Traction force microscopy by deep learning

Cells interact mechanically with their surrounding by exerting forces and sensing forces or force-induced displacements. Traction force microscopy (TFM), purported to map cell-generated forces or stresses, represents an important tool that has powered the rapid advances in mechanobiology. However, to solve the ill-posted mathematical problem, its implementation has involved regularization and the associated compromises in accuracy and resolution. Here we applied neural network-based deep learning as a novel approach for TFM. We modified a network for processing images to process vector fields of stress and strain. Furthermore, we adapted a mathematical model for cell migration to generate large sets of simulated stresses and strains for training the network. We found that deep learning-based TFM yielded results qualitatively similar to those from conventional methods but at a higher accuracy and resolution. The speed and performance of deep learning TFM make it an appealing alternative to conventional methods for characterizing mechanical interactions between cells and the environment. Statement of Significance Traction Force Microscopy has served as a fundamental driving force for mechanobiology. However, its nature as an ill-posed inverse problem has posed serious challenges for conventional mathematical approaches. The present study, facilitated by large sets of simulated stresses and strains, describes a novel approach using deep learning for the calculation of traction stress distribution. By adapting the UNet neural network for handling vector fields, we show that deep learning is able to minimize much of the limitations of conventional approaches to generate results with speed, accuracy, and resolution.

[1]  Pablo A Iglesias,et al.  Cells navigate with a local-excitation, global-inhibition-biased excitable network , 2010, Proceedings of the National Academy of Sciences.

[2]  N. Balaban,et al.  Calculation of forces at focal adhesions from elastic substrate data: the effect of localized force and the need for regularization. , 2002, Biophysical journal.

[3]  Ulrich S Schwarz,et al.  Cell-ECM traction force modulates endogenous tension at cell–cell contacts , 2011, Proceedings of the National Academy of Sciences.

[4]  S. Sen,et al.  Matrix Elasticity Directs Stem Cell Lineage Specification , 2006, Cell.

[5]  Yu-Li Wang,et al.  The regulation of traction force in relation to cell shape and focal adhesions. , 2011, Biomaterials.

[6]  K. Beningo,et al.  Nascent Focal Adhesions Are Responsible for the Generation of Strong Propulsive Forces in Migrating Fibroblasts , 2001, The Journal of cell biology.

[7]  Lewis H Romer,et al.  Cell traction forces direct fibronectin matrix assembly. , 2009, Biophysical journal.

[8]  Ulrich S Schwarz,et al.  Optimization of traction force microscopy for micron-sized focal adhesions , 2010, Journal of physics. Condensed matter : an Institute of Physics journal.

[9]  Christopher S. Chen,et al.  The mechanical regulation of integrin–cadherin crosstalk organizes cells, signaling and forces , 2016, Journal of Cell Science.

[10]  Jonas Adler,et al.  Solving ill-posed inverse problems using iterative deep neural networks , 2017, ArXiv.

[11]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[12]  Roger Lui,et al.  Exploring the control circuit of cell migration by mathematical modeling. , 2008, Biophysical journal.

[13]  M. Dembo,et al.  Stresses at the cell-to-substrate interface during locomotion of fibroblasts. , 1999, Biophysical journal.

[14]  M. Dembo,et al.  Substrate flexibility regulates growth and apoptosis of normal but not transformed cells. , 2000, American journal of physiology. Cell physiology.

[15]  Gerhard Gompper,et al.  Traction force microscopy with optimized regularization and automated Bayesian parameter selection for comparing cells , 2018, Scientific Reports.

[16]  M. Schwartz,et al.  Endothelial fluid shear stress sensing in vascular health and disease. , 2016, The Journal of clinical investigation.

[17]  R. Fässler,et al.  Integrin-mediated mechanotransduction , 2016, The Journal of cell biology.

[18]  Patrick W Oakes,et al.  Spatiotemporal constraints on the force-dependent growth of focal adhesions. , 2011, Biophysical journal.

[19]  Arrate Muñoz-Barrutia,et al.  Full L1-regularized Traction Force Microscopy over whole cells , 2017, BMC Bioinformatics.

[20]  Manuel Théry,et al.  Measurement of cell traction forces with ImageJ. , 2015, Methods in cell biology.

[21]  Ulrich S Schwarz,et al.  Traction force microscopy on soft elastic substrates: A guide to recent computational advances. , 2015, Biochimica et biophysica acta.

[22]  Clare M Waterman,et al.  High resolution traction force microscopy based on experimental and computational advances. , 2008, Biophysical journal.

[23]  M. Dembo,et al.  Cell movement is guided by the rigidity of the substrate. , 2000, Biophysical journal.

[24]  Olaf Ronneberger,et al.  Invited Talk: U-Net Convolutional Networks for Biomedical Image Segmentation , 2017, Bildverarbeitung für die Medizin.

[25]  Marco Fritzsche,et al.  The future of traction force microscopy , 2018 .

[26]  Yu-Li Wang,et al.  Fibroblasts probe substrate rigidity with filopodia extensions before occupying an area , 2014, Proceedings of the National Academy of Sciences.