Geometry-Aware State Space Model: A New Paradigm for Whole-Slide Image Representation

• URL: http://arxiv.org/abs/2605.05164v1
• Date: Wed, 06 May 2026 17:33:30 GMT
• Title: Geometry-Aware State Space Model: A New Paradigm for Whole-Slide Image Representation
• Abstract summary: Whole-slide images (WSIs) digitize tissue specimens at gigapixel resolution.<n>Current methods implicitly embed patch representations in homogeneous Euclidean spaces.<n>We introduce a hybrid hyperbolic-Euclidean representation that embeds WSI features in dual geometric spaces.
• Score: 8.483387656208363
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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, we 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, we develop BatMIL, a WSI classification framework that leverages both geometric spaces. To model long-range dependencies among thousands of patches, we employ a structured state space sequence model (S4) backbone that encodes patch sequences with linear computational complexity. Furthermore, to account for regional heterogeneity, we introduce a chunk-level mixture-of-experts (MoE) module that groups patches into regions and dynamically routes them to specialized subnetworks, improving representational capacity while reducing redundant computation. 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.

Related papers

• Hierarchical Prototype-based Domain Priors for Multiple Instance Learning in Multimodal Histopathology Analysis [4.767529995968428]
  Digital pathology has fundamentally altered diagnostic by enabling the computational analysis of gigapixel Whole Slide Images (WSIs)<n>We propose the Hierarchical Prototype-based Domain Priors framework, a unified multimodal approach for joint histopathology diagnosis and prognosis.
  arXiv  Detail & Related papers  (2026-04-27T02:51:57Z)
• Hierarchical Mesh Transformers with Topology-Guided Pretraining for Morphometric Analysis of Brain Structures [7.663406601980095]
  We introduce a hierarchical transformer framework for heterogeneous mesh analysis.<n>A feature projection module maps variable-length per-vertex clinical descriptors into the spatial hierarchy.<n>We validate our approach on Alzheimer's disease classification and amyloid burden prediction using volumetric brain meshes from ADNI, as well as focal cortical dysplasia detection on cortical surface meshes from the MELD dataset.
  arXiv  Detail & Related papers  (2026-04-06T22:27:36Z)
• Jigsaw Regularization in Whole-Slide Image Classification [0.0]
  Computational pathology involves the digitization of stained tissues into whole-slide images (WSIs) that contain billions of pixels arranged as contiguous patches.<n> Statistical analysis of WSIs largely focuses on classification via multiple instance learning (MIL), in which slide-level labels are inferred from unlabeled patches.<n>This work builds on recent graph-based methods that aim to incorporate spatial awareness into MIL.<n>We find that a combination of these two features markedly improves classification over state-of-the-art attention-based MIL approaches on benchmark datasets in breast, head-and-neck, and colon cancer.
  arXiv  Detail & Related papers  (2026-03-20T18:04:25Z)
• Layout-Guided Controllable Pathology Image Generation with In-Context Diffusion Transformers [57.54843029965778]
  Controllable pathology image synthesis requires reliable regulation of spatial layout, tissue morphology, and semantic detail.<n>We propose In-Context Diffusion Transformer (IC-DiT), a layout-aware generative model that incorporates spatial layouts, textual descriptions, and visual embeddings into a unified diffusion transformer.<n>IC-DiT achieves higher fidelity, stronger spatial controllability, and better diagnostic consistency than existing methods.
  arXiv  Detail & Related papers  (2026-03-11T06:14:11Z)
• A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis [82.01597026329158]
  We introduce a Correlation-Regulated Alignment Framework for Tissue Synthesis (CRAFTS) for pathology-specific text-to-image synthesis.<n>CRAFTS incorporates a novel alignment mechanism that suppresses semantic drift to ensure biological accuracy.<n>This model generates diverse pathological images spanning 30 cancer types, with quality rigorously validated by objective metrics and pathologist evaluations.
  arXiv  Detail & Related papers  (2025-12-15T10:22:43Z)
• HiFusion: Hierarchical Intra-Spot Alignment and Regional Context Fusion for Spatial Gene Expression Prediction from Histopathology [7.982889842329205]
  HiFusion is a novel deep learning framework that integrates two complementary components.<n>We show that HiFusion achieves state-of-the-art performance across both 2D slide-wise cross-validation and more challenging 3D sample-specific scenarios.<n>These results underscore HiFusion's potential as a robust, accurate, and scalable solution for ST inference from routine histopathology.
  arXiv  Detail & Related papers  (2025-11-17T04:47:39Z)
• MamMIL: Multiple Instance Learning for Whole Slide Images with State Space Models [56.37780601189795]
  We propose a framework named MamMIL for WSI analysis. We represent each WSI as an undirected graph. To address the problem that Mamba can only process 1D sequences, we propose a topology-aware scanning mechanism.
  arXiv  Detail & Related papers  (2024-03-08T09:02:13Z)
• Dual-scale Enhanced and Cross-generative Consistency Learning for Semi-supervised Medical Image Segmentation [49.57907601086494]
  Medical image segmentation plays a crucial role in computer-aided diagnosis. We propose a novel Dual-scale Enhanced and Cross-generative consistency learning framework for semi-supervised medical image (DEC-Seg)
  arXiv  Detail & Related papers  (2023-12-26T12:56:31Z)
• The Whole Pathological Slide Classification via Weakly Supervised Learning [7.313528558452559]
  We introduce two pathological priors: nuclear disease of cells and spatial correlation of pathological tiles. We propose a data augmentation method that utilizes stain separation during extractor training. We then describe the spatial relationships between the tiles using an adjacency matrix. By integrating these two views, we designed a multi-instance framework for analyzing H&E-stained tissue images.
  arXiv  Detail & Related papers  (2023-07-12T16:14:23Z)
• Hierarchical Transformer for Survival Prediction Using Multimodality Whole Slide Images and Genomics [63.76637479503006]
  Learning good representation of giga-pixel level whole slide pathology images (WSI) for downstream tasks is critical. This paper proposes a hierarchical-based multimodal transformer framework that learns a hierarchical mapping between pathology images and corresponding genes. Our architecture requires fewer GPU resources compared with benchmark methods while maintaining better WSI representation ability.
  arXiv  Detail & Related papers  (2022-11-29T23:47:56Z)
• Multi-Scale Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition [140.18376685167857]
  A simple yet effective multi-scale semantics-guided neural network is proposed for skeleton-based action recognition. MS-SGN achieves the state-of-the-art performance on the NTU60, NTU120, and SYSU datasets.
  arXiv  Detail & Related papers  (2021-11-07T03:50:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.