Abstract
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.
Similar content being viewed by others
References
Coulter WH. Means for counting particles suspended in a fluid. US 2656508 A, 1953.
Cheung KC, Di Berardino M, Schade-Kampmann G, Hebeisen M, Pierzchalski A, Bocsi J, et al. Microfluidic impedance-based flow cytometry. Cytom Part A. 2010;77(7):648–66. Available from: https://doi.org/10.1002/cyto.a.20910.
Petchakup C, Li KHH, Hou HW. Advances in single cell impedance cytometry for biomedical applications. Micromachines. 2017;8(3):87. Available from: https://doi.org/10.3390/mi8030087.
Vembadi A, Menachery A, Qasaimeh MA. Cell cytometry: review and perspective on biotechnological advances. Front Bioeng Biotechnol. 2019;7:147. Available from: https://doi.org/10.3389/fbioe.2019.00147.
Gawad S, Cheung K, Seger U, Bertsch A, Renaud P. Dielectric spectroscopy in a micromachined flow cytometer: theoretical and practical considerations. Lab Chip. 2004;4(3):241–51. Available from: https://doi.org/10.1039/B313761A.
Reale R, De Ninno A, Businaro L, Bisegna P, Caselli F. Electrical measurement of cross-sectional position of particles flowing through a microchannel. Microfluid Nanofluid. 2018;22(41):1–13. Available from: https://doi.org/10.1007/s10404-018-2055-3.
Reale R, De Ninno A, Businaro L, Bisegna P, Caselli F. High-throughput electrical position detection of single flowing particles/cells with non-spherical shape. Lab Chip. 2019;19(10):1818–27. Available from: https://doi.org/10.1039/C9LC00071B.
McGrath J, Reale R, Honrado C, Bisegna P, Swami N, Caselli F. Towards real-time multiparametric impedance cytometry. In: 23nd International Conference on Miniaturized Systems for Chemistry and Life Sciences (MicroTAS 2019). 2019.
Sun T, van Berkel C, Green NG, Morgan H. Digital signal processing methods for impedance microfluidic cytometry. Microfluid Nanofluid. 2009;6(2):179–87. Available from: https://doi.org/10.1007/s10404-008-0315-3.
Evander M, Ricco AJ, Morser J, Kovacs GTA, Leung LLK, Giovangrandi L. Microfluidic impedance cytometer for platelet analysis. Lab Chip. 2013;13(4):722–9. Available from: https://doi.org/10.1039/C2LC40896A.
Caselli F, Bisegna P. A simple and robust event-detection algorithm for single-cell impedance cytometry. IEEE Trans Biomed Eng. 2016;63(2):415–22. Available from: https://doi.org/10.1109/TBME.2015.2462292.
Guo J, Chen Z, Ban Y, Kang Y. Precise enumeration of circulating tumor cells using support vector machine algorithm on a microfluidic sensor. IEEE Trans Emerg Top Comput. 2014;5(4):518–25. Available from: https://doi.org/10.1109/TETC.2014.2335539.
Ahuja K, Rather GM, Lin Z, Sui J, Xie P, Le T, 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. Microsyst Nanoeng. 2019;5(1):34. Available from: https://doi.org/10.1038/s41378-019-0073-2.
Chen J, Xue C, Zhao Y, Chen D, Wu MH, Wang J. Microfluidic impedance flow cytometry enabling high-throughput single-cell electrical property characterization. Int J Mol Sci. 2015;16(5):9804–30. Available from: https://doi.org/10.3390/ijms16059804.
Zhao Y, Wang K, Chen D, Fan B, Xu Y, Ye Y, et al. Development of microfluidic impedance cytometry enabling the quantification of specific membrane capacitance and cytoplasm conductivity from 100,000 single cells. Biosens Bioelectron. 2018;111:138–43. Available from: http://www.sciencedirect.com/science/article/pii/S0956566318302756.
Furniturewalla A, Chan M, Sui J, Ahuja K, Javanmard M. Fully integrated wearable impedance cytometry platform on flexible circuit board with online smartphone readout. Microsyst Nanoeng. 2018;4(1):20. Available from: https://doi.org/10.1038/s41378-018-0019-0.
Brazey B, Cottet J, Bolopion A, Van Lintel H, Renaud P, Gauthier M. Impedance-based real-time position sensor for lab-on-a-chip devices. Lab Chip. 2018;18(5):818–31. Available from: https://doi.org/10.1039/C7LC01344B.
Saateh A, Kalantarifard A, Celik OT, Asghari M, Serhatlioglu M, Elbuken C. Real-time impedimetric droplet measurement (iDM). Lab Chip. 2019;19(22):3815–24. Available from: https://doi.org/10.1039/C9LC00641A.
Farmehini V, Varhue W, Salahi A, Hyler AR, Čemažar J, Davalos R, Swami NS. On-chip impedance for quantifying parasitic voltages during AC electrokinetic trapping. IEEE Trans Biomed Eng 2019. Available from: https://doi.org/10.1109/TBME.2019.2942572.
Rohani A, Sanghavi BJ, Salahi A, Liao K-TT, Chou C-FF, Swami NS. Frequency-selective electrokinetic enrichment of biomolecules in physiological media based on electrical double-layer polarization. Nanoscale. 2017;9(33):12124–31. Available from: https://doi.org/10.1039/C7NR02376F.
McGrath JS, Honrado C, Moore JH, Adair SJ, Varhue WB, Salahi A, Farmehini V, Goudreau BJ, Nagdas S, Blais EM, Bauer TW, Swami NS. Electrophysiology-based stratification of pancreatic tumorigenicity by label-free single-cell impedance cytometry. Anal Chim Acta. 2020;1101:90–8. Available from: https://doi.org/10.1016/j.aca.2019.12.033.
Riordon J, Sovilj D, Sanner S, Sinton D, Young EWK. Deep learning with microfluidics for biotechnology. Trends Biotechnol. 2019;37(3):310–24. Available from: http://www.sciencedirect.com/science/article/pii/S0167779918302452.
Chu A, Nguyen D, Talathi SS, Wilson AC, Ye C, Smith WL, et al. Automated detection and sorting of microencapsulation via machine learning. Lab Chip. 2019;19(10):1808–17. Available from: https://doi.org/10.1039/C8LC01394B.
Heo YJ, Lee D, Kang J, Lee K, Chung WK. Real-time image processing for microscopy-based label-free imaging flow cytometry in a microfluidic chip. Sci Rep. 2017;7(1):11651. Available from: https://doi.org/10.1038/s41598-017-11534-0.
Nitta N, Sugimura T, Isozaki A, Mikami H, Hiraki K, Sakuma S, et al. Intelligent image-activated cell sorting. Cell. 2018;175(1):266–276.e13. Available from: http://www.sciencedirect.com/science/article/pii/S0092867418310444.
Gupta A, Harrison PJ, Wieslander H, Pielawski N, Kartasalo K, Partel G, et al. Deep learning in image cytometry: a review. Cytom Part A. 2019;95(4):366–80. Available from: https://onlinelibrary.wiley.com/doi/abs/10.1002/cyto.a.23701.
Zhang Y, Ouyang M, Ray A, Liu T, Kong J, Bai B, et al. Computational cytometer based on magnetically modulated coherent imaging and deep learning. Light-Sci Appl. 2019;8(1):91. Available from: https://doi.org/10.1038/s41377-019-0203-5.
Li Y, Mahjoubfar A, Chen CL, Niazi KR, Pei L, Jalali B. Deep cytometry: deep learning with real-time inference in cell sorting and flow cytometry. Sci Rep. 2019;9(1):11088. Available from: https://doi.org/10.1038/s41598-019-47193-6.
Ignatov A. Real-time human activity recognition from accelerometer data using convolutional neural networks. Appl Soft Comput. 2018;62:915–22. Available from: http://www.sciencedirect.com/science/article/pii/S1568494617305665.
Bresch E, Großekathöfer U, Garcia-Molina G. Recurrent deep neural networks for real-time sleep stage classification from single channel EEG. Front Comput Neurosci. 2018:12–85. Available from: https://www.frontiersin.org/article/10.3389/fncom.2018.00085.
Kiranyaz S, Ince T, Gabbouj M. Real-time patient-specific ECG classification by 1-D convolutional neural networks. IEEE Trans Biomed Eng. 2016;63(3):664–75. Available from: https://doi.org/10.1109/TBME.2015.2468589.
Lekha S, Suchetha M. Real-time non-invasive detection and classification of diabetes using modified convolution neural network. IEEE J Biomed Health Inform. 2018;22(5):1630–6. Available from: https://doi.org/10.1109/JBHI.2017.2757510.
Wang N, Liu R, Asmare N, Chu C-HH, Sarioglu AF. Processing code-multiplexed Coulter signals via deep convolutional neural networks. Lab Chip. 2019;19(19):3292–304. Available from: https://doi.org/10.1039/C9LC00597H.
Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature. 1986;323(6088):533–6. Available from: https://doi.org/10.1038/323533a0.
Hopfield JJ. Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci U S A. 1982;79(8):2554–8. Available from: https://www.pnas.org/content/79/8/2554.
Demierre N, Braschler T, Linderholm P, Seger U, van Lintel H, Renaud P. Characterization and optimization of liquid electrodes for lateral dielectrophoresis. Lab Chip. 2007;7(3):355–65. Available from: https://doi.org/10.1039/B612866A.
Caselli F, De Ninno A, Reale R, Businaro L, Bisegna P. A novel wiring scheme for standard chips enabling high-accuracy impedance cytometry. Sens Actuator B-Chem. 2018;256:580–9. Available from: https://doi.org/10.1016/j.snb.2017.10.113.
Caselli F, Reale R, Nodargi NA, Bisegna P. Numerical investigation of a novel wiring scheme enabling simple and accurate impedance cytometry. Micromachines. 2017;8(9):283. Available from: https://doi.org/10.3390/mi8090283.
Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997;9(8):1735–80. Available from: https://doi.org/10.1162/neco.1997.9.8.1735.
Graves A, Schmidhuber J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 2005;18(5):602–10. Available from: http://www.sciencedirect.com/science/article/pii/S0893608005001206.
Caselli F, Bisegna P. Simulation and performance analysis of a novel high-accuracy sheathless microfluidic impedance cytometer with coplanar electrode layout. Med Eng Phys. 2017;48:81–9. Available from: https://doi.org/10.1016/j.medengphy.2017.04.005.
Shen Y, Yalikun Y, Tanaka Y. Recent advances in microfluidic cell sorting systems. Sens Actuator B-Chem. 2019;282:268–81. Available from: http://www.sciencedirect.com/science/article/pii/S0925400518319798.
Rashid KM, Louis J. Times-series data augmentation and deep learning for construction equipment activity recognition. Adv Eng Inform. 2019;42:100944. Available from: http://www.sciencedirect.com/science/article/pii/S1474034619300886.
Reale R, De Ninno A, Businaro L, Bisegna P, Caselli F. Electrical measurement of cross-sectional position of particles flowing through a microchannel. Microfluid Nanofluid. 2018;22(4):1–13. Available from: https://doi.org/10.1007/s10404-018-2055-3.
De Ninno A, Errico V, Bertani FR, Businaro L, Bisegna P, Caselli F. Coplanar electrode microfluidic chip enabling accurate sheathless impedance cytometry. Lab Chip. 2017;17(6):1158–66. Available from: https://doi.org/10.1039/C6LC01516F.
Haandbaek N, Burgel SC, Heer F, Hierlemann A. Characterization of subcellular morphology of single yeast cells using high frequency microfluidic impedance cytometer. Lab Chip. 2014;14(2):369–77. Available from: https://doi.org/10.1039/C3LC50866H.
De Ninno A, Reale R, Giovinazzo A, Bertani FR, Businaro L, Bisegna P, et al. High-throughput label-free characterization of viable, necrotic and apoptotic human lymphoma cells in a coplanar-electrode microfluidic impedance chip. Biosens Bioelectron. 2019;150:111887. Available from: https://doi.org/10.1016/j.bios.2019.111887.
Rollo E, Tenaglia E, Genolet R, Bianchi E, Harari A, Coukos G, et al. Label-free identification of activated T-lymphocytes through tridimensional microsensors on chip. Biosens Bioelectron. 2017;94:193–9. Available from: https://doi.org/10.1016/j.bios.2017.02.047.
Shaker M, Colella L, Caselli F, Bisegna P, Renaud P. An impedance-based flow micro-cytometer for single cell morphology discrimination. Lab Chip. 2014;14(14):2548–55. Available from: https://doi.org/10.1039/C4LC00221K.
Zhu Z, Frey O, Franke F, Haandbæk N, Hierlemann A. Real-time monitoring of immobilized single yeast cells through multifrequency electrical impedance spectroscopy. Anal Bioanal Chem. 2014;406(27):7015–25. Available from: https://doi.org/10.1007/s00216-014-7955-9.
Yu BY, Elbuken C, Shen C, Huissoon JP, Ren CL. An integrated microfluidic device for the sorting of yeast cells using image processing. Sci Rep. 2018;8(1):3550. Available from: https://doi.org/10.1038/s41598-018-21833-9.
Honrado C, Ciuffreda L, Spencer D, Ranford-Cartwright L, Morgan H. Dielectric characterization of Plasmodium falciparum-infected red blood cells using microfluidic impedance cytometry. J R Soc Interface. 2018;15(147):20180416. Available from: https://doi.org/10.1098/rsif.2018.0416.
Funding
This study received funding from the Italian Ministry of Education, University and Research (SIR 2014, Grant RBSI14TX20); from the University of Rome Tor Vergata (Mission Sustainability, Grant E81I18000540005); from the U.S. National Center for Advancing Translational Sciences of the National Institutes of Health (Award Number UL1TR003015); and from Advanced Regenerative Medicine Institute’s BioFab-USA (Subcontract T0163).
Author information
Authors and Affiliations
Contributions
The manuscript was written through contributions of all authors and all authors approved the final version.
Corresponding authors
Ethics declarations
The reported studies on blood samples have been approved by the University of Virginia Institutional Review Board for Health Sciences Research (IRB-HSR protocol no. 21081) and have been performed in accordance with ethical standards.
Conflict of interest
The authors declare that they have no conflicts of interest.
Disclaimer
The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health, the Italian Ministry of Education, University and Research, and the other funding agencies.
Additional information
Published in the topical collection Bioanalytics and Higher Order Electrokinetics with guest editors Mark A. Hayes and Federica Caselli.
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
ESM 1
(DOCX 5792 kb)
Rights and permissions
About this article
Cite this article
Honrado, C., McGrath, J.S., Reale, R. et al. A neural network approach for real-time particle/cell characterization in microfluidic impedance cytometry. Anal Bioanal Chem 412, 3835–3845 (2020). https://doi.org/10.1007/s00216-020-02497-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00216-020-02497-9