SLPD: Slide-level Prototypical Distillation for WSIs
This work addresses the need for improved slide-level feature representation in medical image analysis, which is crucial for tasks like cancer diagnosis and prognosis, but it is incremental as it builds on existing self-supervised learning methods.
The authors tackled the problem of learning slide-level representations for whole slide pathological images (WSIs) to bridge the gap between patch-level self-supervised learning and downstream tasks like subtyping, grading, and staging, achieving state-of-the-art results on multiple slide-level benchmarks.
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.