让病理图像在不同放大倍数下保持一致表征，提升模型泛化能力
Magnification-Aware Distillation (MAD): A Self-Supervised Framework for Unified Representation Learning in Gigapixel Whole-Slide Images
- 通过跨尺度对齐低倍上下文与高倍细节，构建统一表征空间
- 10x特征在40x新图像上仍保持96.7%性能，实现分辨率不变表征
- 适用于需多倍率分析的数字病理学场景，尤其适合无标注训练
全切片图像（WSIs）包含分布在多个放大倍数下的组织信息，但多数自监督方法将这些尺度视为独立视图，导致模型无法学习在分辨率变化下仍稳定的表征，这限制了其在实际神经病理学工作流中的应用。本文提出放大倍数感知蒸馏（MAD），一种自监督策略，通过关联低倍上下文与空间对齐的高倍细节，使模型学习粗略组织结构与精细细胞模式之间的关系。由此训练出的基础模型MAD-NP完全基于跨尺度对应关系，无需标注。仅用10x嵌入训练的线性分类器在未见40x切片上仍保持96.7%性能，证明了强大的分辨率不变表征学习能力。分割结果在不同放大倍数下保持一致，有效保留解剖边界并减少噪声。结果表明，利用统一嵌入空间可实现可扩展、抗放大倍数变化的WSI分析。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。