放大意识蒸馏（MAD）：一种用于吉像素整张图像统一表征学习的自监督框架
Magnification-Aware Distillation (MAD): A Self-Supervised Framework for Unified Representation Learning in Gigapixel Whole-Slide Images
AI总结：
MAD通过跨尺度对应关系学习吉像素整张图像的统一表征，实现放大不变的表征学习和分割一致性。
摘要：
整张图像（WSI）包含在多个放大级别分布的组织信息，但大多数自监督方法将这些尺度视为独立的视图。这种分离阻止了模型学习在分辨率变化时仍保持稳定的表征，这是实际神经病学工作流程的关键要求。本研究引入了放大意识蒸馏（MAD），一种自监督策略，将低放大级别的上下文与空间对齐的高放大细节联系起来，使模型能够学习粗组织结构如何与细细胞模式相关联。所得到的基础模型MAD-NP完全通过这种跨尺度对应关系进行训练。一个仅在10倍放大嵌入上训练的线性分类器在应用于未见过的40倍放大切片时仍能保持96.7%的性能，这展示了强大的分辨率不变表征学习能力。分割输出在不同放大级别下保持一致，保持解剖边界并最小化噪声。这些结果突显了使用统一嵌入空间进行可扩展且放大鲁棒的WSI分析的可行性。
英文摘要：
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
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
