重新审视全切片图像分类中多实例学习的预训练特征提取器选择
Rethinking Pre-Trained Feature Extractor Selection in Multiple Instance Learning for Whole Slide Image Classification
AI总结：
本文系统评估了多实例学习中预训练特征提取器在预训练数据集、骨干模型和预训练方法三个维度对全切片图像分类的影响，揭示了自监督方法、Transformer深层骨干及大规模多样化数据集的关键作用。
摘要：
多实例学习（MIL）已成为千兆像素级全切片图像（WSI）分类的首选方法，无需像素块级别的标注。当前的MIL研究主要依赖基于嵌入的方法，即使用预训练特征提取器提取图像块特征，并将其聚合以进行切片级预测。尽管特征提取起着关键作用，但关于如何选择最优特征提取器以最大化WSI性能的指导仍然有限。本研究通过从三个维度系统评估MIL特征提取器来填补这一空白：预训练数据集、骨干模型和预训练方法。在两个公开WSI数据集（TCGA-NSCLC和Camelyon16）上，使用四种最先进的（SOTA）MIL模型进行了大量实验。我们的研究结果表明：1）选择稳健的自监督学习（SSL）方法对性能的影响大于仅依赖域内预训练数据集；2）优先选择基于Transformer且架构更深的骨干网络，而非基于CNN的模型；3）使用更大、更多样化的预训练数据集可显著提升分类结果。我们希望这些见解能为优化WSI分类提供实用指导，并解释当前SOTA病理学基础模型性能优势背后的原因。此外，这项工作可能为开发更有效的病理学基础模型提供参考。我们的代码已在 https://github.com/bryanwong17/MIL-Feature-Extractor-Selection 公开。
英文摘要：
Multiple instance learning (MIL) has become a preferred method for gigapixel whole slide image (WSI) classification without requiring patch-level annotations. Current MIL research primarily relies on embedding-based approaches, which extract patch features using a pre-trained feature extractor and aggregate them for slide-level prediction. Despite the critical role of feature extraction, there is limited guidance on selecting optimal feature extractors to maximize WSI performance. This study addresses this gap by systematically evaluating MIL feature extractors across three dimensions: pre-training dataset, backbone model, and pre-training method. Extensive experiments were conducted on two public WSI datasets (TCGA-NSCLC and Camelyon16) using four state-of-the-art (SOTA) MIL models. Our findings reveal that: 1) selecting a robust self-supervised learning (SSL) method has a greater impact on performance than relying solely on an in-domain pre-training dataset; 2) prioritizing Transformer-based backbones with deeper architectures over CNN-based models; and 3) using larger, more diverse pre-training datasets significantly enhances classification outcomes. We hope that these insights can provide practical guidance for optimizing WSI classification and explain the reasons behind the performance advantages of the current SOTA pathology foundation models. Furthermore, this work may inform the development of more effective pathology foundation models. Our code is publicly available at https://github.com/bryanwong17/MIL-Feature-Extractor-Selection
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。
