提出弱监督预训练框架，提升病理切片多实例学习的特征表示能力。
SimMIL: A Universal Weakly Supervised Pre-Training Framework for Multi-Instance Learning in Whole Slide Pathology Images
- 通过传播标签实现弱监督预训练，强化实例级特征学习。
- 在多个病理数据集上优于ImageNet和自监督预训练方案。
- 适用于特定病理模型微调及多数据集联合预训练，兼容性强。
基于多实例学习（MIL）的方法已被广泛应用于全切片病理图像（WSI）。现有MIL方法侧重特征聚合器设计，却忽视实例级表征学习。它们假设预训练特征提取器可直接使用或微调，但实际情况常不成立。本文提出一种弱监督预训练框架，通过将弱级别的袋标签传播至对应实例，实现监督学习。为提升MIL的有效特征学习，进一步探索了强数据增强、非线性预测头和鲁棒损失函数等关键组件。在多个大规模WSI数据集上的实验表明，该方法在不同下游任务中均优于其他预训练策略（如ImageNet预训练和自监督学习）。此外，通过在病理专用模型微调及合并多个数据集上进行预训练，验证了该方案的兼容性与可扩展性。据我们所知，这是首个专注于MIL表征学习的工作。
原文摘要 · Abstract (English)
Various multi-instance learning (MIL) based approaches have been developed and successfully applied to whole-slide pathological images (WSI). Existing MIL methods emphasize the importance of feature aggregators, but largely neglect the instance-level representation learning. They assume that the availability of a pre-trained feature extractor can be directly utilized or fine-tuned, which is not always the case. This paper proposes to pre-train feature extractor for MIL via a weakly-supervised scheme, i.e., propagating the weak bag-level labels to the corresponding instances for supervised learning. To learn effective features for MIL, we further delve into several key components, including strong data augmentation, a non-linear prediction head and the robust loss function. We conduct experiments on common large-scale WSI datasets and find it achieves better performance than other pre-training schemes (e.g., ImageNet pre-training and self-supervised learning) in different downstream tasks. We further show the compatibility and scalability of the proposed scheme by deploying it in fine-tuning the pathological-specific models and pre-training on merged multiple datasets. To our knowledge, this is the first work focusing on the representation learning for MIL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。