Improving the feature representation ability is the foundation of many whole slide pathological image (WSIs) tasks. Recent works have achieved great success in pathological-specific self-supervised learning (SSL). However, most of them only focus on learning patch-level representations, thus there is still a gap between pretext and slide-level downstream tasks, e.g., subtyping, grading and staging. Aiming towards slide-level representations, we propose Slide-Level Prototypical Distillation (SLPD) to explore intra- and inter-slide semantic structures for context modeling on WSIs. Specifically, we iteratively perform intra-slide clustering for the regions (4096x4096 patches) within each WSI to yield the prototypes and encourage the region representations to be closer to the assigned prototypes. By representing each slide with its prototypes, we further select similar slides by the set distance of prototypes and assign the regions by cross-slide prototypes for distillation. SLPD achieves state-of-the-art results on multiple slide-level benchmarks and demonstrates that representation learning of semantic structures of slides can make a suitable proxy task for WSI analysis. Code will be available at https://github.com/Carboxy/SLPD.

翻译：提升特征表示能力是诸多全切片病理图像（WSI）任务的基础。近期研究在病理特异性自监督学习（SSL）领域取得了显著进展，然而大多数方法仅关注于学习图像块级表征，导致预训练任务与切片级下游任务（如亚型分类、分级、分期）之间仍存在语义鸿沟。针对切片级表征学习，本文提出滑动层级原型蒸馏（SLPD），通过挖掘切片内与切片间的语义结构实现WSI上下文建模。具体而言，我们对每张WSI中的区域（4096×4096图像块）进行迭代式切片内聚类以生成原型，并促使区域表征向其对应原型靠近。通过原型表征整张切片后，进一步依据原型的集合距离筛选相似切片，并利用跨切片原型完成区域蒸馏任务。SLPD在多个切片级基准测试中取得最优结果，证明滑动语义结构的表征学习可作为WSI分析的合适代理任务。代码将发布于https://github.com/Carboxy/SLPD。