SlideCheck: Guiding Self-Supervised Pretraining of Pathology Foundation Models via Dataset Distributions
Quick Answer
SlideCheck is a novel tool that enhances the pretraining of pathology foundation models by providing explicit abnormality and malignancy scores for patch selection.
Quick Take
It utilizes a dual-head MLP to improve data quality and control over pretraining datasets, demonstrating that curated subsets can achieve near full-data performance, thus optimizing the efficiency of self-supervised ViT pretraining.
Key Points
- SlideCheck uses a dual-head MLP to model abnormal morphology and malignancy evidence.
- It provides scores for organizing and auditing pathology pretraining data effectively.
- Curated subsets defined by SlideCheck can achieve performance close to full datasets.
- The tool influences downstream behavior in self-supervised ViT pretraining.
- It transforms large patch pools into controllable and reusable pretraining datasets.
Paper Resources
Source Excerpt
arXiv:2606. 07590v1 Announce Type: new Abstract: Pathology foundation models are pretrained on large streams of WSI-derived patches, while supervision during data construction is often slide-level, sparse, or heterogeneous. This mismatch makes it difficult to understand and control which biological patterns enter the pretraining data. We propose SlideCheck, a lightweight pretraining data guidance tool built on frozen pathology foundation model patch features.
Rather than serving as a standalone patch diagnostic model, SlideCheck provides explicit abnormality and malignancy scores for organizing, filtering, and auditing pathology pretraining data. …
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.