MoEMambaMIL: Structure-Aware Selective State Space Modeling for Whole-Slide Image Analysis

TL;DR

MoEMambaMIL introduces a structure-aware state space model that effectively captures hierarchical spatial dependencies in whole-slide images, significantly improving performance on multiple diagnostic tasks.

Contribution

It presents a novel framework combining region-nested selective scanning with mixture-of-experts in state space models for hierarchical WSI analysis.

Findings

Achieves state-of-the-art results on 9 downstream tasks.

Effectively models long sequences with hierarchical spatial structure.

Promotes expert specialization for diverse diagnostic patterns.

Abstract

Whole-slide image (WSI) analysis is challenging due to the gigapixel scale of slides and their inherent hierarchical multi-resolution structure. Existing multiple instance learning (MIL) approaches often model WSIs as unordered collections of patches, which limits their ability to capture structured dependencies between global tissue organization and local cellular patterns. Although recent State Space Models (SSMs) enable efficient modeling of long sequences, how to structure WSI tokens to fully exploit their spatial hierarchy remains an open problem.We propose MoEMambaMIL, a structure-aware SSM framework for WSI analysis that integrates region-nested selective scanning with mixture-of-experts (MoE) modeling. Leveraging multi-resolution preprocessing, MoEMambaMIL organizes patch tokens into region-aware sequences that preserve spatial containment across resolutions. On top of this structured sequence, we decouple resolution-aware encoding and region-adaptive contextual modeling via a combination of static, resolution-specific experts and dynamic sparse experts with learned routing. This design enables efficient long-sequence modeling while promoting expert specialization across heterogeneous diagnostic patterns. Experiments demonstrate that MoEMambaMIL achieves the best performance across 9 downstream tasks.