Multi-Scale Representation of Follicular Lymphoma Pathology Images in a Single Hyperbolic Space
This work addresses the challenge of analyzing hierarchical structures in medical images for pathology, though it appears incremental as it applies existing hyperbolic space methods to a specific domain.
The paper tackles the problem of representing follicular lymphoma pathology images across multiple scales by embedding them into a single hyperbolic space using self-supervised learning, resulting in learned representations that capture disease state and cell type variations.
We propose a method for representing malignant lymphoma pathology images, from high-resolution cell nuclei to low-resolution tissue images, within a single hyperbolic space using self-supervised learning. To capture morphological changes that occur across scales during disease progression, our approach embeds tissue and corresponding nucleus images close to each other based on inclusion relationships. Using the Poincaré ball as the feature space enables effective encoding of this hierarchical structure. The learned representations capture both disease state and cell type variations.