Hypergraph Mamba for Efficient Whole Slide Image Understanding

TL;DR

This paper introduces WSI-HGMamba, a hypergraph neural network framework that efficiently models complex spatial relationships in Whole Slide Images, achieving high accuracy with significantly reduced computational costs.

Contribution

It unifies hypergraph neural networks with state space models to improve scalability and efficiency in WSI analysis, outperforming existing methods.

Findings

Up to 7x reduction in FLOPs compared to Transformers

Achieves superior accuracy on multiple WSI benchmarks

Demonstrates scalability and efficiency in large-scale histopathology analysis

Abstract

Whole Slide Images (WSIs) in histopathology pose a significant challenge for extensive medical image analysis due to their ultra-high resolution, massive scale, and intricate spatial relationships. Although existing Multiple Instance Learning (MIL) approaches like Graph Neural Networks (GNNs) and Transformers demonstrate strong instance-level modeling capabilities, they encounter constraints regarding scalability and computational expenses. To overcome these limitations, we introduce the WSI-HGMamba, a novel framework that unifies the high-order relational modeling capabilities of the Hypergraph Neural Networks (HGNNs) with the linear-time sequential modeling efficiency of the State Space Models. At the core of our design is the HGMamba block, which integrates message passing, hypergraph scanning & flattening, and bidirectional state space modeling (Bi-SSM), enabling the model to retain both relational and contextual cues while remaining computationally efficient. Compared to Transformer and Graph Transformer counterparts, WSI-HGMamba achieves superior performance with up to 7* reduction in FLOPs. Extensive experiments on multiple public and private WSI benchmarks demonstrate that our method provides a scalable, accurate, and efficient solution for slide-level understanding, making it a promising backbone for next-generation pathology AI systems.