A method for real-time mechanical characterisation of microcapsules

Biomechanics and Modeling in Mechanobiology - Tập 22 - Trang 1209-1220 - 2023
Ziyu Guo1, Tao Lin1, Dalei Jing1, Wen Wang1, Yi Sui1
1School of Engineering and Material Science, Queen Mary University of London, London, United Kingdom

Tóm tắt

Characterising the mechanical properties of flowing microcapsules is important from both fundamental and applied points of view. In the present study, we develop a novel multilayer perceptron (MLP)-based machine learning (ML) approach, for real-time simultaneous predictions of the membrane mechanical law type, shear and area-dilatation moduli of microcapsules, from their camera-recorded steady profiles in tube flow. By MLP, we mean a neural network where many perceptrons are organised into layers. A perceptron is a basic element that conducts input–output mapping operation. We test the performance of the present approach using both simulation and experimental data. We find that with a reasonably high prediction accuracy, our method can reach an unprecedented low prediction latency of less than 1 millisecond on a personal computer. That is the overall computational time, without using parallel computing, from a single experimental image to multiple capsule mechanical parameters. It is faster than a recently proposed convolutional neural network-based approach by two orders of magnitude, for it only deals with the one-dimensional capsule boundary instead of the entire two-dimensional capsule image. Our new approach may serve as the foundation of a promising tool for real-time mechanical characterisation and online active sorting of deformable microcapsules and biological cells in microfluidic devices.

Tài liệu tham khảo

Abadi M, Barham P, Chen J, etal (2016) Tensorflow: A system for large-scale machine learning. In: 12th USENIX symposium on operating systems design and implementation (OSDI 16). USENIX Association, Savannah, GA, pp 265–283, https://www.usenix.org/conference/osdi16/technical-sessions/presentation/abadi Balogh P, Gounley J, Roychowdhury S (2021) A data-driven approach to modeling cancer cell mechanics during microcirculatory transport. Sci Rep 11(1):1–18. https://doi.org/10.1038/s41598-021-94445-5 Barthés-Biesel D (2016) Motion and deformation of elastic capsules and vesicles in flow. Annu Rev Fluid Mech 48(1):25–52. https://doi.org/10.1146/annurev-fluid-122414-034345 Bhujbal SV, deVos P, Niclou SP (2014) Drug and cell encapsulation: alternative delivery options for the treatment of malignant brain tumors. Adv Drug Deliver Rev 67:142–153. https://doi.org/10.1016/j.addr.2014.01.010 Bouzidi M, Firdaouss M, Lallemand P (2001) Momentum transfer of a boltzmann-lattice fluid with boundaries. Phys Fluids 13(11):3452. https://doi.org/10.1063/1.1399290 Brunton SL, Proctor JL, Kutz JN (2016) Discovering governing equations from data by sparse identification of nonlinear dynamical systems. Proc Natl Acad Sci 113(15):3932–3937. https://doi.org/10.1073/pnas.1517384113 Carin M, Barthès-Biesel D, Edwards-Lévy F et al (2003) Compression of biocompatible liquid-filled hsa-alginate capsules: determination of the membrane mechanical properties. Biotechnol Bioeng 82(2):207–212. https://doi.org/10.1002/bit.10559 Chang KS, Olbricht WL (1993) Experimental studies of the deformation and breakup of a synthetic capsule in steady and unsteady simple shear flow. J Fluid Mech 250:609–633. https://doi.org/10.1017/S0022112093001582 Chen CL, Mahjoubfar A, Tai LC et al (2016) Deep learning in label-free cell classification. Sci Rep 6(1):1–16. https://doi.org/10.1038/srep21471 Chu T, Salsac AV, Barthès-Biesel D et al (2013) Fabrication and in situ characterization of microcapsules in a microfluidic system. Microfluid Nanofluidics 14(1):309–317. https://doi.org/10.1007/s10404-012-1049-9 Cordasco D, Bagchi P (2013) Orbital drift of capsules and red blood cells in shear flow. Phys Fluids 25(9):091–902. https://doi.org/10.1063/1.4820472 Cui J, Liu Y, Xiao L (2021) Numerical study on the adhesion of a circulating tumor cell in a curved microvessel. Biomech Model Mechanobiol 20(1):243–254. https://doi.org/10.1007/s10237-020-01380-x deLoubens C, Deschamps J, Georgelin M et al (2014) Mechanical characterization of cross-linked serum albumin microcapsules. Soft Matter 10(25):4561–4568. https://doi.org/10.1039/C4SM00349G deLoubens C, Deschamps J, Boedec G et al (2015) Stretching of capsules in an elongation flow, a route to constitutive law. J Fluid Mech 767:R3. https://doi.org/10.1017/jfm.2015.69 deLoubens C, Deschamps J, Edwards-Lévy F et al (2016) Tank-treading of microcapsules in shear flow. J Fluid Mech 789:750–767. https://doi.org/10.1017/jfm.2015.758 Dubuisson MP, Jain AK (1994) A modified hausdorff distance for object matching. In: proceedings of 12th international conference on pattern recognition, IEEE, pp 566–568, https://doi.org/10.1109/ICPR.1994.576361 Dupont C, Salsac AV, Barthes-Biesel D, etal (2015) Influence of bending resistance on the dynamics of a spherical capsule in shear flow. Phys Fluids 27(5):051,902. https://doi.org/10.1063/1.4921247 Freund JB (2014) Numerical simulation of flowing blood cells. Annu Rev Fluid Mech 46:67–95. https://doi.org/10.1146/annurev-fluid-010313-141349 Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT press, Cambridge, Massachusetts Gubspun J, Gires PY, Loubens Cd et al (2016) Characterization of the mechanical properties of cross-linked serum albumin microcapsules: effect of size and protein concentration. Colloid Polym Sci 294(8):1381–1389. https://doi.org/10.1007/s00396-016-3885-8 Guo ZL, Zheng CG, Shi BC (2002) Non-equilibrium extrapolation method for velocity and pressure boundary conditions in the lattice boltzmann method. Chin Phys 11(4):366. https://doi.org/10.1088/1009-1963/11/4/310 Häner E, Vesperini D (2021) Sorting of capsules according to their stiffness: from principle to application. Soft Matter 17(13):3722–3732. https://doi.org/10.1039/D0SM02249G Häner E, Heil M, Juel A (2020) Deformation and sorting of capsules in a t-junction. J Fluid Mech. https://doi.org/10.1017/jfm.2019.979 Hu XQ, Sévénié B, Salsac AV et al (2013) Characterizing the membrane properties of capsules flowing in a square-section microfluidic channel: effects of the membrane constitutive law. Phys Rev E 87(6):008–063. https://doi.org/10.1103/PhysRevE.87.063008 Husmann M, Rehage H, Dhenin E et al (2005) Deformation and bursting of nonspherical polysiloxane microcapsules in a spinning-drop apparatus. J Colloid Interf Sci 282(1):109–119. https://doi.org/10.1016/j.jcis.2004.08.129 Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: proceedings of the 32nd international conference on machine learning, Lille, France, pp 448–456 Isozaki A, Mikami H, Tezuka H et al (2020) Intelligent image-activated cell sorting 2.0. Lab Chip 20(13):2263–2273. https://doi.org/10.1039/d0lc00080a Jones G, Parr J, Nithiarasu P et al (2021) Machine learning for detection of stenoses and aneurysms: application in a physiologically realistic virtual patient database. Biomech Model Mechanobiol 20(6):2097–2146. https://doi.org/10.1007/s10237-021-01497-7 Karniadakis GE, Kevrekidis IG, Lu L et al (2021) Physics-informed machine learning. Nat Rev Phys 3(6):422–440. https://doi.org/10.1038/s42254-021-00314-5 Kingma DP, Ba JL (2014) Adam: a method for stochastic optimization. arXiv:1412.6980 Langtangen HP (2008) Python scripting for computational science. Springer, Oslo, Norway Laumann M, Schmidt W, Farutin A et al (2019) Emerging attractor in wavy poiseuille flows triggers sorting of biological cells. Phys Rev Lett 122(12):002–128. https://doi.org/10.1103/PhysRevLett.122.128002 Lefebvre Y, Barthes-Biesel D (2007) Motion of a capsule in a cylindrical tube: effect of membrane pre-stress. J Fluid Mech 589:157–181. https://doi.org/10.1017/S0022112007007586 Lefebvre Y, Leclerc E, Barthès-Biesel D et al (2008) Flow of artificial microcapsules in microfluidic channels: a method for determining the elastic properties of the membrane. Phys Fluids 20(12):102–123. https://doi.org/10.1063/1.3054128 Lin T, Wang Z, Lu R et al (2021) A high-throughput method to characterize membrane viscosity of flowing microcapsules. Phys Fluids 33(1):011–906. https://doi.org/10.1063/5.0031640 Lin T, Wang Z, Wang W et al (2021) A neural network-based algorithm for high-throughput characterisation of viscoelastic properties of flowing microcapsules. Soft Matter 17(15):4027–4039 Lin T, Wang Z, Lu R et al (2022) Characterising mechanical properties of flowing microcapsules using a deep convolutional neural network. Adv Appl Math Mech 14(1):79–100. https://doi.org/10.4208/aamm.OA-2020-0357 Lu R, Wang Z, Salsac AV et al (2021) Path selection of a train of spherical capsules in a branched microchannel. J Fluid Mech 923:11. https://doi.org/10.1017/jfm.2021.571 Maestre J, Pallares J, Cuesta I et al (2019) Dynamics of a capsule flowing in a tube under pulsatile flow. J Mech Behav Biomed 90:441–450. https://doi.org/10.1016/j.jmbbm.2018.10.025 Mayfield AE, Tilokee EL, Latham N et al (2014) The effect of encapsulation of cardiac stem cells within matrix-enriched hydrogel capsules on cell survival, post-ischemic cell retention and cardiac function. Biomaterials 35(1):133–142. https://doi.org/10.1016/j.biomaterials.2013.09.085 Mietke A, Otto O, Girardo S et al (2015) Extracting cell stiffness from real-time deformability cytometry: theory and experiment. Biophys J 109(10):2023–2036. https://doi.org/10.1016/j.bpj.2015.09.006 Nawaz AA, Urbanska M, Herbig M et al (2020) Intelligent image-based deformation-assisted cell sorting with molecular specificity. Nat Methods 17(6):595–599. https://doi.org/10.1038/s41592-020-0831-y Nitta N, Sugimura T, Isozaki A et al (2018) Intelligent image-activated cell sorting. Cell 175(1):266–276. https://doi.org/10.1016/j.cell.2018.08.028 Peirlinck M, Costabal FS, Sack K et al (2019) Using machine learning to characterize heart failure across the scales. Biomech Model Mechanobiol 18(6):1987–2001. https://doi.org/10.1007/s10237-019-01190-w Peskin CS (1977) Numerical analysis of blood flow in the heart. J Comput Phys 25(3):220–252. https://doi.org/10.1016/0021-9991(77)90100-0 Phillip JM, Han KS, Chen WC et al (2021) A robust unsupervised machine-learning method to quantify the morphological heterogeneity of cells and nuclei. Nat Protoc 16(2):754–774. https://doi.org/10.1038/s41596-020-00432-x Pieper G, Rehage H, Barthès-Biesel D (1998) Deformation of a capsule in a spinning drop apparatus. J Colloid Interf Sci 202(2):293–300. https://doi.org/10.1006/jcis.1998.5438 Podskočová J, ChorvátJr D, Kollároková G et al (2005) Characterization of polyelectrolyte microcapsules by confocal laser scanning microscopy and atomic force microscopy. Laser Phys 15(4):545–551 Pozrikidis C (2003) Modeling and simulation of capsules and biological cells. CRC Press, London, England Pozrikidis C (2003) Numerical simulation of the flow-induced deformation of red blood cells. Ann Biomed Eng 31(10):1194–1205. https://doi.org/10.1114/1.1617985 Rachik M, Barthès-Biesel D, Carin M et al (2006) Identification of the elastic properties of an artificial capsule membrane with the compression test: effect of thickness. J Colloid Interf Sci 301(1):217–226. https://doi.org/10.1016/j.jcis.2006.04.062 Rahmat A, Barigou M, Alexiadis A (2019) Deformation and rupture of compound cells under shear: a discrete multiphysics study. Phys Fluids 31(5):051–903. https://doi.org/10.1063/1.5091999 Risso F, Carin M (2004) Compression of a capsule: mechanical laws of membranes with negligible bending stiffness. Phys Rev E 69(6):061–601. https://doi.org/10.1103/PhysRevE.69.061601 Risso F, CollÉ-Paillot F, Zagzoule M (2006) Experimental investigation of a bioartificial capsule flowing in a narrow tube. J Fluid Mech 547:149–173. https://doi.org/10.1017/S0022112005007652 Rubinstein R (1999) The cross-entropy method for combinatorial and continuous optimization. Methodol Comput Appl 1(2):127–190. https://doi.org/10.1023/A:1010091220143 Saadat A, Huyke DA, Oyarzun DI et al (2020) A system for the high-throughput measurement of the shear modulus distribution of human red blood cells. Lab Chip 20(16):2927–2936. https://doi.org/10.1039/D0LC00283F Saxby DJ, Killen BA, Pizzolato C et al (2020) Machine learning methods to support personalized neuromusculoskeletal modelling. Biomech Model Mechanobiol 19(4):1169–1185. https://doi.org/10.1007/s10237-020-01367-8 Sekar V, Zhang M, Shu C et al (2019) Inverse design of airfoil using a deep convolutional neural network. Aiaa J 57(3):993–1003. https://doi.org/10.2514/1.J057894 Skalak R, Tozeren A, Zarda R et al (1973) Strain energy function of red blood cell membranes. Biophys J 13(3):245–264. https://doi.org/10.1016/S0006-3495(73)85983-1 Srivastava N, Hinton G, Krizhevsky A et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958 Sui Y, Chew YT, Roy P et al (2008) Dynamic motion of red blood cells in simple shear flow. Phys Fluids 20(11):106–112. https://doi.org/10.1063/1.3026569 Sui Y, Chew YT, Roy P et al (2008) A hybrid method to study flow-induced deformation of three-dimensional capsules. J Comput Phys 227(12):6351–6371. https://doi.org/10.1016/j.jcp.2008.03.017 Sui Y, Chen X, Chew Y et al (2010) Numerical simulation of capsule deformation in simple shear flow. Comput Fluids 39(2):242–250. https://doi.org/10.1016/j.compfluid.2009.09.001 Suzuki S, Abe K (1985) Topological structural analysis of digitized binary images by border following. Comput Vision Graph 30(1):32–46. https://doi.org/10.1016/0734-189X(85)90016-7 Takeishi N, Imai Y, Yamaguchi T et al (2015) Flow of a circulating tumor cell and red blood cells in microvessels. Phys Rev E 92(6):11–063. https://doi.org/10.1103/PhysRevE.92.063011 Walter A, Rehage H, Leonhard H (2001) Shear induced deformation of microcapsules: shape oscillations and membrane folding. Colloid Surface A 183:123–132. https://doi.org/10.1016/S0927-7757(01)00564-7 Wang Z, Sui Y, Salsac AV et al (2016) Motion of a spherical capsule in branched tube flow with finite inertia. J Fluid Mech 806:603–626. https://doi.org/10.1017/jfm.2016.603 Wang Z, Sui Y, Salsac AV et al (2018) Path selection of a spherical capsule in a microfluidic branched channel: towards the design of an enrichment device. J Fluid Mech 849:136–162. https://doi.org/10.1017/jfm.2018.414 Wang XY, Merlo A, Dupont C et al (2021) A microfluidic methodology to identify the mechanical properties of capsules: comparison with a microrheometric approach. Flow. https://doi.org/10.1017/flo.2021.8 Wu PH, Aroush DRB, Asnacios A et al (2018) A comparison of methods to assess cell mechanical properties. Nat Methods 15:491–498. https://doi.org/10.1038/s41592-018-0015-1 Xiao L, Liu Y, Chen S et al (2017) Effects of flowing RBCS on adhesion of a circulating tumor cell in microvessels. Biomech Model Mechanobiol 16(2):597–610. https://doi.org/10.1007/s10237-016-0839-5 Xie K, DeLoubens C, Dubreuil F et al (2017) Interfacial rheological properties of self-assembling biopolymer microcapsules. Soft matter 13(36):6208–6217. https://doi.org/10.1039/C7SM01377A Zhong-can OY, Helfrich W (1989) Bending energy of vesicle membranes: General expressions for the first, second, and third variation of the shape energy and applications to spheres and cylinders. Phys Rev A 39(10):5280. https://doi.org/10.1103/PhysRevA.39.5280 Zhou Z, Ngan AHW, Tang B et al (2012) Reliable measurement of elastic modulus of cells by nanoindentation in an atomic force microscope. J Mech Behav Biomed 8:134–142. https://doi.org/10.1016/j.jmbbm.2011.11.010 Zhu Y, Tian FB, Young J et al (2021) A numerical study of fish adaption behaviors in complex environments with a deep reinforcement learning and immersed boundary-lattice boltzmann method. Sci Rep 11(1):1–20. https://doi.org/10.1038/s41598-021-81124-8