Magnification-Aware Distillation (MAD): A Self-Supervised Framework for Unified Representation Learning in Gigapixel Whole-Slide Images

TL;DR

This paper presents MAD, a self-supervised framework that learns stable, resolution-invariant representations of gigapixel whole-slide images by linking different magnification levels, improving robustness and consistency in pathology analysis.

Contribution

MAD introduces a cross-scale distillation method that unifies multi-magnification information without annotations, enabling scalable and robust WSI analysis.

Findings

Linear classifiers retain 96.7% performance across magnifications

Segmentation remains consistent and anatomically accurate across scales

MAD-NP achieves resolution-invariant representations in WSI analysis

Abstract

Whole-slide images (WSIs) contain tissue information distributed across multiple magnification levels, yet most self-supervised methods treat these scales as independent views. This separation prevents models from learning representations that remain stable when resolution changes, a key requirement for practical neuropathology workflows. This study introduces Magnification-Aware Distillation (MAD), a self-supervised strategy that links low-magnification context with spatially aligned high-magnification detail, enabling the model to learn how coarse tissue structure relates to fine cellular patterns. The resulting foundation model, MAD-NP, is trained entirely through this cross-scale correspondence without annotations. A linear classifier trained only on 10x embeddings maintains 96.7% of its performance when applied to unseen 40x tiles, demonstrating strong resolution-invariant representation learning. Segmentation outputs remain consistent across magnifications, preserving anatomical boundaries and minimizing noise. These results highlight the feasibility of scalable, magnification-robust WSI analysis using a unified embedding space