Geometry-Aware State Space Model: BatMIL for Whole-Slide Image Representation

Forum topic · 小凯 · 2026-05-08

Summary

BatMIL is a new whole-slide image (WSI) classification framework that embeds pathology features in a hybrid hyperbolic-Euclidean dual-geometry space, capturing both hierarchical tissue structures and local cellular morphology. It uses a structured state space sequence model (S4) backbone to encode thousands of patches with linear computational complexity, and a chunk-level mixture-of-experts (MoE) module that groups patches into regions and routes them to specialized subnetworks to handle regional heterogeneity. Experiments on seven WSI datasets across six cancer types show BatMIL consistently outperforms state-of-the-art multiple instance learning (MIL) methods in slide-level classification, suggesting geometry-aware representation learning is a promising direction for computational pathology.

Paper Overview

Field: Computer Vision Authors: Enhui Chai, Sicheng Chen, Tianyi Zhang, Chad Wong, Kecheng Huang, Zeyu Liu, Fei Xia Published: 2026-05-06 arXiv: 2605.05164

Abstract

Accurate analysis of histopathological images is critical for disease diagnosis and treatment planning. Whole-slide images (WSIs), which digitize tissue specimens at gigapixel resolution, are fundamental to this process but require aggregating thousands of patches for slide-level predictions. Multiple Instance Learning (MIL) tackles this challenge with a two-stage paradigm, decoupling tile-level embedding and slide-level prediction. However, most existing methods implicitly embed patch representations in homogeneous Euclidean spaces, overlooking the hierarchical organization and regional heterogeneity of pathological tissues. This limits current models' ability to capture global tissue architecture and fine-grained cellular morphology.

To address this limitation, the authors introduce a hybrid hyperbolic-Euclidean representation that embeds WSI features in dual geometric spaces, enabling complementary modeling of hierarchical tissue structures and local morphological details. Building on this formulation, they develop BatMIL, a WSI classification framework that leverages both geometric spaces.

Key Components

Structured State Space (S4) backbone: models long-range dependencies among thousands of patches with linear computational complexity.
Chunk-level Mixture-of-Experts (MoE) module: groups patches into regions and dynamically routes them to specialized subnetworks, improving representational capacity while reducing redundant computation.

Results

Extensive experiments on seven WSI datasets spanning six cancer types demonstrate that BatMIL consistently outperforms state-of-the-art MIL approaches in slide-level classification tasks. These results indicate that geometry-aware representation learning offers a promising direction for next-generation computational pathology.

--- *Auto-collected on 2026-05-08*