logo logo
Discrimination of tumor cell type based on cytometric detection of dielectric properties. Talanta In this paper, a microfluidic impedance cytometer (MIC) was employed to analyze the dielectric properties of human white blood cells (WBCs) and four tumor cell lines and realize the label-free identification of cell types. The impedance of cells was detected using an asymmetric serpentine microchannel based MIC under four different frequencies simultaneously. The asymmetric serpentine microchannel achieved the elasto-inertial focusing of cells into a single train, ensuring accurate impedance detection of cells. Various dielectric parameters (cell diameters, impedance amplitude |Z|, impedance phase shift ΦZ, and electric opacities |Z|/|Z|, ΦZ/ΦZ, Re(Z)/Re(Z), and Im(Z)/Im(Z)) were defined and used to analyze the dielectric properties of cells. The obtained dielectric parameters were used to train machine learning classification models for identifying cell types. Using all parameters proposed in this paper (cell diameter, opacity |Z|/|Z|, ΦZ/ΦZ, Re(Z)/Re(Z), and Im(Z)/Im(Z)) to train the classification model, the true positive rate (TPR) for the identification of WBCs, A549, MCF7, H226, and H460 cells were 99.6%, 96.2%, 99.1%, 97.6%, and 97.2%, respectively. Results showed that our MIC provided a promising method for label-free discrimination of circulating tumor cells in multiple primary cancers. 10.1016/j.talanta.2022.123524
Deterministic Lateral Displacement (DLD) Analysis Tool Utilizing Machine Learning towards High-Throughput Separation. Micromachines 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. 10.3390/mi13050661
Blood quality evaluation on-chip classification of cell morphology using a deep learning algorithm. Lab on a chip The quality of red blood cells (RBCs) in stored blood has a direct impact on the recovery of patients treated by blood transfusion, which directly reflects the quality of blood. The traditional means for blood quality evaluation involve the use of reagents and multi-step and time-consuming operations. Here, a low-cost, multi-classification, label-free and high-precision method is developed, which combines microfluidic technology and a deep learning algorithm together to recognize and classify RBCs based on morphology. The microfluidic channel is designed to effectively and controllably solve the problem of cell overlap, which has a severe negative impact on the identification of cells. The object detection model in the deep learning algorithm is optimized and used to recognize multiple RBCs simultaneously in the whole field of view, so as to classify them into six morphological subcategories and count the numbers in each subgroup. The mean average precision of the developed object detection model reaches 89.24%. The blood quality can be evaluated by calculating the morphology index (MI) according to the numbers of cells in subgroups. The validation of the method is verified by evaluating three blood samples stored for 7 days, 21 days and 42 days, which have MIs of 84.53%, 73.33% and 24.34%, respectively, indicating good agreement with the actual blood quality. This method has the merits of cell identification in a wide channel, no need for single cell alignment as the image cytometry does and it is not only applicable to the quality evaluation of RBCs, but can also be used for general cell identifications with different morphologies. 10.1039/d2lc01078j
Screening for urothelial carcinoma cells in urine based on digital holographic flow cytometry through machine learning and deep learning methods. Lab on a chip The incidence of urothelial carcinoma continues to rise annually, particularly among the elderly. Prompt diagnosis and treatment can significantly enhance patient survival and quality of life. Urine cytology remains a widely-used early screening method for urothelial carcinoma, but it still has limitations including sensitivity, labor-intensive procedures, and elevated cost. In recent developments, microfluidic chip technology offers an effective and efficient approach for clinical urine specimen analysis. Digital holographic microscopy, a form of quantitative phase imaging technology, captures extensive data on the refractive index and thickness of cells. The combination of microfluidic chips and digital holographic microscopy facilitates high-throughput imaging of live cells without staining. In this study, digital holographic flow cytometry was employed to rapidly capture images of diverse cell types present in urine and to reconstruct high-precision quantitative phase images for each cell type. Then, various machine learning algorithms and deep learning models were applied to categorize these cell images, and remarkable accuracy in cancer cell identification was achieved. This research suggests that the integration of digital holographic flow cytometry with artificial intelligence algorithms offers a promising, precise, and convenient approach for early screening of urothelial carcinoma. 10.1039/d3lc00854a
Validation of a Microfluidic Device Prototype for Cancer Detection and Identification: Circulating Tumor Cells Classification Based on Cell Trajectory Analysis Leveraging Cell-Based Modeling and Machine Learning. bioRxiv : the preprint server for biology Microfluidic devices (MDs) present a novel method for detecting (CTCs), enhancing the process through targeted techniques and visual inspection. However, current approaches often yield heterogeneous CTC populations, necessitating additional processing for comprehensive analysis and phenotype identification. These procedures are often expensive, time-consuming, and need to be performed by skilled technicians. In this study, we investigate the potential of a cost-effective and efficient hyperuniform micropost MD approach for CTC classification. Our approach combines mathematical modeling of fluid-structure interactions in a simulated microfluidic channel with machine learning techniques. Specifically, we developed a cell-based modeling framework to assess CTC dynamics in erythrocyte-laden plasma flow, generating a large dataset of CTC trajectories that account for two distinct CTC phenotypes. Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) were then employed to analyze the dataset and classify these phenotypes. The results demonstrate the potential effectiveness of the hyperuniform micropost MD design and analysis approach in distinguishing between different CTC phenotypes based on cell trajectory, offering a promising avenue for early cancer detection. 10.1101/2024.08.19.608572
Precise diagnosis of tumor cells and hemocytes using ultrasensitive, stable, selective cuprous oxide composite SERS bioprobes assisted with high-efficiency separation microfluidic chips. Materials horizons Efficient enrichment and accurate diagnosis of cancer cells from biological samples can guide effective treatment strategies. However, the accessibility and accuracy of rapid identification of tumor cells have been hampered due to the overlap of white blood cells (WBCs) and cancer cells in size. Therefore, a diagnosis system for the identification of tumor cells using reliable surface-enhanced Raman spectroscopy (SERS) bioprobes assisted with high-efficiency microfluidic chips for rapid enrichment of cancer cells was developed. According to this, a homogeneous flower-like CuO@Ag composite with high SERS performance was constructed. It showed a favorable spectral stability of 5.81% and can detect trace alizarin red (10 mol L). Finite-difference time-domain (FDTD) simulation of CuO, Ag and CuO@Ag, decreased the fluorescence lifetime of methylene blue after adsorption on CuO@Ag, and surface defects of CuO observed using a spherical aberration-corrected transmission electron microscope (AC-TEM) demonstrated that the combined effects of electromagnetic enhancement and promoted charge transfer endowed the CuO@Ag with good SERS activity. In addition, the modulation of the absorption properties of flower-like CuO@Ag composites significantly improved electromagnetic enhancement and charge transfer effects at 532 nm, providing a reliable basis for the label-free SERS detection. After the cancer cells in blood were separated by a spiral inertial microfluidic chip (purity >80%), machine learning-assisted linear discriminant analysis (LDA) successfully distinguished three types of cancer cells and WBCs with high accuracy (>90%). In conclusion, this study provides a profound reference for the rational design of SERS probes and the efficient diagnosis of malignant tumors. 10.1039/d4mh00791c
Deep Learning-Enabled Label-Free On-Chip Detection and Selective Extraction of Cell Aggregate-Laden Hydrogel Microcapsules. Small (Weinheim an der Bergstrasse, Germany) 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. 10.1002/smll.202100491
Comprehensive quantitative analysis of erythrocytes and leukocytes using trace volume of human blood using microfluidic-image cytometry and machine learning. Lab on a chip A diagnostic test based on microfluidic image cytometry and machine learning has been designed and applied for accurate classification of erythrocytes and leukocytes, including a unique fully-automated 5-part quantitative differentiation into neutrophils, lymphocytes, monocytes, eosinophils, and basophils, using minute amounts of whole blood in a single counting chamber. A low-cost disposable multilayer microdevice for microfluidic image cytometry was developed that comprises a 1 mm × 22 mm × 70 μm ( × × ) rectangular microchannel, allowing the analysis of trace volume of blood (20 μL) for each assay. Automated analysis of digitized binary images applying a border following algorithm was performed allowing the qualitative analysis of erythrocytes. Bright-field imaging was used for the detection of erythrocytes and fluorescence imaging for 5-part differentiation of leukocytes after acridine orange staining, applying a convolutional neural network enabling unparalleled speed for identification and automated morphology classification yielding 98.57% accuracy. Blood samples were obtained from 30 volunteers and count values did not significantly differ from data obtained using a commercial automated hematology analyzer. 10.1039/d3lc00692a
Multiparameter Mechanical Phenotyping for Accurate Cell Identification Using High-Throughput Microfluidic Deformability Cytometry. Analytical chemistry Mechanical phenotyping has been widely employed for single-cell analysis over recent years. However, most previous works on characterizing the cellular mechanical properties measured only a single parameter from one image. In this paper, the quasi-real-time multiparameter analysis of cell mechanical properties was realized using high-throughput adjustable deformability cytometry. We first extracted 12 deformability parameters from the cell contours. Then, the machine learning for cell identification was performed to preliminarily verify the rationality of multiparameter mechanical phenotyping. The experiments on characterizing cells after cytoskeletal modification verified that multiple parameters extracted from the cell contours contributed to an identification accuracy of over 80%. Through continuous frame analysis of the cell deformation process, we found that temporal variation and an average level of parameters were correlated with cell type. To achieve quasi-real-time and high-precision multiplex-type cell detection, we constructed a back propagation (BP) neural network model to complete the fast identification of four cell lines. The multiparameter detection method based on time series achieved cell detection with an accuracy of over 90%. To solve the challenges of cell rarity and data lacking for clinical samples, based on the developed BP neural network model, the transfer learning method was used for the identification of three different clinical samples, and finally, a high identification accuracy of approximately 95% was achieved. 10.1021/acs.analchem.4c01175
Kernel-Based Microfluidic Constriction Assay for Tumor Sample Identification. Ren Xiang,Ghassemi Parham,Kanaan Yasmine M,Naab Tammey,Copeland Robert L,Dewitty Robert L,Kim Inyoung,Strobl Jeannine S,Agah Masoud ACS sensors A high-throughput multiconstriction microfluidic channels device can distinguish human breast cancer cell lines (MDA-MB-231, HCC-1806, MCF-7) from immortalized breast cells (MCF-10A) with a confidence level of ∼81-85% at a rate of 50-70 cells/min based on velocity increment differences through multiconstriction channels aligned in series. The results are likely related to the deformability differences between nonmalignant and malignant breast cells. The data were analyzed by the methods/algorithms of Ridge, nonnegative garrote on kernel machine (NGK), and Lasso using high-dimensional variables, including the cell sizes, velocities, and velocity increments. In kernel learning based methods, the prediction values of 10-fold cross-validations are used to represent the difference between two groups of data, where a value of 100% indicates the two groups are completely distinct and identifiable. The prediction value is used to represent the difference between two groups using the established algorithm classifier from high-dimensional variables. These methods were applied to heterogeneous cell populations prepared using primary tumor and adjacent normal tissue obtained from two patients. Primary breast cancer cells were distinguished from patient-matched adjacent normal cells with a prediction ratio of 70.07%-75.96% by the NGK method. Thus, this high-throughput multiconstriction microfluidic device together with the kernel learning method can be used to perturb and analyze the biomechanical status of cells obtained from small primary tumor biopsy samples. The resultant biomechanical velocity signatures identify malignancy and provide a new marker for evaluation in risk assessment. 10.1021/acssensors.8b00301
Human sensor-inspired supervised machine learning of smartphone-based paper microfluidic analysis for bacterial species classification. Biosensors & bioelectronics Bacteria identification has predominantly been conducted using specific bioreceptors such as antibodies or nucleic acid sequences. This approach may be inappropriate for environmental monitoring when the user does not know the target bacterial species and for screening complex water samples with many unknown bacterial species. In this work, we investigate the supervised machine learning of the bacteria-particle aggregation pattern induced by the peptide sets identified from the biofilm-bacteria interface. Each peptide is covalently conjugated to polystyrene particles and loaded together with bacterial suspensions onto paper microfluidic chips. Each peptide interacts with bacterial species to a different extent, leading to varying sizes of particle aggregation. This aggregation changes the surface tension and viscosity of the liquid flowing through the paper pores, altering the flow velocity at different extents. A smartphone camera captures this flow velocity without being affected by ambient and environmental conditions, towards a low-cost, rapid, and field-ready assay. A collection of such flow velocity data generates a unique fingerprinting profile for each bacterial species. Support vector machine is utilized to classify the species. At optimized conditions, the training model can predict the species at 93.3% accuracy out of five bacteria: Escherichia coli, Staphylococcus aureus, Salmonella Typhimurium, Enterococcus faecium, and Pseudomonas aeruginosa. Flow rates are monitored for less than 6 s and the sample-to-answer assay time is less than 10 min. The demonstrated method can open a new way of analyzing complex biological and environmental samples in a biomimetic manner with machine learning classification. 10.1016/j.bios.2021.113335
Machine learning assisted discrimination and detection of antibiotics by using multicolor microfluidic chemiluminescence detection chip. Talanta The fabrication of multicolor chemiluminescence (CL) sensing chip for the discrimination and detection of multianalytes remains a great challenge. Herein, machine learning assisted multicolor microfluidic CL detection chip for the identification and concentration prediction of antibiotics was presented. Firstly, a three-channel microfluidic CL detection chip was fabricated. The three detection zones of the microfluidic detection chip were modified with CL catalyst Co(II) and different CL reagents including luminol, luminol mixed with fluorescein, and luminol mixed with phloxine B, respectively. Strong blue, green and pink-purple colored light emissions can be generated from the three detection zones in the presence of HO solution. The three multicolor CL emissions show different degrees of reduce in intensity and change in color in the presence of different antibiotics, including diethylstilbestro (DES), metronidazole (MNZ), kanamycin (KAN), isoniazide (INH), and ceftiofur sodium (CS), resulting in distinct fingerprint-like response patterns. The red (R), green (G), blue (B) and gray scale values of the three multicolor light emissions were extracted and ten characteristic sensing parameters were chosen to obtain multicolor CL response database. Then, machine learning assisted data analysis were carried out. The five antibiotics can be facilely classified by using principal component analysis (PCA) and hierarchical clustering analysis (HCA), and further quantified by using deep neural networks (DNN) algorithm. Good results were obtained for identification of binary antibiotic mixtures, spiked antibiotics in water samples, and unknown antibiotic samples. Satisfied results were obtained for concentration prediction of antibiotics. This work provides a simple machine learning assisted and multicolor microfluidic CL detection chip based CL sensing strategy for discrimination and quantitative detection of multiple analytes. 10.1016/j.talanta.2023.125446
CD4+ versus CD8+ T-lymphocyte identification in an integrated microfluidic chip using light scattering and machine learning. Rossi Domenico,Dannhauser David,Telesco Mariarosaria,Netti Paolo A,Causa Filippo Lab on a chip T lymphocytes are a group of cells representing the main effectors of human adaptive immunity. Characterization of the most representative T-lymphocyte subclasses, CD4+ and CD8+, is challenging, but has a significant impact on clinical decisions. Up to now, T lymphocytes have been identified by quite complex cytometric assays, which are based on antibody labeling. However, a label-free approach based on pure biophysical evaluation at a single-cell level could enable the ability to distinguish between these subclasses. Here, we report a light-scattering approach, supported by accurate data mining, to evaluate cell biophysical properties on an integrated microfluidic chip. In order to perform single-cell optical analysis in viscoelastic fluids, such a chip is composed of mixing, alignment, readout and collection sections. In particular, we measured the cell dimensions, the refractive index of the cell nucleus, the refractive index of the cytosol, and the nucleus-to-cytosol ratio. Combining measurement of biophysical properties and machine learning allows us to both distinguish and count human CD4+ and CD8+ cells with an accuracy of 79%. An enhanced identification accuracy of 88% can be achieved by stimulating the cells with a selective anti-apoptotic protein, which results in increased biophysical differences between CD4+ and CD8+ cells. This approach has been successfully validated by analysis of samples that recapitulate physiological and pathological scenarios (CD4+/CD8+ ratios). The results are encouraging for the possible application of our approach in hematological clinical routines, as well as in diagnosis and follow-up of specific pathologies, such as human immunodeficiency virus (HIV) progression. 10.1039/c9lc00695h