Detection of Rare Objects by Flow Cytometry: Imaging, Cell Sorting, and Deep Learning Approaches

Flow cytometry: Aspects and application in plant and biological science

Flow cytometry is a potent method that enables the quick and concurrent investigation of several characteristics of single cells in solution. Photodiodes or photomultiplier tubes are employed to detect the dispersed and fluorescent light signals that are produced by the laser beam as it passes through the cells. Photodetectors transform the light signals produced by the laser into electrical impulses. A computer then analyses these electrical impulses to identify and measure the various cell populations depending on their fluorescence or light scattering characteristics. Based on their fluorescence or light scattering properties, cell populations can be examined and/or isolated. This review covers the basic principle, components, working and specific biological applications of flow cytometry, including studies on plant, cell and molecular biology and methods employed for data processing and interpretation as well as the potential future relevance of this methodology in light of retrospective analysis and recent advancements in flow cytometry.

Validation of Artificial Intelligence (AI)-Assisted Flow Cytometry Analysis for Immunological Disorders

Flow cytometry is a vital diagnostic tool for hematologic and immunologic disorders, but manual analysis is prone to variation and time-consuming. Over the last decade, artificial intelligence (AI) has advanced significantly. In this study, we developed and validated an AI-assisted flow cytometry workflow using 379 clinical cases from 2021, employing a 3-tube, 10-color flow panel with 21 antibodies for primary immunodeficiency diseases and related immunological disorders. The AI software (DeepFlow™, version 2.1.1) is fully automated, reducing analysis time to under 5 min per case. It interacts with hematopatholoists for manual gating adjustments when necessary. Using proprietary multidimensional density-phenotype coupling algorithm, the AI model accurately classifies and enumerates T, B, and NK cells, along with important immune cell subsets, including CD4+ helper T cells, CD8+ cytotoxic T cells, CD3+/CD4-/CD8- double-negative T cells, and class-switched or non-switched B cells. Compared to manual analysis with hematopathologist-determined lymphocyte subset percentages as the gold standard, the AI model exhibited a strong correlation (r > 0.9) across lymphocyte subsets. This study highlights the accuracy and efficiency of AI-assisted flow cytometry in diagnosing immunological disorders in a clinical setting, providing a transformative approach within a concise timeframe.

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.

Pixel-level multimodal fusion deep networks for predicting subcellular organelle localization from label-free live-cell imaging

Complex intracellular organizations are commonly represented by dividing the metabolic process of cells into different organelles. Therefore, identifying sub-cellular organelle architecture is significant for understanding intracellular structural properties, specific functions, and biological processes in cells. However, the discrimination of these structures in the natural organizational environment and their functional consequences are not clear. In this article, we propose a new pixel-level multimodal fusion (PLMF) deep network which can be used to predict the location of cellular organelle using label-free cell optical microscopy images followed by deep-learning-based automated image denoising. It provides valuable insights that can be of tremendous help in improving the specificity of label-free cell optical microscopy by using the Transformer-Unet network to predict the ground truth imaging which corresponds to different sub-cellular organelle architectures. The new prediction method proposed in this article combines the advantages of a transformer's global prediction and CNN's local detail analytic ability of background features for label-free cell optical microscopy images, so as to improve the prediction accuracy. Our experimental results showed that the PLMF network can achieve over 0.91 Pearson's correlation coefficient (PCC) correlation between estimated and true fractions on lung cancer cell-imaging datasets. In addition, we applied the PLMF network method on the cell images for label-free prediction of several different subcellular components simultaneously, rather than using several fluorescent labels. These results open up a new way for the time-resolved study of subcellular components in different cells, especially for cancer cells.

Dimensionality reduction by UMAP for visualizing and aiding in classification of imaging flow cytometry data

Recent advances in imaging flow cytometry (IFC) have revolutionized high-throughput multiparameter analyses at single-cell resolution. Although enabling the discovery of population heterogeneities and the detection of rare events, IFC generates hyperdimensional datasets that demand innovative analytical approaches. Current methods work in a supervised manner, utilize only limited information content, or require large annotated reference datasets. Dimensionality reduction algorithms, including uniform manifold approximation and projection (UMAP), have been successfully applied to analyze the large number of parameters generated in various high-throughput techniques.

Here, we apply a workflow incorporating UMAP to analyze different IFC datasets. We demonstrate that it out-competes other popular dimensionality reduction methods in speed and accuracy. Moreover, it enables fast visualization, clustering, and tagging of unannotated objects in large-scale experiments. We anticipate that our workflow will be a robust method to address complex IFC datasets, either alone or as an upstream addition to the deep learning approaches.

•

UMAP dimensionality reduction provides fast and accurate method of IFC data analysis

•

UMAP yields improved object clustering and tagging of the multispectral IFC data

•

PCA decomposition allows multispectral signals merging for direct image embedding

The Influence of Magnetic Composite Capsule Structure and Size on Their Trapping Efficiency in the Flow

A promising approach to targeted drug delivery is the remote control of magnetically sensitive objects using an external magnetic field source. This method can assist in the accumulation of magnetic carriers in the affected area for local drug delivery, thus providing magnetic nanoparticles for MRI contrast and magnetic hyperthermia, as well as the magnetic separation of objects of interest from the bloodstream and liquid biopsy samples. The possibility of magnetic objects' capture in the flow is determined by the ratio of the magnetic field strength and the force of viscous resistance. Thus, the capturing ability is limited by the objects' magnetic properties, size, and flow rate. Despite the importance of a thorough investigation of this process to prove the concept of magnetically controlled drug delivery, it has not been sufficiently investigated. Here, we studied the efficiency of polyelectrolyte capsules' capture by the external magnetic field source depending on their size, the magnetic nanoparticle payload, and the suspension's flow rate. Additionally, we estimated the possibility of magnetically trapping cells containing magnetic capsules in flow and evaluated cells' membrane integrity after that. These results are required to prove the possibility of the magnetically controlled delivery of the encapsulated medicine to the affected area with its subsequent retention, as well as the capability to capture magnetically labeled cells in flow.

Multiple Parallel Fusion Network for Predicting Protein Subcellular Localization from Stimulated Raman Scattering (SRS) Microscopy Images in Living Cells

Stimulated Raman Scattering Microscopy (SRS) is a powerful tool for label-free detailed recognition and investigation of the cellular and subcellular structures of living cells. Determining subcellular protein localization from the cell level of SRS images is one of the basic goals of cell biology, which can not only provide useful clues for their functions and biological processes but also help to determine the priority and select the appropriate target for drug development. However, the bottleneck in predicting subcellular protein locations of SRS cell imaging lies in modeling complicated relationships concealed beneath the original cell imaging data owing to the spectral overlap information from different protein molecules. In this work, a multiple parallel fusion network, MPFnetwork, is proposed to study the subcellular locations from SRS images. This model used a multiple parallel fusion model to construct feature representations and combined multiple nonlinear decomposing algorithms as the automated subcellular detection method. Our experimental results showed that the MPFnetwork could achieve over 0.93 dice correlation between estimated and true fractions on SRS lung cancer cell datasets. In addition, we applied the MPFnetwork method to cell images for label-free prediction of several different subcellular components simultaneously, rather than using several fluorescent labels. These results open up a new method for the time-resolved study of subcellular components in different cells, especially cancer cells.

On the robustness of machine learning algorithms toward microfluidic distortions for cell classification via on-chip fluorescence microscopy

Single-cell imaging and sorting are critical technologies in biology and clinical applications. The power of these technologies is increased when combined with microfluidics, fluorescence markers, and machine learning. However, this quest faces several challenges. One of these is the effect of the sample flow velocity on the classification performances. Indeed, cell flow speed affects the quality of image acquisition by increasing motion blur and decreasing the number of acquired frames per sample. We investigate how these visual distortions impact the final classification task in a real-world use-case of cancer cell screening, using a microfluidic platform in combination with light sheet fluorescence microscopy. We demonstrate, by analyzing both simulated and experimental data, that it is possible to achieve high flow speed and high accuracy in single-cell classification. We prove that it is possible to overcome the 3D slice variability of the acquired 3D volumes, by relying on their 2D sum z-projection transformation, to reach an efficient real time classification with an accuracy of 99.4% using a convolutional neural network with transfer learning from simulated data. Beyond this specific use-case, we provide a web platform to generate a synthetic dataset and to investigate the effect of flow speed on cell classification for any biological samples and a large variety of fluorescence microscopes (https://www.creatis.insa-lyon.fr/site7/en/MicroVIP).

Impact of red blood cell lysing on rare event analysis

The challenges associated with analyzing rare cells are dependent on a series of factors, which usually require large numbers of cells per sample for successful resolution. Among these is determining the minimum number of total events needed to be acquired as defined by the expected frequency of the target cell population. The choice of markers that identify the target population, as well as the event rate and the number of aborted events/second, will also determine the statistically significant detection of rare cell events. Sample preparation is another important but often overlooked factor in rare cell analysis, and in this study we examine Poisson theory and methods to determine the effect of sample manipulation on rare cell detection. After verifying the applicability of this theory, we have evaluated the potential impact of red cell lysis on rare cell analysis, and how cell rarity can be underestimated or overestimated based on erythrolytic sensitivity or resistance of healthy leukocytes and pathological rare cells. This article is protected by copyright. All rights reserved.

Combining imaging flow cytometry and machine learning for high-throughput schistocyte quantification: A SVM classifier development and external validation cohort

Background

Schistocyte counts are a cornerstone of the diagnosis of thrombotic microangiopathy syndrome (TMA). Their manual quantification is complex and alternative automated methods suffer from pitfalls that limit their use. We report a method combining imaging flow cytometry (IFC) and artificial intelligence for the direct label-free and operator-independent quantification of schistocytes in whole blood.

Methods

We used 135,045 IFC images from blood acquisition among 14 patients to extract 188 features with IDEAS® software and 128 features from a convolutional neural network (CNN) with Keras framework in order to train a support vector machine (SVM) blood elements’ classifier used for schistocytes quantification.

Finding

Keras features showed better accuracy (94.03%, CI: 93.75-94.31%) than ideas features (91.54%, CI: 91.21-91.87%) in recognising whole-blood elements, and together they showed the best accuracy (95.64%, CI: 95.39-95.88%). We obtained an excellent correlation (0.93, CI: 0.90-0.96) between three haematologists and our method on a cohort of 102 patient samples. All patients with schistocytosis (>1% schistocytes) were detected with excellent specificity (91.3%, CI: 82.0-96.7%) and sensitivity (100%, CI: 89.4-100.0%). We confirmed these results with a similar specificity (91.1%, CI: 78.8-97.5%) and sensitivity (100%, CI: 88.1-100.0%) on a validation cohort (n=74) analysed in an independent healthcare centre. Simultaneous analysis of 16 samples in both study centres showed a very good correlation between the 2 imaging flow cytometers (Y=1.001x).

Interpretation

We demonstrate that IFC can represent a reliable tool for operator-independent schistocyte quantification with no pre-analytical processing which is of most importance in emergency situations such as TMA.

Funding

None.

Classifying grains using behaviour-informed machine learning

Sorting granular materials such as ores, coffee beans, cereals, gravels and pills is essential for applications in mineral processing, agriculture and waste recycling. Existing sorting methods are based on the detection of contrast in grain properties including size, colour, density and chemical composition. However, many grain properties cannot be directly detected in-situ, which significantly impairs sorting efficacy. We show here that a simple neural network can infer contrast in a wide range of grain properties by detecting patterns in their observable kinematics. These properties include grain size, density, stiffness, friction, dissipation and adhesion. This method of classification based on behaviour can significantly widen the range of granular materials that can be sorted. It can similarly be applied to enhance the sorting of other particulate materials including cells and droplets in microfluidic devices.

A combination of immune cell types identified through ensemble machine learning strategy detects altered profile in recurrent pregnancy loss: a pilot study

OBJECTIVE

To compare the immunologic profiles of peripheral and menstrual blood (MB) of women who experience recurrent pregnancy loss and women without pregnancy complications.

DESIGN

Explorative case-control study. Cross-sectional assessment of flow cytometry-derived immunologic profiles.

SETTING

Academic medical center.

PATIENT(S)

Women who experienced more than 2 consecutive miscarriages.

INTERVENTION(S)

None.

MAIN OUTCOME MEASURE(S)

Flow cytometry-based immune profiles of uterine and systemic immunity (recurrent pregnancy loss, n = 18; control, n = 14) assessed by machine learning classifiers in an ensemble strategy, followed by recursive feature selection.

RESULT(S)

In peripheral blood, the combination of 4 cell types (nonswitched memory B cells, CD8+ T cells, CD56bright CD16- natural killer [NKbright] cells, and CD4+ effector T cells) classified samples correctly to their respective cohort. The identified classifying cell types in peripheral blood differed from the results observed in MB, where a combination of 6 cell types (Ki67+CD8+ T cells, (Human leukocyte antigen-DR+) regulatory T cells, CD27+ B cells, NKbright cells, regulatory T cells, and CD24HiCD38Hi B cells) plus age allowed for assigning samples correctly to their respective cohort. Based on the combination of these features, the average area under the curve of a receiver operating characteristic curve and the associated accuracy were >0.8 for both sample sources.

CONCLUSION(S)

A combination of immune subsets for cohort classification allows for robust identification of immune parameters with possible diagnostic value. The noninvasive source of MB holds several opportunities to assess and monitor reproductive health.

Fluorescent Nanosystems for Drug Tracking and Theranostics: Recent Applications in the Ocular Field

The greatest challenge associated with topical drug delivery for the treatment of diseases affecting the posterior segment of the eye is to overcome the poor bioavailability of the carried molecules. Nanomedicine offers the possibility to overcome obstacles related to physiological mechanisms and ocular barriers by exploiting different ocular routes. Functionalization of nanosystems by fluorescent probes could be a useful strategy to understand the pathway taken by nanocarriers into the ocular globe and to improve the desired targeting accuracy. The application of fluorescence to decorate nanocarrier surfaces or the encapsulation of fluorophore molecules makes the nanosystems a light probe useful in the landscape of diagnostics and theranostics. In this review, a state of the art on ocular routes of administration is reported, with a focus on pathways undertaken after topical application. Numerous studies are reported in the first section, confirming that the use of fluorescent within nanoparticles is already spread for tracking and biodistribution studies. The first section presents fluorescent molecules used for tracking nanosystems’ cellular internalization and permeation of ocular tissues; discussions on the classification of nanosystems according to their nature (lipid-based, polymer-based, metallic-based and protein-based) follows. The following sections are dedicated to diagnostic and theranostic uses, respectively, which represent an innovation in the ocular field obtained by combining dual goals in a single administration system. For its great potential, this application of fluorescent nanoparticles would experience a great development in the near future. Finally, a brief overview is dedicated to the use of fluorescent markers in clinical trials and the market in the ocular field.

Diagnosis of Acute Leukemia by Multiparameter Flow Cytometry with the Assistance of Artificial Intelligence

We developed an artificial intelligence (AI) model that evaluates the feasibility of AI-assisted multiparameter flow cytometry (MFC) diagnosis of acute leukemia. Two hundred acute leukemia patients and 94 patients with cytopenia(s) or hematocytosis were selected to study the AI application in MFC diagnosis of acute leukemia. The kappa test analyzed the consistency of the diagnostic results and the immunophenotype of acute leukemia. Bland–Altman and Pearson analyses evaluated the consistency and correlation of the abnormal cell proportion between the AI and manual methods. The AI analysis time for each case (83.72 ± 23.90 s, mean ± SD) was significantly shorter than the average time for manual analysis (15.64 ± 7.16 min, mean ± SD). The total consistency of diagnostic results was 0.976 (kappa (κ) = 0.963). The Bland–Altman evaluation of the abnormal cell proportion between the AI analysis and manual analysis showed that the bias ± SD was 0.752 ± 6.646, and the 95% limit of agreement was from −12.775 to 13.779 (p = 0.1225). The total consistency of the AI immunophenotypic diagnosis and the manual results was 0.889 (kappa, 0.775). The consistency and speedup of the AI-assisted workflow indicate its promising clinical application.

Advantages of optical fibers for facile and enhanced detection in droplet microfluidics

Droplet microfluidics offers a unique opportunity for ultrahigh-throughput experimentation with minimal sample consumption and thus has obtained increasing attention, particularly for biological applications. Detection and measurements of analytes or biomarkers in tiny droplets are essential for proper analysis of biological and chemical assays like single-cell studies, cytometry, nucleic acid detection, protein quantification, environmental monitoring, drug discovery, and point-of-care diagnostics. Current detection setups widely use microscopes as a central device and other free-space optical components. However, microscopic setups are bulky, complicated, not flexible, and expensive. Furthermore, they require precise optical alignments, specialized optical and technical knowledge, and cumbersome maintenance. The establishment of efficient, simple, and cheap detection methods is one of the bottlenecks for adopting microfluidic strategies for diverse bioanalytical applications and widespread laboratory use. Together with great advances in optofluidic components, the integration of optical fibers as a light guiding medium into microfluidic chips has recently revolutionized analytical possibilities. Optical fibers embedded in a microfluidic platform provide a simpler, more flexible, lower-cost, and sensitive setup for the detection of several parameters from biological and chemical samples and enable widespread, hands-on application much beyond thriving point-of-care developments. In this review, we examine recent developments in droplet microfluidic systems using optical fiber as a light guiding medium, primarily focusing on different optical detection methods such as fluorescence, absorbance, light scattering, and Raman scattering and the potential applications in biochemistry and biotechnology that are and will be arising from this.

Imaging flow cytometry data analysis using convolutional neural network for quantitative investigation of phagocytosis

Macrophages play an important role in the adaptive immune system. Their ability to neutralize cellular targets through Fc receptor-mediated phagocytosis has relied upon immunotherapy that has become of particular interest for the treatment of cancer and autoimmune diseases. A detailed investigation of phagocytosis is the key to the improvement of the therapeutic efficiency of existing medications and the creation of new ones. A promising method for studying the process is imaging flow cytometry (IFC) that acquires thousands of cell images per second in up to 12 optical channels and allows multiparametric fluorescent and morphological analysis of samples in the flow. However, conventional IFC data analysis approaches are based on a highly subjective manual choice of masks and other processing parameters that can lead to the loss of valuable information embedded in the original image. Here, we show the application of a Faster region-based convolutional neural network (CNN) for accurate quantitative analysis of phagocytosis using imaging flow cytometry data. Phagocytosis of erythrocytes by peritoneal macrophages was chosen as a model system. CNN performed automatic high-throughput processing of datasets and demonstrated impressive results in the identification and classification of macrophages and erythrocytes, despite the variety of shapes, sizes, intensities, and textures of cells in images. The developed procedure allows determining the number of phagocytosed cells, disregarding cases with a low probability of correct classification. We believe that CNN-based approaches will enable powerful in-depth investigation of a wide range of biological processes and will reveal the intricate nature of heterogeneous objects in images, leading to completely new capabilities in diagnostics and therapy.

A flow cytometric journey into cell cycle analysis

Cell cycle involves a series of changes that lead to cell growth and division. Cell cycle analysis is crucial to understand cellular responses to changing environmental conditions. Since its inception, flow cytometry has been particularly useful for cell cycle analysis at single cell level due to its speed and precision. Previously, flow cytometric cell cycle analysis relied solely on the measurement of cellular DNA content. Later, methods were developed for multiparametric analysis. This review explains the journey of flow cytometry to understand different molecular and cellular events underlying cell cycle using various protocols. Recent advances in the field that overcome the shortcomings of traditional flow cytometry and expand its scope for cell cycle studies are also discussed.

Inertial cell sorting of microparticle-laden flows: An innovative OpenFOAM-based arbitrary Lagrangian-Eulerian numerical approach

The need for cell and particle sorting in human health care and biotechnology applications is undeniable. Inertial microfluidics has proven to be an effective cell and particle sorting technology in many of these applications. Still, only a limited understanding of the underlying physics of particle migration is currently available due to the complex inertial and impact forces arising from particle-particle and particle-wall interactions. Thus, even though it would likely enable significant advances in the field, very few studies have tried to simulate particle-laden flows in inertial microfluidic devices. To address this, this study proposes new codes (solved in OpenFOAM software) that capture all the salient inertial forces, including the four-way coupling between the conveying fluid and the suspended particles traveling a spiral microchannel. Additionally, these simulations are relatively (computationally) inexpensive since the arbitrary Lagrangian-Eulerian formulation allows the fluid elements to be much larger than the particles. In this study, simulations were conducted for two different spiral microchannel cross sections (e.g., rectangular and trapezoidal) for comparison against previously published experimental results. The results indicate good agreement with experiments in terms of (monodisperse) particle focusing positions, and the codes can readily be extended to simulate two different particle types. This new numerical approach is significant because it opens the door to rapid geometric and flow rate optimization in order to improve the efficiency and purity of cell and particle sorting in biotechnology applications.

Effect of cell-nanostructured substrate interactions on the capture efficiency of HeLa cells

Circulating tumour cells (CTCs) are regarded as an effective biomarker for cancer detection, diagnosis and prognosis monitoring. CTCs capture based on nanostructured substrates is a powerful technique. Some specific adhesion molecule antibody-coated on the surface of nanostructured substrates, such as EpCAM, is commonly used to enhance CTCs capture efficiency. Substrate nanotopographies regulate the interaction between the substrates and captured cells, further influencing cell capture efficiency. However, the relationship between cell capture efficiency and cell-substrate interaction remains poorly understood. Here, we explored the relationship between cell capture efficiency and cell-substrate interaction based on two sets of nanostructures with different nanotopographies without antibody conjugation. Given the urgent demand of improving capture efficiency of EpCAM-negative cells, we used HeLa (EpCAM-negative) cells as the main targets. We demonstrated that HeLa cells could be more effectively captured by two nanostructural substrates, especially by DCNFs. Therefore, the morphological and migrating interaction between HeLa cells and distinct substrates were associated with cell capture efficiency. Our findings demonstrated the potential mechanism for optimizing the nanotopography for higher capture efficiency, and provide a potential foundation for cancer detection, diagnosis and treatment.

Changes in Autofluorescence Level of Live and Dead Cells for Mouse Cell Lines

Label-free characterization of cell subpopulations is a very promising biomedical approach. Nowadays, there are several label-free methods based on different physical properties such as size, density, stiffness, etc. allowing the characterization of biological objects. However, fluorescence properties are the most suitable feature for the label-free study of tissue and cells. Understanding the autofluorescence level peculiarities of normal and pathological / live and dead cells can become a helpful tool for cells' metabolic activity, viability evaluation, and diagnostics of a number of diseases. In this study, we applied a series of mouse cell lines (RAW 264.7 - macrophages, L929 - fibroblasts, C2C12 - myoblasts, and B16-F10 - melanoma) to compare cell autofluorescence of live and dead cells under 488 nm laser excitation and found the difference between their autofluorescence depending on a cell state and type.

Cell Reprogramming With CRISPR/Cas9 Based Transcriptional Regulation Systems

The speed of reprogramming technologies evolution is rising dramatically in modern science. Both the scientific community and health workers depend on such developments due to the lack of safe autogenic cells and tissues for regenerative medicine, genome editing tools and reliable screening techniques. To perform experiments efficiently and to propel the fundamental science it is important to keep up with novel modifications and techniques that are being discovered almost weekly. One of them is CRISPR/Cas9 based genome and transcriptome editing. The aim of this article is to summarize currently existing CRISPR/Cas9 applications for cell reprogramming, mainly, to compare them with other non-CRISPR approaches and to highlight future perspectives and opportunities.