Persistent entropy: a scale-invariant topological statistic for analyzing cell arrangements

Abstract

In this work, we develop a method for detecting differences in the topological distribution of cells forming epithelial tissues. In particular, we extract topological information from their images using persistent homology and a summary statistic called persistent entropy. This method is scale invariant, robust to noise and sensitive to global topological features of the tissue. We have found significant differences between chick neuroepithelium and epithelium of Drosophila wing discs in both, larva and prepupal stages. Besides, we have tested our method, with good results, with images of mathematical tesselations that model biological tissues.