexity that were once inconceivable. Recognizing these exciting but overwhelming developments, we provide a timely review of their latest trends in the context of lab-on-a-chip imaging, or coined optofluidic imaging. More importantly, here we discuss the strengths and caveats of how to adopt, reinvent, and integrate these imaging techniques and DL algorithms in order to tailor different lab-on-a-chip applications. In particular, we highlight three areas where the latest advances in lab-on-a-chip imaging and DL can form unique synergisms: image formation, image analytics and intelligent image-guided autonomous lab-on-a-chip. Despite the on-going challenges, we anticipate that they will represent the next frontiers in lab-on-a-chip imaging that will spearhead new capabilities in advancing analytical chemistry research, accelerating biological discovery, and empowering new intelligent clinical applications.