A Multi-scale Linear-time Encoder for Whole-Slide Image Analysis
On the map: State-space sequence models (S4, Mamba) → Mamba for medical image analysis
Abstract (arXiv)
We introduce Multi-scale Adaptive Recurrent Biomedical Linear-time Encoder (MARBLE), the first textitpurely Mamba-based multi-state multiple instance learning (MIL) framework for whole-slide image (WSI) analysis. MARBLE processes multiple magnification levels in parallel and integrates coarse-to-fine reasoning within a linear-time state-space model, efficiently capturing cross-scale dependencies with minimal parameter overhead. WSI analysis remains challenging due to gigapixel resolutions and hierarchical magnifications, while existing MIL methods typically operate at a single scale and transformer-based approaches suffer from quadratic attention costs. By coupling parallel multi-scale processing with linear-time sequence modeling, MARBLE provides a scalable and modular alternative to attention-based architectures. Experiments on five public datasets show improvements of up to 6.9% in AUC, 20.3% in accuracy, and 2.3% in C-index, establishing MARBLE as an efficient and generalizable framework for multi-scale WSI analysis.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Mamba for medical image analysis, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 9 of its 19 references that are in the map. First posted on arXiv 2 Feb 2026.
Builds on
9 of 19 references.
Closest ancestors · 2
Same direction, newest first
- 2024MambaMIL: Enhancing Long Sequence Modeling with Sequence Reordering in Computational Pathology11 Mar
- 2023Structured State Space Models for Multiple Instance Learning in Digital Pathology27 Jun
Other references · 7
- 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,336
- 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 745
- 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 555
- 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 478
- 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 256
- 20242DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classificationcited by 35
- 2023Diagnose Like a Pathologist: Transformer-Enabled Hierarchical Attention-Guided Multiple Instance Learning for Whole Slide Image Classificationcited by 27
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025PathRWKV: Enhancing Whole Slide Image Inference with Asymmetric Recurrent Modeling
- 2026MambaBack: Bridging Local Features and Global Contexts in Whole Slide Image Analysis
- 2025MambaMIL+: Modeling Long-Term Contextual Patterns for Gigapixel Whole Slide Image
- 2026ReconMIL: Synergizing Latent Space Reconstruction with Bi-Stream Mamba for Whole Slide Image Analysis
- 2025Advancing Multiple Instance Learning with Continual Learning for Whole Slide Imaging
- 2026MoEMambaMIL: Structure-Aware Selective State Space Modeling for Whole-Slide Image Analysis
- 2025LadderMIL: Multiple Instance Learning with Coarse-to-Fine Self-Distillation
- 2026KHiM-Mamba: Injecting Pathology Knowledge into Mamba via Hidden-State Modulation for Whole Slide Image Analysis