Wrinkle force microscopy: a new machine learning based approach to predict cell mechanics from images

Abstract

In this paper, we propose a new machine learning system that can predict the cellular force distributions from the microscope images. The full process can be divided into three steps. First, we culture the cells on a special substrate and measure both the cellular contractile force and the substrate wrinkles simultaneously. The cellular contractile forces are obtained using the traction force microscopy (TFM), while cells generate wrinkles thanks to our original plasma-irradiated substrates. Second, the wrinkle positions are extracted from the microscope images by using SW-UNet. Third, we train the machine learning system with GAN (generative adversarial network) by using sets of corresponding two images, the force distributions and the input images (raw microscope images or extracted wrinkle images), as the training data. The network understands the way to convert the input images to the force distributions from the training. After sufficient training, the network can be utilized to predict the cellular forces just from the input images. Comparing with the TFM experiment (test data), our system has 33-35% errors in the force magnitude prediction and angle errors 19-20 o in the force direction. The system would be a powerful tool to evaluate the cellular forces efficiently because the forces can be predicted just by observing the cells, which is a way simpler method compared to the TFM experiment. We believe that our machine learning based system will be an useful method for other cellular assay applicants and researches in the future.

Mechanics of Live Cell Elimination

“…Since we conjecture that both topological defect- and disclination-mediated extrusion mechanisms are closely linked with stress localization, we characterize the in-plane and out-of-plane stresses associated with the simulated monolayer. We compute a coarse-grained stress field [44, 45], where represents the center of the coarse-grained volume, corresponding to coarse-graining length and unit vector Fig. 3(c) shows the evolution of local isotropic stress, σ iso = (1/3) tr σ , and an out-of-plane component of the shear stress, σ xz , aver-aged over an extruding cell i and its nearest-neighbors, nn .…”

“…Since we conjecture that both topological defect-and disclination-mediated extrusion mechanisms are closely linked with stress localization, we characterize the in-plane and out-of-plane stresses associated with the simulated monolayer. We compute a coarse-grained stress field [44,45],…”