Fig. 3: Comparison of morphological feature distributions at the start and end of simulations reflecting changes in cell morphology, for the best and worst parameter sets according to the metric m, Eq. (3).
From: Improving 3D deep learning segmentation with biophysically motivated cell synthesis
Data is derived from a manually segmented image patch. Individual Wasserstein distances, quantifying the variations between the simulation’s start and end for each feature, are marked above the plots for the best (blue, λV = 10.0, λA = 0.001, J(c-c) = 2.0, J(c-m) = 55.0) and worst (orange, λV = 0.001, λA = 10.0, J(c-c) = 10.0, J(c-m) = 10.0) parameter sets. Boxes indicate median and quartiles of data, while whiskers encompass all values within 1.5 times the IQR. All individual data points are shown.
