Processing code-multiplexed Coulter signals via deep convolutional neural networks

Microfluidic characterization of single-cell biophysical properties and the applications in cancer diagnosis

Single-cell biophysical properties play a crucial role in regulating cellular physiological states and functions, demonstrating significant potential in the fields of life sciences and clinical diagnostics. Therefore, over the last few decades, researchers have developed various detection tools to explore the relationship between the biophysical changes of biological cells and human diseases. With the rapid advancement of modern microfabrication technology, microfluidic devices have quickly emerged as a promising platform for single-cell analysis offering advantages including high-throughput, exceptional precision, and ease of manipulation. Consequently, this paper provides an overview of the recent advances in microfluidic analysis and detection systems for single-cell biophysical properties and their applications in the field of cancer. The working principles and latest research progress of single-cell biophysical property detection are first analyzed, highlighting the significance of electrical and mechanical properties. The development of data acquisition and processing methods for real-time, high-throughput, and practical applications are then discussed. Furthermore, the differences in biophysical properties between tumor and normal cells are outlined, illustrating the potential for utilizing single-cell biophysical properties for tumor cell identification, classification, and drug response assessment. Lastly, we summarize the limitations of existing microfluidic analysis and detection systems in single-cell biophysical properties, while also pointing out the prospects and future directions of their applications in cancer diagnosis and treatment.

A review on intelligent impedance cytometry systems: Development, applications and advances

Impedance cytometry is a well-established technique for counting and analyzing single cells, with several advantages, such as convenience, high throughput, and no labeling required. A typical experiment consists of the following steps: single-cell measurement, signal processing, data calibration, and particle subtype identification. At the beginning of this article, we compared commercial and self-developed options extensively and provided references for developing reliable detection systems, which are necessary for cell measurement. Then, a number of typical impedance metrics and their relationships to biophysical properties of cells were analyzed with respect to the impedance signal analysis. Given the rapid advances of intelligent impedance cytometry in the past decade, this article also discussed the development of representative machine learning-based approaches and systems, and their applications in data calibration and particle identification. Finally, the remaining challenges facing the field were summarized, and potential future directions for each step of impedance detection were discussed.

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.

Label-free microfluidic cell sorting and detection for rapid blood analysis

Blood tests are considered as standard clinical procedures to screen for markers of diseases and health conditions. However, the complex cellular background (>99.9% RBCs) and biomolecular composition often pose significant technical challenges for accurate blood analysis. An emerging approach for point-of-care blood diagnostics is utilizing "label-free" microfluidic technologies that rely on intrinsic cell properties for blood fractionation and disease detection without any antibody binding. A growing body of clinical evidence has also reported that cellular dysfunction and their biophysical phenotypes are complementary to standard hematoanalyzer analysis (complete blood count) and can provide a more comprehensive health profiling. In this review, we will summarize recent advances in microfluidic label-free separation of different blood cell components including circulating tumor cells, leukocytes, platelets and nanoscale extracellular vesicles. Label-free single cell analysis of intrinsic cell morphology, spectrochemical properties, dielectric parameters and biophysical characteristics as novel blood-based biomarkers will also be presented. Next, we will highlight research efforts that combine label-free microfluidics with machine learning approaches to enhance detection sensitivity and specificity in clinical studies, as well as innovative microfluidic solutions which are capable of fully integrated and label-free blood cell sorting and analysis. Lastly, we will envisage the current challenges and future outlook of label-free microfluidics platforms for high throughput multi-dimensional blood cell analysis to identify non-traditional circulating biomarkers for clinical diagnostics.

Recent advances in non-optical microfluidic platforms for bioparticle detection

The effective analysis of the basic structure and functional information of bioparticles are of great significance for the early diagnosis of diseases. The synergism between microfluidics and particle manipulation/detection technologies offers enhanced system integration capability and test accuracy for the detection of various bioparticles. Most microfluidic detection platforms are based on optical strategies such as fluorescence, absorbance, and image recognition. Although optical microfluidic platforms have proven their capabilities in the practical clinical detection of bioparticles, shortcomings such as expensive components and whole bulky devices have limited their practicality in the development of point-of-care testing (POCT) systems to be used in remote and underdeveloped areas. Therefore, there is an urgent need to develop cost-effective non-optical microfluidic platforms for bioparticle detection that can act as alternatives to optical counterparts. In this review, we first briefly summarise passive and active methods for bioparticle manipulation in microfluidics. Then, we survey the latest progress in non-optical microfluidic strategies based on electrical, magnetic, and acoustic techniques for bioparticle detection. Finally, a perspective is offered, clarifying challenges faced by current non-optical platforms in developing practical POCT devices and clinical applications.

An autonomous microchip for real-time, label-free immune cell analysis

Characterization of cell populations and identification of distinct subtypes based on surface markers are needed in a variety of applications from basic research and clinical assays to cell manufacturing. Conventional immunophenotyping techniques such as flow cytometry or fluorescence microscopy require immunolabeling of cells, expensive and complex instrumentation, skilled operators, and are therefore incompatible with field deployment and automated cell manufacturing systems. In this work, we introduce an autonomous microchip that can electronically quantify the immunophenotypical composition of a cell suspension. Our microchip identifies different cell subtypes by capturing each in different microfluidic chambers functionalized against the markers of the target populations. All on-chip activity is electronically monitored by an integrated sensor network, which informs an algorithm determining subpopulation fractions from chip-wide immunocapture statistics in real time. Moreover, optimal operational conditions within the chip are enforced through a closed-loop feedback control on the sensor data and the cell flow speed, and hence, the antibody-antigen interaction time is maintained within its optimal range for selective immunocapture. We apply our microchip to analyze a mixture of unlabeled CD4⁺ and CD8⁺ T cell sub-populations and then validated the results against flow cytometry measurements. The demonstrated capability to quantitatively analyze immune cells with no labels has the potential to enable not only autonomous biochip-based immunoassays for remote testing but also cell manufacturing bioreactors with built-in, adaptive quality control.

Droplet Detection and Sorting System in Microfluidics: A Review

Since being invented, droplet microfluidic technologies have been proven to be perfect tools for high-throughput chemical and biological functional screening applications, and they have been heavily studied and improved through the past two decades. Each droplet can be used as one single bioreactor to compartmentalize a big material or biological population, so millions of droplets can be individually screened based on demand, while the sorting function could extract the droplets of interest to a separate pool from the main droplet library. In this paper, we reviewed droplet detection and active sorting methods that are currently still being widely used for high-through screening applications in microfluidic systems, including the latest updates regarding each technology. We analyze and summarize the merits and drawbacks of each presented technology and conclude, with our perspectives, on future direction of development.

Deciphering impedance cytometry signals with neural networks

Microfluidic impedance cytometry is a label-free technique for high-throughput single-cell analysis. Multi-frequency impedance measurements provide data that allows full characterisation of cells, linking electrical phenotype to individual biophysical properties. To efficiently extract the information embedded in the electrical signals, potentially in real-time, tailored signal processing is needed. Artificial intelligence approaches provide a promising new direction. Here we demonstrate the ability of neural networks to decipher impedance cytometry signals in two challenging scenarios: (i) to determine the intrinsic dielectric properties of single cells directly from raw impedance data streams, (ii) to capture single-cell signals that are hidden in the measured signals of coincident cells. The accuracy of the results and the high processing speed (fractions of ms per cell) demonstrate that neural networks can have an important role in impedance-based single-cell analysis.

Joint Particle Detection and Analysis by a CNN and Adaptive Norm Minimization Approach

Optical flow cytometry is used as the gold standard in single cell function diagnostics with the drawback of involving high complexity and operator costs. Magnetic flow cytometers try to overcome this problem by replacing optical labeling with magnetic nanoparticles to assign each cell a magnetic fingerprint. This allows operators to obtain rich cell information from a biological sample with minimal sample preparation at near in-vivo conditions in a decentralized environment. A central task in flow cytometry is the determination of cell concentrations and cell parameters, e.g. hydrodynamic diameter. For the acquisition of this information, signal processing is an essential component. Previous approaches mainly focus on the processing of one-cell signals, leaving out superimposed signals originating from cells passing the magnetic sensors in close proximity. In this work, we present a framework for joint cell/particle detection and analysis, which is capable of processing one-cell as well as multi-cell signals. We employ deep learning and compressive sensing in this approach, which involves the minimization of an adaptive norm. We evaluate our method on simulated and experimental signals, the latter being obtained with polymer microparticles. Our results show that the framework is capable of counting cells with a relative error smaller than 2 %. Inference of cell parameters works reliably at both low and high noise levels.

Electronic measurement of cell antigen expression in whole blood

Membrane antigens are phenotypic signatures of cells used for distinguishing various subpopulations and, therefore, are of great interest for diagnosis of diseases and monitoring of patients in hematology and oncology. Existing methods to measure antigen expression of a target subpopulation in blood samples require labor-intensive lysis of contaminating cells and subsequent analysis with complex and bulky instruments in specialized laboratories. To address this long-standing limitation in clinical cytometry, we introduce a microchip-based technique that can directly measure surface expression of target cells in hematological samples. Our microchip isolates an immunomagnetically-labeled target cell population from the contaminating background in whole blood and then utilizes the differential responses of target cells to on-chip magnetic manipulation to estimate their antigen expression. Moreover, manipulating cells with chip-sized permanent magnets and performing quantitative measurements via an on-chip electrical sensor network allows the assay to be performed in a portable platform with no reliance on laboratory infrastructure. Using our technique, we could successfully measure expressions of the CD45 antigen that is commonly expressed by white blood cells, as well as CD34 that is expressed by scarce hematopoietic progenitor cells, which constitutes only ∼0.0001% of all blood cells, directly from whole blood. With our technology, flow cytometry can potentially become a rapid bedside or at-home testing method that is available around the clock in environments where this invaluable assay with proven clinical utility is currently either outsourced or not even accessible.

Neural network-enhanced real-time impedance flow cytometry for single-cell intrinsic characterization

Single-cell impedance flow cytometry (IFC) is emerging as a label-free and non-invasive method for characterizing the electrical properties and revealing sample heterogeneity. At present, most IFC studies utilize phenomenological parameters (e.g., impedance amplitude, phase and opacity) to characterize single cells instead of intrinsic biophysical metrics (e.g., radius r, cytoplasm conductivity σ_i and specific membrane capacitance C_sm). Intrinsic parameters are normally calculated off-line by time-consuming model-fitting methods. Here, we propose to employ neural network (NN)-enhanced IFC to achieve both real-time single-cell intrinsic characterization and intrinsic parameter-based cell classification at high throughput. Three intrinsic parameters (r, σ_i and C_sm) can be obtained online and in real-time via a trained NN at 0.3 ms per single-cell event, achieving significant improvement in calculation speed. Experiments involving four cancer cells and one lymphocyte cell demonstrated 91.5% classification accuracy in the cell type for a test group of 9751 cell samples. By performing a viability assay, we provide evidence that the IFC test per se would not substantially affect the cell property. We envision that the NN-enhanced real-time IFC will provide a new platform for high-throughput, real-time and online cell intrinsic electrical characterization.

Deep Learning Assisted Microfluidic Impedance Flow Cytometry for Label-free Foodborne Bacteria Analysis and Classification. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2021;2021:7087-7090. [PMID: 34892734 DOI: 10.1109/embc46164.2021.9630684] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

According to the urgent need for rapid detection and identification of foodborne bacteria to prevent public health event, a microfluidic electrical impedance flow cytometry assisted with convolutional neural network (ConvNet) based deep learning algorithm was proposed in this study to analyze the impedance signals of bacteria. With the assistance of the deep learning algorithm, Escherichia coli (EPEC), Salmonella enteritidis (SE) and Vibrio parahaemolyticus (VP) were identified with an accuracy of 100%. The proposed impedance based analysis system can be potentially applied for pre-classification of different subtypes of bacteria in a label-free manner.Clinical Relevance-The whole platform can be miniaturized and applied for point-of-care testing (POCT) of pathogenic bacteria detection.

Machine learning assisted fast prediction of inertial lift in microchannels

Inertial effect has been extensively used in manipulating both engineered particles and biocolloids in microfluidic platforms. The design of inertial microfluidic devices largely relies on precise prediction of particle migration that is determined by the inertial lift acting on the particle. In spite of being the only means to accurately obtain the lift forces, direct numerical simulation (DNS) often consumes high computational cost and even becomes impractical when applied to microchannels with complex geometries. Herein, we proposed a fast numerical algorithm in conjunction with machine learning techniques for the analysis and design of inertial microfluidic devices. A database of inertial lift forces was first generated by conducting DNS over a wide range of operating parameters in straight microchannels with three types of cross-sectional shapes, including rectangular, triangular and semicircular shapes. A machine learning assisted model was then developed to gain the inertial lift distribution, by simply specifying the cross-sectional shape, Reynolds number and particle blockage ratio. The resultant inertial lift was integrated into the Lagrangian tracking method to quickly predict the particle trajectories in two types of microchannels in practical devices and yield good agreement with experimental observations. Our database and the associated codes allow researchers to expedite the development of the inertial microfluidic devices for particle manipulation.

Microfluidic impedance cytometry for single-cell sensing: Review on electrode configurations

Single-cell analysis has gained considerable attention for disease diagnosis, drug screening, and differentiation monitoring. Compared to the well-established flow cytometry, which uses fluorescent-labeled antibodies, microfluidic impedance cytometry (MIC) offers a simple, label-free, and noninvasive method for counting, classifying, and monitoring cells. Superior features including a small footprint, low reagent consumption, and ease of use have also been reported. The MIC device detects changes in the impedance signal caused by cells passing through the sensing/electric field zone, which can extract information regarding the size, shape, and dielectric properties of these cells. According to recent studies, electrode configuration has a remarkable effect on detection accuracy, sensitivity, and throughput. With the improvement in microfabrication technology, various electrode configurations have been reported for improving detection accuracy and throughput. However, the various electrode configurations of MIC devices have not been reviewed. In this review, the theoretical background of the impedance technique for single-cell analysis is introduced. Then, two-dimensional, three-dimensional, and liquid electrode configurations are discussed separately; their sensing mechanisms, fabrication processes, advantages, disadvantages, and applications are also described in detail. Finally, the current limitations and future perspectives of these electrode configurations are summarized. The main aim of this review is to offer a guide for researchers on the ongoing advancement in electrode configuration designs.

Closed-loop feedback control of microfluidic cell manipulation via deep-learning integrated sensor networks

Microfluidic technologies have long enabled the manipulation of flow-driven cells en masse under a variety of force fields with the goal of characterizing them or discriminating the pathogenic ones. On the other hand, a microfluidic platform is typically designed to function under optimized conditions, which rarely account for specimen heterogeneity and internal/external perturbations. In this work, we demonstrate a proof-of-principle adaptive microfluidic system that consists of an integrated network of distributed electrical sensors for on-chip tracking of cells and closed-loop feedback control that modulates chip parameters based on the sensor data. In our system, cell flow speed is measured at multiple locations throughout the device, the data is interpreted in real-time via deep learning-based algorithms, and a proportional-integral feedback controller updates a programmable pressure pump to maintain a desired cell flow speed. We validate the adaptive microfluidic system with both static and dynamic targets and also observe a fast convergence of the system under continuous external perturbations. With an ability to sustain optimal processing conditions in unsupervised settings, adaptive microfluidic systems would be less prone to artifacts and could eventually serve as reliable standardized biomedical tests at the point of care.

Single-cell microfluidic impedance cytometry: from raw signals to cell phenotypes using data analytics

The biophysical analysis of single-cells by microfluidic impedance cytometry is emerging as a label-free and high-throughput means to stratify the heterogeneity of cellular systems based on their electrophysiology. Emerging applications range from fundamental life-science and drug assessment research to point-of-care diagnostics and precision medicine. Recently, novel chip designs and data analytic strategies are laying the foundation for multiparametric cell characterization and subpopulation distinction, which are essential to understand biological function, follow disease progression and monitor cell behaviour in microsystems. In this tutorial review, we present a comparative survey of the approaches to elucidate cellular and subcellular features from impedance cytometry data, covering the related subjects of device design, data analytics (i.e., signal processing, dielectric modelling, population clustering), and phenotyping applications. We give special emphasis to the exciting recent developments of the technique (timeframe 2017-2020) and provide our perspective on future challenges and directions. Its synergistic application with microfluidic separation, sensor science and machine learning can form an essential toolkit for label-free quantification and isolation of subpopulations to stratify heterogeneous biosystems.

A Bayesian Approach for Coincidence Resolution in Microfluidic Impedance Cytometry

OBJECTIVE

Cell counting and characterization is fundamental for medicine, science and technology. Coulter-type microfluidic devices are effective and automated systems for cell/particle analysis, based on the electrical sensing zone principle. However, their throughput and accuracy are limited by coincidences (i.e., two or more particles passing through the sensing zone nearly simultaneously), which reduce the observed number of particles and may lead to errors in the measured particle properties. In this work, a novel approach for coincidence resolution in microfluidic impedance cytometry is proposed.

METHODS

The approach relies on: (i) a microchannel comprising two electrical sensing zones and (ii) a model of the signals generated by coinciding particles. Maximum a posteriori probability (MAP) estimation is used to identify the model parameters and therefore characterize individual particle properties.

RESULTS

Quantitative performance assessment on synthetic data streams shows a counting sensitivity of 97% and a positive predictive value of 99% at concentrations of 2×10⁶ particles/ml. An application to red blood cell analysis shows accurate particle characterization up to a throughput of about 2500 particles/s. An original formula providing the expected number of coinciding particles is derived, and good agreement is found between experimental results and theoretical predictions.

CONCLUSION

The proposed cytometer enables the decomposition of signals generated by coinciding particles into individual particle contributions, by using a Bayesian approach.

SIGNIFICANCE

This system can be profitably used in applications where accurate counting and characterization of cell/particle suspensions over a broad range of concentrations is required.

AI on a chip

Artificial intelligence (AI) has dramatically changed the landscape of science, industry, defence, and medicine in the last several years. Supported by considerably enhanced computational power and cloud storage, the field of AI has shifted from mostly theoretical studies in the discipline of computer science to diverse real-life applications such as drug design, material discovery, speech recognition, self-driving cars, advertising, finance, medical imaging, and astronomical observation, where AI-produced outcomes have been proven to be comparable or even superior to the performance of human experts. In these applications, what is essentially important for the development of AI is the data needed for machine learning. Despite its prominent importance, the very first process of the AI development, namely data collection and data preparation, is typically the most laborious task and is often a limiting factor of constructing functional AI algorithms. Lab-on-a-chip technology, in particular microfluidics, is a powerful platform for both the construction and implementation of AI in a large-scale, cost-effective, high-throughput, automated, and multiplexed manner, thereby overcoming the above bottleneck. On this platform, high-throughput imaging is a critical tool as it can generate high-content information (e.g., size, shape, structure, composition, interaction) of objects on a large scale. High-throughput imaging can also be paired with sorting and DNA/RNA sequencing to conduct a massive survey of phenotype-genotype relations whose data is too complex to analyze with traditional computational tools, but is analyzable with the power of AI. In addition to its function as a data provider, lab-on-a-chip technology can also be employed to implement the developed AI for accurate identification, characterization, classification, and prediction of objects in mixed, heterogeneous, or unknown samples. In this review article, motivated by the excellent synergy between AI and lab-on-a-chip technology, we outline fundamental elements, recent advances, future challenges, and emerging opportunities of AI with lab-on-a-chip technology or "AI on a chip" for short.

Early Prediction of Single-Cell Derived Sphere Formation Rate Using Convolutional Neural Network Image Analysis

Functional identification of cancer stem-like cells (CSCs) is an established method to identify and study this cancer subpopulation critical for cancer progression and metastasis. The method is based on the unique capability of single CSCs to survive and grow to tumorspheres in harsh suspension culture environment. Recent advances in microfluidic technology have enabled isolating and culturing thousands of single cells on a chip. However, tumorsphere assay takes a relatively long period of time, limiting the throughput of this assay. In this work, we incorporated machine learning with single-cell analysis to expedite tumorsphere assay. We collected 1,710 single-cell events as the database and trained a convolutional neural network model that predicts whether a single cell could grow to a tumorsphere on Day 14 based on its Day 4 image. With this future-telling model, we precisely estimated the sphere formation rate of SUM159 breast cancer cells to be 17.8% based on Day 4 images. The estimation was close to the ground truth of 17.6% on Day 14. The preliminary work demonstrates not only the feasibility to significantly accelerate tumorsphere assay but also a synergistic combination between single-cell analysis with machine learning, which can be applied to many other biomedical applications.

A neural network approach for real-time particle/cell characterization in microfluidic impedance cytometry

Microfluidic applications such as active particle sorting or selective enrichment require particle classification techniques that are capable of working in real time. In this paper, we explore the use of neural networks for fast label-free particle characterization during microfluidic impedance cytometry. A recurrent neural network is designed to process data from a novel impedance chip layout for enabling real-time multiparametric analysis of the measured impedance data streams. As demonstrated with both synthetic and experimental datasets, the trained network is able to characterize with good accuracy size, velocity, and cross-sectional position of beads, red blood cells, and yeasts, with a unitary prediction time of 0.4 ms. The proposed approach can be extended to other device designs and cell types for electrical parameter extraction. This combination of microfluidic impedance cytometry and machine learning can serve as a stepping stone to real-time single-cell analysis and sorting. Graphical Abstract.

Combinatorial Immunophenotyping of Cell Populations with an Electronic Antibody Microarray

Immunophenotyping is widely used to characterize cell populations in basic research and to diagnose diseases from surface biomarkers in the clinic. This process usually requires complex instruments such as flow cytometers or fluorescence microscopes, which are typically housed in centralized laboratories. Microfluidics are combined with an integrated electrical sensor network to create an antibody microarray for label-free cell immunophenotyping against multiple antigens. The device works by fractionating the sample via capturing target subpopulations in an array of microfluidic chambers functionalized against different antigens and by electrically quantifying the cell capture statistics through a network of code-multiplexed electrical sensors. Through a combinatorial arrangement of antibody sequences along different microfluidic paths, the device can measure the prevalence of different cell subpopulations in a sample from computational analysis of the electrical output signal. The device performance is characterized by analyzing heterogeneous samples of mixed tumor cell populations and then the technique is applied to determine leukocyte subpopulations in blood samples and the results are validated against complete blood cell count and flow cytometry results. Label-free immunophenotyping of cell populations against multiple targets on a disposable electronic chip presents opportunities in global health and telemedicine applications for cell-based diagnostics and health monitoring.