aThe FindFoci algorithm was trained on individual images and the highest F1-score reported and averaged over the 21 images per experimenter. The analysis was performed using the original selected pixe
In all cases, latent means and standard deviations were set as μj1 = 4, μj2 = 1, σj1 = 3 and σj2 = 2. Unless otherwise stated, our simulations were based on: I = 60 cells, J = 300 features, 20% ZI rat