HyperPath: Knowledge-Guided Hyperbolic Semantic Hierarchy Modeling for WSI Analysis

TL;DR

HyperPath introduces a knowledge-guided hyperbolic embedding framework that models the semantic hierarchy of whole slide images in pathology, improving classification accuracy by leveraging textual descriptions and hyperbolic geometry.

Contribution

It is the first to integrate textual knowledge with hyperbolic space modeling for WSI analysis, capturing semantic hierarchies more effectively than Euclidean methods.

Findings

Achieves superior classification performance on WSI datasets.

Effectively models semantic hierarchies using hyperbolic embeddings.

Enhances cross-modal alignment with novel angular loss.

Abstract

Pathology is essential for cancer diagnosis, with multiple instance learning (MIL) widely used for whole slide image (WSI) analysis. WSIs exhibit a natural hierarchy -- patches, regions, and slides -- with distinct semantic associations. While some methods attempt to leverage this hierarchy for improved representation, they predominantly rely on Euclidean embeddings, which struggle to fully capture semantic hierarchies. To address this limitation, we propose HyperPath, a novel method that integrates knowledge from textual descriptions to guide the modeling of semantic hierarchies of WSIs in hyperbolic space, thereby enhancing WSI classification. Our approach adapts both visual and textual features extracted by pathology vision-language foundation models to the hyperbolic space. We design an Angular Modality Alignment Loss to ensure robust cross-modal alignment, while a Semantic Hierarchy Consistency Loss further refines feature hierarchies through entailment and contradiction relationships and thus enhance semantic coherence. The classification is performed with geodesic distance, which measures the similarity between entities in the hyperbolic semantic hierarchy. This eliminates the need for linear classifiers and enables a geometry-aware approach to WSI analysis. Extensive experiments show that our method achieves superior performance across tasks compared to existing methods, highlighting the potential of hyperbolic embeddings for WSI analysis.