Enabling Progressive Whole-slide Image Analysis with Multi-scale Pyramidal Network

2026-02-02

AI Summary

This work addresses key limitations in existing multi-scale feature fusion approaches in computational pathology, which often rely on predefined magnification levels, lack cross-scale associations, and incur high computational costs. To overcome these challenges, the authors propose a plug-and-play Multi-Scale Pyramid Network (MSPN) that enables cross-scale feature generation through grid remapping. MSPN incorporates a Coarse-to-fine Guidance Network (CGN) to reconstruct low-magnification representations from high-magnification features and integrates an attention-based multiple instance learning (MIL) framework for progressive whole-slide analysis. Notably, MSPN operates without fixed magnification levels and is compatible with diverse backbone models and MIL architectures. Extensive experiments across four clinical tasks, three backbone networks, and multiple MIL frameworks consistently demonstrate performance improvements, highlighting MSPN’s lightweight design, flexibility, and plug-and-play utility.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Multiagent Systems: Other Foundations of Multi Agent Systems

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Multiple-instance Learning (MIL) is commonly used to undertake computational pathology (CPath) tasks, and the use of multi-scale patches allows diverse features across scales to be learned. Previous studies using multi-scale features in clinical applications rely on multiple inputs across magnifications with late feature fusion, which does not retain the link between features across scales while the inputs are dependent on arbitrary, manufacturer-defined magnifications, being inflexible and computationally expensive. In this paper, we propose the Multi-scale Pyramidal Network (MSPN), which is plug-and-play over attention-based MIL that introduces progressive multi-scale analysis on WSI. Our MSPN consists of (1) grid-based remapping that uses high magnification features to derive coarse features and (2) the coarse guidance network (CGN) that learns coarse contexts. We benchmark MSPN as an add-on module to 4 attention-based frameworks using 4 clinically relevant tasks across 3 types of foundation model, as well as the pre-trained MIL framework. We show that MSPN consistently improves MIL across the compared configurations and tasks, while being lightweight and easy-to-use.

Problem

• whole-slide image
• multi-scale analysis
• computational pathology
• multiple-instance learning
• feature fusion

Innovation

• Multi-scale Pyramidal Network
• Progressive Whole-slide Image Analysis
• Coarse Guidance Network
• Attention-based MIL
• Computational Pathology