Real-time Image Processing for Microscopy-based Label-free Imaging Flow Cytometry in a Microfluidic Chip

Synthetic gene circuit evolution: Insights and opportunities at the mid-scale

Directed evolution focuses on optimizing single genetic components for predefined engineering goals by artificial mutagenesis and selection. In contrast, experimental evolution studies the adaptation of entire genomes in serially propagated cell populations, to provide an experimental basis for evolutionary theory. There is a relatively unexplored gap at the middle ground between these two techniques, to evolve in vivo entire synthetic gene circuits with nontrivial dynamic function instead of single parts or whole genomes. We discuss the requirements for such mid-scale evolution, with hypothetical examples for evolving synthetic gene circuits by appropriate selection and targeted shuffling of a seed set of genetic components in vivo. Implementing similar methods should aid the rapid generation, functionalization, and optimization of synthetic gene circuits in various organisms and environments, accelerating both the development of biomedical and technological applications and the understanding of principles guiding regulatory network evolution.

Label-free cell classification in holographic flow cytometry through an unbiased learning strategy

Nowadays, label-free imaging flow cytometry at the single-cell level is considered the stepforward lab-on-a-chip technology to address challenges in clinical diagnostics, biology, life sciences and healthcare. In this framework, digital holography in microscopy promises to be a powerful imaging modality thanks to its multi-refocusing and label-free quantitative phase imaging capabilities, along with the encoding of the highest information content within the imaged samples. Moreover, the recent achievements of new data analysis tools for cell classification based on deep/machine learning, combined with holographic imaging, are urging these systems toward the effective implementation of point of care devices. However, the generalization capabilities of learning-based models may be limited from biases caused by data obtained from other holographic imaging settings and/or different processing approaches. In this paper, we propose a combination of a Mask R-CNN to detect the cells, a convolutional auto-encoder, used to the image feature extraction and operating on unlabelled data, thus overcoming the bias due to data coming from different experimental settings, and a feedforward neural network for single cell classification, that operates on the above extracted features. We demonstrate the proposed approach in the challenging classification task related to the identification of drug-resistant endometrial cancer cells.

Deep in situ microscopy for real-time analysis of mammalian cell populations in bioreactors

An in situ microscope based on pulsed transmitted light illumination via optical fiber was combined to artificial-intelligence to enable for the first time an online cell classification according to well-known cellular morphological features. A 848 192-image database generated during a lab-scale production process of antibodies was processed using a convolutional neural network approach chosen for its accurate real-time object detection capabilities. In order to induce different cell death routes, hybridomas were grown in normal or suboptimal conditions in a stirred tank reactor, in the presence of substrate limitation, medium addition, pH regulation problem or oxygen depletion. Using such an optical system made it possible to monitor real-time the evolution of different classes of animal cells, among which viable, necrotic and apoptotic cells. A class of viable cells displaying bulges in feast or famine conditions was also revealed. Considered as a breakthrough in the catalogue of process analytical tools, in situ microscopy powered by artificial-intelligence is also of great interest for research.

Microfluidic Blood Separation: Key Technologies and Critical Figures of Merit

Blood is a complex sample comprised mostly of plasma, red blood cells (RBCs), and other cells whose concentrations correlate to physiological or pathological health conditions. There are also many blood-circulating biomarkers, such as circulating tumor cells (CTCs) and various pathogens, that can be used as measurands to diagnose certain diseases. Microfluidic devices are attractive analytical tools for separating blood components in point-of-care (POC) applications. These platforms have the potential advantage of, among other features, being compact and portable. These features can eventually be exploited in clinics and rapid tests performed in households and low-income scenarios. Microfluidic systems have the added benefit of only needing small volumes of blood drawn from patients (from nanoliters to milliliters) while integrating (within the devices) the steps required before detecting analytes. Hence, these systems will reduce the associated costs of purifying blood components of interest (e.g., specific groups of cells or blood biomarkers) for studying and quantifying collected blood fractions. The microfluidic blood separation field has grown since the 2000s, and important advances have been reported in the last few years. Nonetheless, real POC microfluidic blood separation platforms are still elusive. A widespread consensus on what key figures of merit should be reported to assess the quality and yield of these platforms has not been achieved. Knowing what parameters should be reported for microfluidic blood separations will help achieve that consensus and establish a clear road map to promote further commercialization of these devices and attain real POC applications. This review provides an overview of the separation techniques currently used to separate blood components for higher throughput separations (number of cells or particles per minute). We present a summary of the critical parameters that should be considered when designing such devices and the figures of merit that should be explicitly reported when presenting a device's separation capabilities. Ultimately, reporting the relevant figures of merit will benefit this growing community and help pave the road toward commercialization of these microfluidic systems.

Artificial neural network modelling hydrodenticity for optimal design by microfluidics of polymer nanoparticles to apply in magnetic resonance imaging

The engineering of nanoparticles impacts the control of their nano-bio interactions at each level of the delivery pathway. Therefore, optimal nanoparticle physicochemical properties should be identified to favour on-target interactions and deliver efficiently active compounds to a specific target. To date, traditional batch processes do not guarantee the reproducibility of results and low polydispersity index of the nanostructures, while microfluidics has emerged as cost effectiveness, short-production time approach to control the nanoparticle size and size distribution. Several thermodynamic processes have been implemented in microfluidics, such as nanoprecipitation, ionotropic gelation, self-assembly, etc., to produce nanoparticles in a continuous mode and high throughput way.   In this work, we show how the Artificial Neural Network (ANN) can be adopted to model the impact of microfluidic parameters (namely, flow rates and polymer concentrations) on the size of the nanoparticles. Promising results have been obtained, with the highest model accuracy reaching 98.9 %, thus confirming the proposed approach's potential applicability for an ANN-guided biopolymer nanoparticle design for biomedical applications. Nanostructures with different degrees of complexity are analysed, and a proof-of-concept machine learning approach is proposed to evaluate Hydrodenticity in biopolymer matrices. STATEMENT OF SIGNIFICANCE: Size, shape and surface charge determine nano-bio interactions of nanoparticles and their ability to target diseases. The ideal nanoparticle design avoids off-target interactions and favours on-target interactions. So, tools enabling the identification of the optimal nanoparticle physicochemical properties for delivery to a specific target are required. In this work, we evaluate the use of Artificial Neural Network (ANN) to analyse the role of microfluidic parameters in predicting the optimal size of the different hydrogel nanoparticles and their ability to trigger Hydrodenticity.

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.

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.

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.

The Synergy between Deep Learning and Organs-on-Chips for High-Throughput Drug Screening: A Review

Organs-on-chips (OoCs) are miniature microfluidic systems that have arguably become a class of advanced in vitro models. Deep learning, as an emerging topic in machine learning, has the ability to extract a hidden statistical relationship from the input data. Recently, these two areas have become integrated to achieve synergy for accelerating drug screening. This review provides a brief description of the basic concepts of deep learning used in OoCs and exemplifies the successful use cases for different types of OoCs. These microfluidic chips are of potential to be assembled as highly potent human-on-chips with complex physiological or pathological functions. Finally, we discuss the future supply with perspectives and potential challenges in terms of combining OoCs and deep learning for image processing and automation designs.

Biosensors and machine learning for enhanced detection, stratification, and classification of cells: a review

Biological cells, by definition, are the basic units which contain the fundamental molecules of life of which all living things are composed. Understanding how they function and differentiating cells from one another, therefore, is of paramount importance for disease diagnostics as well as therapeutics. Sensors focusing on the detection and stratification of cells have gained popularity as technological advancements have allowed for the miniaturization of various components inching us closer to Point-of-Care (POC) solutions with each passing day. Furthermore, Machine Learning has allowed for enhancement in the analytical capabilities of these various biosensing modalities, especially the challenging task of classification of cells into various categories using a data-driven approach rather than physics-driven. In this review, we provide an account of how Machine Learning has been applied explicitly to sensors that detect and classify cells. We also provide a comparison of how different sensing modalities and algorithms affect the classifier accuracy and the dataset size required.

Microfluidic flow cytometry for blood-based biomarker analysis

Flow cytometry has proven its capability for rapid and quantitative analysis of individual cells and the separation of targeted biological samples from others. The emerging microfluidics technology makes it possible to develop portable microfluidic diagnostic devices for point-of-care testing (POCT) applications. Microfluidic flow cytometry (MFCM), where flow cytometry and microfluidics are combined to achieve similar or even superior functionalities on microfluidic chips, provides a powerful single-cell characterisation and sorting tool for various biological samples. In recent years, researchers have made great progress in the development of the MFCM including focusing, detecting, and sorting subsystems, and its unique capabilities have been demonstrated in various biological applications. Moreover, liquid biopsy using blood can provide various physiological and pathological information. Thus, biomarkers from blood are regarded as meaningful circulating transporters of signal molecules or particles and have great potential to be used as non (or minimally)-invasive diagnostic tools. In this review, we summarise the recent progress of the key subsystems for MFCM and its achievements in blood-based biomarker analysis. Finally, foresight is offered to highlight the research challenges faced by MFCM in expanding into blood-based POCT applications, potentially yielding commercialisation opportunities.

CellNet: A Lightweight Model towards Accurate LOC-Based High-Speed Cell Detection

Label-free cell separation and sorting in a microfluidic system, an essential technique for modern cancer diagnosis, resulted in high-throughput single-cell analysis becoming a reality. However, designing an efficient cell detection model is challenging. Traditional cell detection methods are subject to occlusion boundaries and weak textures, resulting in poor performance. Modern detection models based on convolutional neural networks (CNNs) have achieved promising results at the cost of a large number of both parameters and floating point operations (FLOPs). In this work, we present a lightweight, yet powerful cell detection model named CellNet, which includes two efficient modules, CellConv blocks and the h-swish nonlinearity function. CellConv is proposed as an effective feature extractor as a substitute to computationally expensive convolutional layers, whereas the h-swish function is introduced to increase the nonlinearity of the compact model. To boost the prediction and localization ability of the detection model, we re-designed the model’s multi-task loss function. In comparison with other efficient object detection methods, our approach achieved state-of-the-art 98.70% mean average precision (mAP) on our custom sea urchin embryos dataset with only 0.08 M parameters and 0.10 B FLOPs, reducing the size of the model by 39.5× and the computational cost by 4.6×. We deployed CellNet on different platforms to verify its efficiency. The inference speed on a graphics processing unit (GPU) was 500.0 fps compared with 87.7 fps on a CPU. Additionally, CellNet is 769.5-times smaller and 420 fps faster than YOLOv3. Extensive experimental results demonstrate that CellNet can achieve an excellent efficiency/accuracy trade-off on resource-constrained platforms.

Deterministic Lateral Displacement (DLD) Analysis Tool Utilizing Machine Learning towards High-Throughput Separation

Deterministic lateral displacement (DLD) is a microfluidic method for the continuous separation of particles based on their size. There is growing interest in using DLD for harvesting circulating tumor cells from blood for further assays due to its low cost and robustness. While DLD is a powerful tool and development of high-throughput DLD separation devices holds great promise in cancer diagnostics and therapeutics, much of the experimental data analysis in DLD research still relies on error-prone and time-consuming manual processes. There is a strong need to automate data analysis in microfluidic devices to reduce human errors and the manual processing time. In this work, a reliable particle detection method is developed as the basis for the DLD separation analysis. Python and its available packages are used for machine vision techniques, along with existing identification methods and machine learning models. Three machine learning techniques are implemented and compared in the determination of the DLD separation mode. The program provides a significant reduction in video analysis time in DLD separation, achieving an overall particle detection accuracy of 97.86% with an average computation time of 25.274 s.

Fast custom wavelet analysis technique for single molecule detection and identification

Many sensors operate by detecting and identifying individual events in a time-dependent signal which is challenging if signals are weak and background noise is present. We introduce a powerful, fast, and robust signal analysis technique based on a massively parallel continuous wavelet transform (CWT) algorithm. The superiority of this approach is demonstrated with fluorescence signals from a chip-based, optofluidic single particle sensor. The technique is more accurate than simple peak-finding algorithms and several orders of magnitude faster than existing CWT methods, allowing for real-time data analysis during sensing for the first time. Performance is further increased by applying a custom wavelet to multi-peak signals as demonstrated using amplification-free detection of single bacterial DNAs. A 4x increase in detection rate, a 6x improved error rate, and the ability for extraction of experimental parameters are demonstrated. This cluster-based CWT analysis will enable high-performance, real-time sensing when signal-to-noise is hardware limited, for instance with low-cost sensors in point of care environments.

The authors introduce an accurate, fast and efficient technique to analyze sensory data. They use a continuous wavelet transform concept to look for certain patterns in noisy raw data. The superiority of this approach is demonstrated with fluorescence signals from a chip-based, optofluidic single particle sensor.

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.

Multispectral Imaging Flow Cytometry with Spatially and Spectrally Resolving Snapshot-Mosaic Cameras for the Characterization and Classification of Bioparticles

In the development and optimization of biotechnological cultivation processes the continuous monitoring through the acquisition and interpretation of spectral and morphological properties of bioparticles are challenging. There is therefore a need for the parallel acquisition and interpretation of spatially and spectrally resolved measurements with which particles can be characterized and classified in-flow with high throughput. Therefore, in this paper we investigated the scientific and technological connectivity of standard imaging flow cytometry (IFC) with filter-on-chip based spatially and spectrally resolving snapshot-mosaic cameras for photonic sensing and control in a smart and innovative microfluidic device. For the investigations presented here we used the microalgae Haematococcus pluvialis (HP). These microalgae are used commercially to produce the antioxidant keto-carotenoid astaxanthin. Therefore, HP is relevant to practically demonstrate the usability of the developed system for Multispectral Imaging Flow Cytometry (MIFC) platform. The extension of standard IFC with snapshot-mosaic cameras and multivariate data processing is an innovative approach for the in-flow characterization and derived classification of bioparticles. Finally, the multispectral data acquisition and the therefore developed methodology is generalizable and enables further applications far beyond the here characterized population of HP cells.

Exploiting machine learning for bestowing intelligence to microfluidics

Intelligent microfluidics is an emerging cross-discipline research area formed by combining microfluidics with machine learning. It uses the advantages of microfluidics, such as high throughput and controllability, and the powerful data processing capabilities of machine learning, resulting in improved systems in biotechnology and chemistry. Compared to traditional microfluidics using manual analysis methods, intelligent microfluidics needs less human intervention, and results in a more user-friendly experience with faster processing. There is a paucity of literature reviewing this burgeoning and highly promising cross-discipline. Therefore, we herein comprehensively and systematically summarize several aspects of microfluidic applications enabled by machine learning. We list the types of microfluidics used in intelligent microfluidic applications over the last five years, as well as the machine learning algorithms and the hardware used for training. We also present the most recent advances in key technologies, developments, challenges, and the emerging opportunities created by intelligent microfluidics.

Progressive use of multispectral imaging flow cytometry in various research areas

Multi-spectral imaging flow cytometry (MIFC) has become one of the most powerful technologies for investigating general analytics, molecular and cell biology, biotechnology, medicine, and related fields. It combines the capabilities of the morphometric and photometric analysis of single cells and micrometer-sized particles in flux with regard to thousands of events. It has become the tool of choice for a wide range of research and clinical applications. By combining the features of flow cytometry and fluorescence microscopy, it offers researchers the ability to couple the spatial resolution of multicolour images of cells and organelles with the simultaneous analysis of a large number of events in a single system. This provides the opportunity to visually confirm findings and collect novel data that would otherwise be more difficult to obtain. This has led many researchers to design innovative assays to gain new insight into important research questions. To date, it has been successfully used to study cell morphology, surface and nuclear protein co-localization, protein-protein interactions, cell signaling, cell cycle, cell death, and cytotoxicity, intracellular calcium, drug uptake, pathogen internalization, and other applications. Herein we describe some of the recent advances in the field of multiparametric imaging flow cytometry methods in various research areas.

Chips for Biomaterials and Biomaterials for Chips: Recent Advances at the Interface between Microfabrication and Biomaterials Research

In recent years, the use of microfabrication techniques has allowed biomaterials studies which were originally carried out at larger length scales to be miniaturized as so-called "on-chip" experiments. These miniaturized experiments have a range of advantages which have led to an increase in their popularity. A range of biomaterial shapes and compositions are synthesized or manufactured on chip. Moreover, chips are developed to investigate specific aspects of interactions between biomaterials and biological systems. Finally, biomaterials are used in microfabricated devices to replicate the physiological microenvironment in studies using so-called "organ-on-chip," "tissue-on-chip" or "disease-on-chip" models, which can reduce the use of animal models with their inherent high cost and ethical issues, and due to the possible use of human cells can increase the translation of research from lab to clinic. This review gives an overview of recent developments at the interface between microfabrication and biomaterials science, and indicates potential future directions that the field may take. In particular, a trend toward increased scale and automation is apparent, allowing both industrial production of micron-scale biomaterials and high-throughput screening of the interaction of diverse materials libraries with cells and bioengineered tissues and organs.

Deep Learning-Enabled Label-Free On-Chip Detection and Selective Extraction of Cell Aggregate-Laden Hydrogel Microcapsules

Microfluidic encapsulation of cells/tissues in hydrogel microcapsules has attracted tremendous attention in the burgeoning field of cell-based medicine. However, when encapsulating rare cells and tissues (e.g., pancreatic islets and ovarian follicles), the majority of the resultant hydrogel microcapsules are empty and should be excluded from the sample. Furthermore, the cell-laden hydrogel microcapsules are usually suspended in an oil phase after microfluidic generation, while the microencapsulated cells require an aqueous phase for further culture/transplantation and long-term suspension in oil may compromise the cells/tissues. Thus, real-time on-chip selective extraction of cell-laden hydrogel microcapsules from oil into aqueous phase is crucial to the further use of the microencapsulated cells/tissues. Contemporary extraction methods either require labeling of cells for their identification along with an expensive detection system or have a low extraction purity (<≈30%). Here, a deep learning-enabled approach for label-free detection and selective extraction of cell-laden microcapsules with high efficiency of detection (≈100%) and extraction (≈97%), high purity of extraction (≈90%), and high cell viability (>95%) is reported. The utilization of deep learning to dynamically analyze images in real time for label-free detection and on-chip selective extraction of cell-laden hydrogel microcapsules is unique and may be valuable to advance the emerging cell-based medicine.

Rapid capture of biomolecules from blood via stimuli-responsive elastomeric particles for acoustofluidic separation

The detection of biomarkers in blood often requires extensive and time-consuming sample preparation to remove blood cells and concentrate the biomarker(s) of interest. We demonstrate proof-of-concept for a chip-based, acoustofluidic method that enables the rapid capture and isolation of a model protein biomarker (i.e., streptavidin) from blood for off-chip quantification. Our approach makes use of two key components - namely, soluble, thermally responsive polypeptides fused to ligands for the homogeneous capture of biomarkers from whole blood and silicone microparticles functionalized with similar, tethered, thermally responsive polypeptides. When the two components are mixed together and subjected to a mild thermal trigger, the thermally responsive moieties undergo a phase transition, causing the untethered (soluble) polypeptides to co-aggregate with the particle-bound polypeptides. The mixture is then diluted with warm buffer and injected into a microfluidic channel supporting a bulk acoustic standing wave. The biomarker-bearing particles migrate to the pressure antinodes, whereas blood cells migrate to the pressure node, leading to rapid separation with efficiencies exceeding 90% in a single pass. The biomarker-bearing particles can then be analyzed via flow cytometry, with a limit of detection of 0.75 nM for streptavidin spiked in blood plasma. Finally, by cooling the solution below the solubility temperature of the polypeptides, greater than 75% of the streptavidin is released from the microparticles, offering a unique approach for downstream analysis (e.g., sequencing or structural analysis). Overall, this methodology has promise for the detection, enrichment and analysis of some biomarkers from blood and other complex biological samples.

Blind Deconvolution Based on Compressed Sensing with bi-l0-l2-norm Regularization in Light Microscopy Image

Blind deconvolution of light microscopy images could improve the ability of distinguishing cell-level substances. In this study, we investigated the blind deconvolution framework for a light microscope image, which combines the benefits of bi-l₀-l₂-norm regularization with compressed sensing and conjugated gradient algorithms. Several existing regularization approaches were limited by staircase artifacts (or cartooned artifacts) and noise amplification. Thus, we implemented our strategy to overcome these problems using the bi-l₀-l₂-norm regularization proposed. It was investigated through simulations and experiments using optical microscopy images including the background noise. The sharpness was improved through the successful image restoration while minimizing the noise amplification. In addition, quantitative factors of the restored images, including the intensity profile, root-mean-square error (RMSE), edge preservation index (EPI), structural similarity index measure (SSIM), and normalized noise power spectrum, were improved compared to those of existing or comparative images. In particular, the results of using the proposed method showed RMSE, EPI, and SSIM values of approximately 0.12, 0.81, and 0.88 when compared with the reference. In addition, RMSE, EPI, and SSIM values in the restored image were proven to be improved by about 5.97, 1.26, and 1.61 times compared with the degraded image. Consequently, the proposed method is expected to be effective for image restoration and to reduce the cost of a high-performance light microscope.

Deep learning-enabled imaging flow cytometry for high-speed Cryptosporidium and Giardia detection

Imaging flow cytometry has become a popular technology for bioparticle image analysis because of its capability of capturing thousands of images per second. Nevertheless, the vast number of images generated by imaging flow cytometry imposes great challenges for data analysis especially when the species have similar morphologies. In this work, we report a deep learning-enabled high-throughput system for predicting Cryptosporidium and Giardia in drinking water. This system combines imaging flow cytometry and an efficient artificial neural network called MCellNet, which achieves a classification accuracy >99.6%. The system can detect Cryptosporidium and Giardia with a sensitivity of 97.37% and a specificity of 99.95%. The high-speed analysis reaches 346 frames per second, outperforming the state-of-the-art deep learning algorithm MobileNetV2 in speed (251 frames per second) with a comparable classification accuracy. The reported system empowers rapid, accurate, and high throughput bioparticle detection in clinical diagnostics, environmental monitoring and other potential biosensing applications.

Microfluidics in Biotechnology: Quo Vadis

The emerging technique of microfluidics offers new approaches for precisely controlling fluidic conditions on a small scale, while simultaneously facilitating data collection in both high-throughput and quantitative manners. As such, the so-called lab-on-a-chip (LOC) systems have the potential to revolutionize the field of biotechnology. But what needs to happen in order to truly integrate them into routine biotechnological applications? In this chapter, some of the most promising applications of microfluidic technology within the field of biotechnology are surveyed, and a few strategies for overcoming current challenges posed by microfluidic LOC systems are examined. In addition, we also discuss the intensifying trend (across all biotechnology fields) of using point-of-use applications which is being facilitated by new technological achievements.

Machine learning issues and opportunities in ultrafast particle classification for label-free microflow cytometry

Machine learning offers promising solutions for high-throughput single-particle analysis in label-free imaging microflow cytomtery. However, the throughput of online operations such as cell sorting is often limited by the large computational cost of the image analysis while offline operations may require the storage of an exceedingly large amount of data. Moreover, the training of machine learning systems can be easily biased by slight drifts of the measurement conditions, giving rise to a significant but difficult to detect degradation of the learned operations. We propose a simple and versatile machine learning approach to perform microparticle classification at an extremely low computational cost, showing good generalization over large variations in particle position. We present proof-of-principle classification of interference patterns projected by flowing transparent PMMA microbeads with diameters of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${15.2}\,\upmu \text {m}$$\end{document}15.2μm and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${18.6}\,\upmu \text {m}$$\end{document}18.6μm. To this end, a simple, cheap and compact label-free microflow cytometer is employed. We also discuss in detail the detection and prevention of machine learning bias in training and testing due to slight drifts of the measurement conditions. Moreover, we investigate the implications of modifying the projected particle pattern by means of a diffraction grating, in the context of optical extreme learning machine implementations.

An inexpensive microfluidic device for three-dimensional hydrodynamic focusing in imaging flow cytometry

We present design, characterization, and testing of an inexpensive, sheath-flow based microfluidic device for three-dimensional (3D) hydrodynamic focusing of cells in imaging flow cytometry. In contrast to other 3D sheathing devices, our device hydrodynamically focuses the cells in a single-file near the bottom wall of the microchannel that allows imaging cells with high magnification and low working distance objectives, without the need for small device dimensions. The relatively large dimensions of the microchannels enable easy fabrication using less-precise fabrication techniques, and the simplicity of the device design avoids the need for tedious alignment of various layers. We have characterized the performance of the device with 3D numerical simulations and validated these simulations with experiments of hydrodynamic focusing of a fluorescently dyed sample fluid. The simulations show that the width and the height of the 3D focused sample stream can be controlled independently by varying the heights of main and side channels of the device, and the flow rates of sample and sheath fluids. Based on simulations, we also provide useful guidelines for choosing the device dimensions and flow rates for focusing cells of a particular size. Thereafter, we demonstrate the applicability of our device for imaging a large number of RBCs using brightfield microscopy. We also discuss the choice of the region of interest and camera frame rate so as to image each cell individually in our device. The design of our microfluidic device makes it equally applicable for imaging cells of different sizes using various other imaging techniques such as phase-contrast and fluorescence microscopy.

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.

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.

Classifying T cell activity in autofluorescence intensity images with convolutional neural networks

The importance of T cells in immunotherapy has motivated developing technologies to improve therapeutic efficacy. One objective is assessing antigen-induced T cell activation because only functionally active T cells are capable of killing the desired targets. Autofluorescence imaging can distinguish T cell activity states in a non-destructive manner by detecting endogenous changes in metabolic co-enzymes such as NAD(P)H. However, recognizing robust activity patterns is computationally challenging in the absence of exogenous labels. We demonstrate machine learning methods that can accurately classify T cell activity across human donors from NAD(P)H intensity images. Using 8260 cropped single-cell images from six donors, we evaluate classifiers ranging from traditional models that use previously-extracted image features to convolutional neural networks (CNNs) pre-trained on general non-biological images. Adapting pre-trained CNNs for the T cell activity classification task provides substantially better performance than traditional models or a simple CNN trained with the autofluorescence images alone. Visualizing the images with dimension reduction provides intuition into why the CNNs achieve higher accuracy than other approaches. Our image processing and classifier training software is available at https://github.com/gitter-lab/t-cell-classification.

High-speed device synchronization in optical microscopy with an open-source hardware control platform

Azimuthal beam scanning eliminates the uneven excitation field arising from laser interference in through-objective total internal reflection fluorescence (TIRF) microscopy. The same principle can be applied to scanning angle interference microscopy (SAIM), where precision control of the scanned laser beam presents unique technical challenges for the builders of custom azimuthal scanning microscopes. Accurate synchronization between the instrument computer, beam scanning system and excitation source is required to collect high quality data and minimize sample damage in SAIM acquisitions. Drawing inspiration from open-source prototyping systems, like the Arduino microcontroller boards, we developed a new instrument control platform to be affordable, easily programmed, and broadly useful, but with integrated, precision analog circuitry and optimized firmware routines tailored to advanced microscopy. We show how the integration of waveform generation, multiplexed analog outputs, and native hardware triggers into a single central hub provides a versatile platform for performing fast circle-scanning acquisitions, including azimuthal scanning SAIM and multiangle TIRF. We also demonstrate how the low communication latency of our hardware platform can reduce image intensity and reconstruction artifacts arising from synchronization errors produced by software control. Our complete platform, including hardware design, firmware, API, and software, is available online for community-based development and collaboration.

Cell Cytometry: Review and Perspective on Biotechnological Advances

Cell identification and enumeration are essential procedures within clinical and research laboratories. For over 150 years, quantitative investigation of body fluids such as counts of various blood cells has been an important tool for diagnostic analysis. With the current evolution of point-of-care diagnostics and precision medicine, cheap and precise cell counting technologies are in demand. This article reviews the timeline and recent notable advancements in cell counting that have occurred as a result of improvements in sensing including optical and electrical technology, enhancements in image processing capabilities, and contributions of micro and nanotechnologies. Cell enumeration methods have evolved from the use of manual counting using a hemocytometer to automated cell counters capable of providing reliable counts with high precision and throughput. These developments have been enabled by the use of precision engineering, micro and nanotechnology approaches, automation and multivariate data analysis. Commercially available automated cell counters can be broadly classified into three categories based on the principle of detection namely, electrical impedance, optical analysis and image analysis. These technologies have many common scientific uses, such as hematological analysis, urine analysis and bacterial enumeration. In addition to commercially available technologies, future technological trends using lab-on-a-chip devices have been discussed in detail. Lab-on-a-chip platforms utilize the existing three detection technologies with innovative design changes utilizing advanced nano/microfabrication to produce customized devices suited to specific applications.

COMBImage2: a parallel computational framework for higher-order drug combination analysis that includes automated plate design, matched filter based object counting and temporal data mining

BACKGROUND

Pharmacological treatment of complex diseases using more than two drugs is commonplace in the clinic due to better efficacy, decreased toxicity and reduced risk for developing resistance. However, many of these higher-order treatments have not undergone any detailed preceding in vitro evaluation that could support their therapeutic potential and reveal disease related insights. Despite the increased medical need for discovery and development of higher-order drug combinations, very few reports from systematic large-scale studies along this direction exist. A major reason is lack of computational tools that enable automated design and analysis of exhaustive drug combination experiments, where all possible subsets among a panel of pre-selected drugs have to be evaluated.

RESULTS

Motivated by this, we developed COMBImage2, a parallel computational framework for higher-order drug combination analysis. COMBImage2 goes far beyond its predecessor COMBImage in many different ways. In particular, it offers automated 384-well plate design, as well as quality control that involves resampling statistics and inter-plate analyses. Moreover, it is equipped with a generic matched filter based object counting method that is currently designed for apoptotic-like cells. Furthermore, apart from higher-order synergy analyses, COMBImage2 introduces a novel data mining approach for identifying interesting temporal response patterns and disentangling higher- from lower- and single-drug effects. COMBImage2 was employed in the context of a small pilot study focused on the CUSP9v4 protocol, which is currently used in the clinic for treatment of recurrent glioblastoma. For the first time, all 246 possible combinations of order 4 or lower of the 9 single drugs consisting the CUSP9v4 cocktail, were evaluated on an in vitro clonal culture of glioma initiating cells.

CONCLUSIONS

COMBImage2 is able to automatically design and robustly analyze exhaustive and in general higher-order drug combination experiments. Such a versatile video microscopy oriented framework is likely to enable, guide and accelerate systematic large-scale drug combination studies not only for cancer but also other diseases.

Deep Learning in Image Cytometry: A Review

Artificial intelligence, deep convolutional neural networks, and deep learning are all niche terms that are increasingly appearing in scientific presentations as well as in the general media. In this review, we focus on deep learning and how it is applied to microscopy image data of cells and tissue samples. Starting with an analogy to neuroscience, we aim to give the reader an overview of the key concepts of neural networks, and an understanding of how deep learning differs from more classical approaches for extracting information from image data. We aim to increase the understanding of these methods, while highlighting considerations regarding input data requirements, computational resources, challenges, and limitations. We do not provide a full manual for applying these methods to your own data, but rather review previously published articles on deep learning in image cytometry, and guide the readers toward further reading on specific networks and methods, including new methods not yet applied to cytometry data. © 2018 The Authors. Cytometry Part A published by Wiley Periodicals, Inc. on behalf of International Society for Advancement of Cytometry.

Coding of Experimental Conditions in Microfluidic Droplet Assays Using Colored Beads and Machine Learning Supported Image Analysis

To efficiently exploit the potential of several millions of droplets that can be considered as individual bioreactors in microfluidic experiments, methods to encode different experimental conditions in droplets are needed. The approach presented here is based on coencapsulation of colored polystyrene beads with biological samples. The decoding of the droplets, as well as content quantification, are performed by automated analysis of triggered images of individual droplets in-flow using bright-field microscopy. The decoding strategy combines bead classification using a random forest classifier and Bayesian inference to identify different codes and thus experimental conditions. Antibiotic susceptibility testing of nine different antibiotics and the determination of the minimal inhibitory concentration of a specific antibiotic against a laboratory strain of Escherichia coli are presented as a proof-of-principle. It is demonstrated that this method allows successful encoding and decoding of 20 different experimental conditions within a large droplet population of more than 10⁵ droplets per condition. The decoding strategy correctly assigns 99.6% of droplets to the correct condition and a method for the determination of minimal inhibitory concentration using droplet microfluidics is established. The current encoding and decoding pipeline can readily be extended to more codes by adding more bead colors or color combinations.

CSSTag: Optical Nanoscale Radar and Particle Tracking for In-Body and Microfluidic Systems With Vibrating Graphene and Resonance Energy Transfer

Biological particle tracking systems monitor cellular processes or particle behaviors with the great accuracy. The emissions of fluorescent molecules or direct images of particles are captured with cameras or photodetectors. The current imaging systems have challenges in detection, collection, and analysis of imaging data, penetration depth, and complicated set-ups. In this paper, a signaling-based nanoscale acousto-optic radar and microfluidic multiple particle tracking (MPT) system is proposed based on the theoretical design providing nanoscale optical modulator with vibrating Förster resonance energy transfer and vibrating cadmium selenide/zinc sulfide quantum dots (QDs) on graphene resonators. The modulator combines significant advantages of graphene membranes having wideband resonance frequencies with QDs having broad absorption spectrum and tunable properties. The solution denoted by chirp spread spectrum(CSS) Tag utilizes classical radar target tracking approaches in nanoscale environments based on the capability to generate CSS sequences identifying different bio-particles. Monte Carlo simulations show significant performance for MPT with a modulator of dimension and several picograms of weight, the signal-to-noise ratio in the range from -7 to 10 dB, simple light emitting diode sources with power less than 4 W/cm² and high speed tracking for microfluidic environments.