Hyperbolic Representation Learning for Spatial Biology: Evaluating Cell Type Hierarchies in Breast Cancer Imaging Data

Youssef Wally, Johan Mylius-Kroken, Michael Kampffmeyer, Rezvan Ehsani, Vladan Milosevic, Elisabeth Wetzer

Keywords: Mutual Information, Unsupervised Learning, Hyperbolic Representation, Lorentz Geometry, Imaging Mass Cytometry, Breast Cancer

TL;DR: We propose a geometry-agnostic mutual information framework for evaluating hyperbolic embeddings. Applied to imaging mass cytometry, Lorentzian models align best with biological hierarchies. Code for estimation and visualization is released.

Abstract: We demonstrate that hyperbolic representation learning effectively captures hierarchical cellular relationships in breast cancer. Using information-theoretic metrics, Lorentzian embeddings are shown to preserve significantly more biologically meaningful structure than Euclidean ones. Code: \url{https://github.com/youssefwally/FlatlandandBeyond}.

Serve As Reviewer: ~Youssef_Wally1

Submission Number: 11