重新审视数字病理学中视觉基础模型的自动数据整理
Revisiting Automatic Data Curation for Vision Foundation Models in Digital Pathology
AI总结：
本文针对数字病理学视觉基础模型，提出在组织块层面利用层次聚类树进行无监督自动数据整理，以平衡预训练数据，并设计批次采样策略缓解规模与平衡的权衡，提升下游任务性能。
摘要：
视觉基础模型（FMs）正在加速数字病理学算法的发展，并推动生物医学研究的变革。这些模型以自监督方式学习，从真实世界患者样本的全切片图像（WSIs）中提取的高度异质性组织块中表征组织学特征。这些基础模型的性能受到预训练数据规模、多样性和平衡性的显著影响。然而，数据选择主要依赖专家在WSI层面的知识，侧重于疾病分类和组织类型等因素，而在很大程度上忽视了组织块层面可用的细粒度细节。在本文中，我们研究了在组织块层面进行无监督自动数据整理的潜力，考虑了3.5亿个组织块。具体而言，我们将层次聚类树应用于预提取的组织块嵌入，从而能够在预训练基础模型的嵌入空间中均匀采样平衡数据集。我们进一步发现这些数据集在规模和平衡性之间存在权衡，可能损害基础模型学习到的表示质量，并提出了定制的批次采样策略以减轻这种影响。我们通过在多样化的临床相关下游任务上的性能提升证明了我们方法的有效性。
英文摘要：
Vision foundation models (FMs) are accelerating the development of digital pathology algorithms and transforming biomedical research. These models learn, in a self-supervised manner, to represent histological features in highly heterogeneous tiles extracted from whole-slide images (WSIs) of real-world patient samples. The performance of these FMs is significantly influenced by the size, diversity, and balance of the pre-training data. However, data selection has been primarily guided by expert knowledge at the WSI level, focusing on factors such as disease classification and tissue types, while largely overlooking the granular details available at the tile level. In this paper, we investigate the potential of unsupervised automatic data curation at the tile-level, taking into account 350 million tiles. Specifically, we apply hierarchical clustering trees to pre-extracted tile embeddings, allowing us to sample balanced datasets uniformly across the embedding space of the pretrained FM. We further identify these datasets are subject to a trade-off between size and balance, potentially compromising the quality of representations learned by FMs, and propose tailored batch sampling strategies to mitigate this effect. We demonstrate the effectiveness of our method through improved performance on a diverse range of clinically relevant downstream tasks.
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。
