WSD-MIL: Window Scale Decay Multiple Instance Learning for Whole Slide Image Classification

TL;DR

This paper introduces WSD-MIL, a novel multiple instance learning method for whole slide image classification that models multi-scale tumor regions efficiently, improving accuracy and reducing computational memory.

Contribution

WSD-MIL employs a window scale decay attention mechanism and a region gate module to better capture multi-scale tumor regions and enhance global information modeling in WSIs.

Findings

Achieves state-of-the-art results on CAMELYON16 and TCGA-BRCA datasets.

Reduces 62% of computational memory compared to existing methods.

Effectively models tumor regions of varying scales.

Abstract

In recent years, the integration of pre-trained foundational models with multiple instance learning (MIL) has improved diagnostic accuracy in computational pathology. However, existing MIL methods focus on optimizing feature extractors and aggregation strategies while overlooking the complex semantic relationships among instances within whole slide image (WSI). Although Transformer-based MIL approaches aiming to model instance dependencies, the quadratic computational complexity limits their scalability to large-scale WSIs. Moreover, due to the pronounced variations in tumor region scales across different WSIs, existing Transformer-based methods employing fixed-scale attention mechanisms face significant challenges in precisely capturing local instance correlations and fail to account for the distance-based decay effect of patch relevance. To address these challenges, we propose window scale decay MIL (WSD-MIL), designed to enhance the capacity to model tumor regions of varying scales while improving computational efficiency. WSD-MIL comprises: 1) a window scale decay based attention module, which employs a cluster-based sampling strategy to reduce computational costs while progressively decaying attention window-scale to capture local instance relationships at varying scales; and 2) a squeeze-and-excitation based region gate module, which dynamically adjusts window weights to enhance global information modeling. Experimental results demonstrate that WSD-MIL achieves state-of-the-art performance on the CAMELYON16 and TCGA-BRCA datasets while reducing 62% of the computational memory. The code will be publicly available.