MambaMIL+: Modeling Long-Term Contextual Patterns for Gigapixel Whole Slide Image

TL;DR

MambaMIL+ is a novel framework for gigapixel whole slide image analysis that effectively models long-range spatial context and dependencies, outperforming previous methods across multiple diagnostic and predictive tasks.

Contribution

It introduces overlapping scanning, a selective stripe position encoder, and a contextual token selection mechanism to enhance spatial and long-range dependency modeling in MIL for WSIs.

Findings

Achieves state-of-the-art results on 20 benchmarks

Demonstrates robustness across various feature extractors

Improves long-range spatial context modeling in WSI analysis

Abstract

Whole-slide images (WSIs) are an important data modality in computational pathology, yet their gigapixel resolution and lack of fine-grained annotations challenge conventional deep learning models. Multiple instance learning (MIL) offers a solution by treating each WSI as a bag of patch-level instances, but effectively modeling ultra-long sequences with rich spatial context remains difficult. Recently, Mamba has emerged as a promising alternative for long sequence learning, scaling linearly to thousands of tokens. However, despite its efficiency, it still suffers from limited spatial context modeling and memory decay, constraining its effectiveness to WSI analysis. To address these limitations, we propose MambaMIL+, a new MIL framework that explicitly integrates spatial context while maintaining long-range dependency modeling without memory forgetting. Specifically, MambaMIL+ introduces 1) overlapping scanning, which restructures the patch sequence to embed spatial continuity and instance correlations; 2) a selective stripe position encoder (S2PE) that encodes positional information while mitigating the biases of fixed scanning orders; and 3) a contextual token selection (CTS) mechanism, which leverages supervisory knowledge to dynamically enlarge the contextual memory for stable long-range modeling. Extensive experiments on 20 benchmarks across diagnostic classification, molecular prediction, and survival analysis demonstrate that MambaMIL+ consistently achieves state-of-the-art performance under three feature extractors (ResNet-50, PLIP, and CONCH), highlighting its effectiveness and robustness for large-scale computational pathology