非参数分布匹配用于自监督全切片图像压缩
Nonparametric Distribution Matching for Self-Supervised Whole-Slide Image Condensation
浏览论文内容
中文总结 AI 辅助
针对全切片图像高分辨率带来的计算挑战，提出将WSI压缩重构为分布匹配问题，开发非参数先验的NICER框架，在五个数据集上平均准确率提升7.44%，优于现有方法。
中文摘要 AI 辅助
组织学全切片图像（WSIs）是计算病理学的核心，但由于其极高的分辨率（通常每张切片达数GB），带来了严重的计算挑战。为了实现可扩展的学习，现有方法采用自监督数据压缩来降低计算成本，但通常依赖启发式原型学习，并未明确保留对下游任务有学习相关性的特征分布。为此，我们将WSI压缩重新表述为一个在固定表征视角下的分布匹配问题，并开发了NICER，一种基于具有切片自适应能力的非参数先验的可处理近似框架。在五个组织病理学数据集上的实验，以及来自委员会认证病理学家的临床评估表明，NICER始终优于现有方法，平均准确率提升7.44%，同时提供了更好的效率-准确性权衡，突显了原则性、分布感知的压缩对可扩展组织学表征学习的益处。源代码可在该https URL中获取。
英文摘要
Histological whole-slide images (WSIs) are central to computational pathology but pose severe computational challenges due to their extremely high resolution, often spanning several gigabytes per slide. To enable scalable learning, existing methods apply self-supervised data condensation to reduce computational cost, but typically rely on heuristic prototype learning and do not explicitly preserve learning-relevant feature distributions for downstream tasks. In response, we introduce a principled reformulation of WSI condensation as a distribution-matching problem under a fixed representational lens, and develop NICER, a tractable approximation framework based on a nonparametric prior with slide-adaptive capacity. Experiments on five histopathology datasets, together with clinical evaluation from a board-certified pathologist, show that NICER consistently outperforms prior methods, achieving an average accuracy improvement of 7.44% while offering improved efficiency-accuracy trade-offs, highlighting the benefits of principled, distribution-aware condensation for scalable histological representation learning. Source codes are available in https://github.com/nmduonggg/NICER.
发表机构
- University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
- Washington State University（华盛顿州立大学）
- Hanoi Medical University（河内医科大学）
- VinUniversity（文森大学）
- Hanoi University of Science and Technology（河内科技大学）
机构由 AI 辅助整理，请以论文原文为准。
