Applications of machine learning for simulations of red blood cells in microfluidic devices

Background For optimization of microfluidic devices for the analysis of blood samples, it is useful to simulate blood cells as elastic objects in flow of blood plasma. In such numerical models, we primarily need to take into consideration the movement and behavior of the dominant component of the blood, the red blood cells. This can be done quite precisely in small channels and within a short timeframe. However, larger volumes or timescales require different approaches. Instead of simplifying the simulation, we use a neural network to predict the movement of the red blood cells. Results The neural network uses data from the numerical simulation for learning, however, the simulation needs only be run once. Alternatively, the data could come from video processing of a recording of a biological experiment. Afterwards, the network is able to predict the movement of the red blood cells because it is a system of bases that gives an approximate cell velocity at each point of the simulation channel as a linear combination of bases.In a simple box geometry, the neural network gives results comparable to predictions using fluid streamlines, however in a channel with obstacles forming slits, the neural network is about five times more accurate.The network can also be used as a discriminator between different situations. We observe about two-fold increase in mean relative error when a network trained on one geometry is used to predict trajectories in a modified geometry. Even larger increase was observed when it was used to predict trajectories of cells with different elastic properties. Conclusions While for uncomplicated box channels there is no advantage in using a system of bases instead of a simple prediction using fluid streamlines, in a more complicated geometry, the neural network is significantly more accurate. Another application of this system of bases is using it as a comparison tool for different modeled situations. This has a significant future potential when applied to processing data from videos of microfluidic flows.

[1]  Martin Slavík,et al.  Statistics for comparison of simulations and experiments of flow of blood cells , 2017 .

[2]  Martin Slavík,et al.  Simulation of Blood Flow in Microfluidic Devices for Analysing of Video from Real Experiments , 2018, IWBBIO.

[3]  Dierk Raabe,et al.  Author's Personal Copy Computers and Mathematics with Applications , 2022 .

[4]  Franck Nicoud,et al.  How should the optical tweezers experiment be used to characterize the red blood cell membrane mechanics? , 2017, Biomechanics and Modeling in Mechanobiology.

[5]  Junfei Qiao,et al.  Adaptive Computation Algorithm for RBF Neural Network , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[6]  Alessandra Carbone,et al.  Meet-U: Educating through research immersion , 2018, PLoS Comput. Biol..

[7]  M. Brandl,et al.  Cell Damage Index as Computational Indicator for Blood Cell Activation and Damage , 2018, Artificial organs.

[8]  George Em Karniadakis,et al.  Multiscale modeling of blood flow in cerebral malaria , 2009 .

[9]  Axel Arnold,et al.  ESPResSo 3.1: Molecular Dynamics Software for Coarse-Grained Models , 2013 .

[10]  J. Remacle,et al.  Gmsh: A 3‐D finite element mesh generator with built‐in pre‐ and post‐processing facilities , 2009 .

[11]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[12]  Hilde van der Togt,et al.  Publisher's Note , 2003, J. Netw. Comput. Appl..

[13]  D. Fedosov,et al.  Effect of spectrin network elasticity on the shapes of erythrocyte doublets. , 2018, Soft matter.

[14]  Gerhard Gompper,et al.  Margination and stretching of von Willebrand factor in the blood stream enable adhesion , 2017, Scientific Reports.

[15]  Rozli Zulkifli,et al.  Impact of the TiO2 Nanosolution Concentration on Heat Transfer Enhancement of the Twin Impingement Jet of a Heated Aluminum Plate , 2019, Micromachines.

[16]  Dino Di Carlo,et al.  Biophysical isolation and identification of circulating tumor cells. , 2017, Lab on a chip.

[17]  Hynek Bachratý,et al.  The sensitivity of the statistical characteristics to the selected parameters of the simulation model in the red blood cell flow simulations , 2017, 2017 International Conference on Information and Digital Technologies (IDT).

[18]  Alexander Kihm,et al.  Classification of red blood cell shapes in flow using outlier tolerant machine learning , 2018, PLoS Comput. Biol..

[19]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[20]  M A Muchtar,et al.  The morphological classification of normal and abnormal red blood cell using Self Organizing Map , 2018 .

[21]  H. Elsalamony,et al.  Healthy and unhealthy red blood cell detection in human blood smears using neural networks. , 2016, Micron.

[22]  Ivan Cimrák,et al.  Simulation study of rare cell trajectories and capture rate in periodic obstacle arrays , 2016, J. Comput. Sci..

[23]  Dmitry A. Fedosov,et al.  Multiscale Modeling of Blood Flow and Soft Matter , 2010 .

[24]  S. Wada,et al.  Analysis of Red Blood Cell Deformation under Fast Shear Flow for Better Estimation of Hemolysis , 2014, International journal for numerical methods in biomedical engineering.

[25]  M. Faivre,et al.  Impact of Channel Geometry on the Discrimination of Mechanically Impaired Red Blood Cells in Passive Microfluidics , 2017 .

[26]  Claude E. Shannon,et al.  The mathematical theory of communication , 1950 .

[27]  M. Slavík,et al.  Methods of exploring the red blood cells rotation during the simulations in devices with periodic topology , 2017, 2017 International Conference on Information and Digital Technologies (IDT).

[28]  C. Lim,et al.  Deformability study of breast cancer cells using microfluidics , 2009, Biomedical microdevices.

[29]  Markus Gusenbauer,et al.  An ESPResSo implementation of elastic objects immersed in a fluid , 2013, Comput. Phys. Commun..

[30]  Dimitry Gorinevsky,et al.  Radial basis function network approximation and learning in task-dependent feedforward control of nonlinear dynamical systems , 1998 .

[31]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[32]  Burkhard Dünweg,et al.  Lattice Boltzmann Simulation of Polymer-Solvent Systems , 1998 .

[33]  James J. Feng,et al.  How malaria parasites reduce the deformability of infected red blood cells. , 2012, Biophysical journal.

[34]  Christophe Geuzaine,et al.  Gmsh: A 3‐D finite element mesh generator with built‐in pre‐ and post‐processing facilities , 2009 .

[35]  V. Martinelli,et al.  Red blood cell deformation in microconfined flow , 2009 .

[36]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[37]  Makoto Kaneko,et al.  An On-Chip RBC Deformability Checker Significantly Improves Velocity-Deformation Correlation , 2016, Micromachines.

[38]  Subra Suresh,et al.  Circulating Tumor Cell Phenotyping via High-Throughput Acoustic Separation. , 2018, Small.

[39]  Alexander Kihm,et al.  Numerical-experimental observation of shape bistability of red blood cells flowing in a microchannel. , 2017, Soft matter.