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

[1]  Hywel Morgan,et al.  Digital signal processing methods for impedance microfluidic cytometry , 2009 .

[2]  Vito Errico,et al.  Coplanar electrode microfluidic chip enabling accurate sheathless impedance cytometry. , 2017, Lab on a chip.

[3]  Urban Seger,et al.  Dielectric spectroscopy in a micromachined flow cytometer: theoretical and practical considerations. , 2004, Lab on a chip.

[4]  Junbo Wang,et al.  Microfluidic Impedance Flow Cytometry Enabling High-Throughput Single-Cell Electrical Property Characterization , 2015, International journal of molecular sciences.

[5]  P Renaud,et al.  Impedance-based real-time position sensor for lab-on-a-chip devices. , 2018, Lab on a chip.

[6]  Du T. Nguyen,et al.  Automated detection and sorting of microencapsulation via machine learning. , 2019, Lab on a chip.

[7]  Ola Spjuth,et al.  Deep Learning in Image Cytometry: A Review , 2018, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[8]  Caglar Elbuken,et al.  Real-time impedimetric droplet measurement (iDM). , 2019, Lab on a chip.

[9]  Junbo Wang,et al.  Development of microfluidic impedance cytometry enabling the quantification of specific membrane capacitance and cytoplasm conductivity from 100,000 single cells. , 2018, Biosensors & bioelectronics.

[10]  Federica Caselli,et al.  Electrical measurement of cross-sectional position of particles flowing through a microchannel , 2018 .

[11]  Federica Caselli,et al.  A Simple and Robust Event-Detection Algorithm for Single-Cell Impedance Cytometry , 2016, IEEE Transactions on Biomedical Engineering.

[12]  Federica Caselli,et al.  Numerical Investigation of a Novel Wiring Scheme Enabling Simple and Accurate Impedance Cytometry , 2017, Micromachines.

[13]  Zhi Chen,et al.  Precise Enumeration of Circulating Tumor Cells Using Support Vector Machine Algorithm on a Microfluidic Sensor , 2017, IEEE Transactions on Emerging Topics in Computing.

[14]  Khandakar M. Rashid,et al.  Times-series data augmentation and deep learning for construction equipment activity recognition , 2019, Adv. Eng. Informatics.

[15]  Andreas Hierlemann,et al.  Characterization of subcellular morphology of single yeast cells using high frequency microfluidic impedance cytometer. , 2014, Lab on a chip.

[16]  Tuan Le,et al.  Toward point-of-care assessment of patient response: a portable tool for rapidly assessing cancer drug efficacy using multifrequency impedance cytometry and supervised machine learning , 2019, Microsystems & Nanoengineering.

[17]  Wan Kyun Chung,et al.  Real-time Image Processing for Microscopy-based Label-free Imaging Flow Cytometry in a Microfluidic Chip , 2017, Scientific Reports.

[18]  P. Renaud,et al.  Characterization and optimization of liquid electrodes for lateral dielectrophoresis. , 2007, Lab on a chip.

[19]  Erik Bresch,et al.  Recurrent Deep Neural Networks for Real-Time Sleep Stage Classification From Single Channel EEG , 2018, Front. Comput. Neurosci..

[20]  Yo Tanaka,et al.  Recent advances in microfluidic cell sorting systems , 2019, Sensors and Actuators B: Chemical.

[21]  Federica Caselli,et al.  High-throughput electrical position detection of single flowing particles/cells with non-spherical shape. , 2019, Lab on a chip.

[22]  Federica Caselli,et al.  High-throughput label-free characterization of viable, necrotic and apoptotic human lymphoma cells in a coplanar-electrode microfluidic impedance chip. , 2019, Biosensors & bioelectronics.

[23]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[24]  Elena Bianchi,et al.  Label-free identification of activated T lymphocytes through tridimensional microsensors on chip. , 2017, Biosensors & bioelectronics.

[25]  L. Ranford-Cartwright,et al.  Dielectric characterization of Plasmodium falciparum-infected red blood cells using microfluidic impedance cytometry , 2018, Journal of The Royal Society Interface.

[26]  Nina Kovalchuk,et al.  Simulation of immiscible liquid–liquid flows in complex microchannel geometries using a front-tracking scheme , 2018, Microfluidics and Nanofluidics.

[27]  S. Lekha,et al.  Real-Time Non-Invasive Detection and Classification of Diabetes Using Modified Convolution Neural Network , 2018, IEEE Journal of Biomedical and Health Informatics.

[28]  Mohammad A. Qasaimeh,et al.  Cell Cytometry: Review and Perspective on Biotechnological Advances , 2019, Front. Bioeng. Biotechnol..

[29]  Li Pei,et al.  Deep Cytometry: Deep learning with Real-time Inference in Cell Sorting and Flow Cytometry , 2019, Scientific Reports.

[30]  Paolo Bisegna,et al.  Simulation and performance analysis of a novel high-accuracy sheathless microfluidic impedance cytometer with coplanar electrode layout. , 2017, Medical engineering & physics.

[31]  P Bisegna,et al.  An impedance-based flow microcytometer for single cell morphology discrimination. , 2014, Lab on a chip.

[32]  Andreas Hierlemann,et al.  Real-time monitoring of immobilized single yeast cells through multifrequency electrical impedance spectroscopy , 2014, Analytical and Bioanalytical Chemistry.

[33]  Mehdi Javanmard,et al.  Fully integrated wearable impedance cytometry platform on flexible circuit board with online smartphone readout , 2018, Microsystems & Nanoengineering.

[34]  Andrey Ignatov,et al.  Real-time human activity recognition from accelerometer data using Convolutional Neural Networks , 2018, Appl. Soft Comput..

[35]  Scott Sanner,et al.  Deep Learning with Microfluidics for Biotechnology. , 2019, Trends in biotechnology.

[36]  Vahid Farmehini,et al.  On-Chip Impedance for Quantifying Parasitic Voltages During AC Electrokinetic Trapping , 2020, IEEE Transactions on Biomedical Engineering.

[37]  G. Kovacs,et al.  Microfluidic impedance cytometer for platelet analysis. , 2013, Lab on a chip.

[38]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[39]  A. F. Sarioglu,et al.  Processing code-multiplexed Coulter signals via deep convolutional neural networks. , 2019, Lab on a chip.

[40]  Federica Caselli,et al.  A novel wiring scheme for standard chips enabling high-accuracy impedance cytometry , 2018 .

[41]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[42]  Han Wei Hou,et al.  Advances in Single Cell Impedance Cytometry for Biomedical Applications , 2017, Micromachines.

[43]  Arkadiusz Pierzchalski,et al.  Microfluidic impedance‐based flow cytometry , 2010, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[44]  Moncef Gabbouj,et al.  Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks , 2016, IEEE Transactions on Biomedical Engineering.

[45]  Jan Paul Huissoon,et al.  An integrated microfluidic device for the sorting of yeast cells using image processing , 2018, Scientific Reports.

[46]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[47]  N. Swami,et al.  Electrophysiology-based stratification of pancreatic tumorigenicity by label-free single-cell impedance cytometry. , 2020, Analytica chimica acta.

[48]  Yibo Zhang,et al.  Computational cytometer based on magnetically modulated coherent imaging and deep learning , 2019, Light: Science & Applications.

[49]  Fumihito Arai,et al.  Intelligent Image-Activated Cell Sorting , 2018, Cell.

[50]  Chia-Fu Chou,et al.  Frequency-selective electrokinetic enrichment of biomolecules in physiological media based on electrical double-layer polarization. , 2017, Nanoscale.

[51]  SchmidhuberJürgen,et al.  2005 Special Issue , 2005 .