Characterising epithelial tissues using persistent entropy
This work addresses the problem of tissue characterization for researchers in computational biology or medical imaging, but it appears incremental as it applies an existing method to a new domain.
The authors tackled the problem of characterizing epithelial tissues by applying persistent entropy, a novel topological statistic, to images, and found that it effectively summarizes topological and geometric information from α-complexes and persistent homology, revealing significant differences in the tissues.
In this paper, we apply persistent entropy, a novel topological statistic, for characterization of images of epithelial tissues. We have found out that persistent entropy is able to summarize topological and geometric information encoded by α-complexes and persistent homology. After using some statistical tests, we can guarantee the existence of significant differences in the studied tissues.