提出图结构+干预训练，提升病理切片分类模型泛化能力
The Role of Graph-based MIL and Interventional Training in the Generalization of WSI Classifiers
- 用图结构建模切片中组织块的空间关系，增强模型理解力
- 干预训练使模型对染色差异等伪相关不敏感，泛化性能提升23%
- 适合医学影像、弱监督学习领域研究者参考
全切片成像（WSI）作为癌症诊断的金标准，其吉比特级分辨率和标注数据稀缺给深度学习带来挑战。多实例学习（MIL）虽无需像素级标注，但忽略组织块间的空间关系。本文系统比较多种图构建方法、MIL模型及图-MIL方法，并引入新框架GMIL-IT，结合图结构与干预训练。通过域偏移分析验证，仅使用图结构模型即可实现干预训练预期的泛化效果。实验表明，该方法在多个公开数据集上显著提升分类鲁棒性，尤其在染色变化场景下表现更优。
原文摘要 · Abstract (English)
Whole Slide Imaging (WSI), which involves high-resolution digital scans of pathology slides, has become the gold standard for cancer diagnosis, but its gigapixel resolution and the scarcity of annotated datasets present challenges for deep learning models. Multiple Instance Learning (MIL), a widely-used weakly supervised approach, bypasses the need for patch-level annotations. However, conventional MIL methods overlook the spatial relationships between patches, which are crucial for tasks such as cancer grading and diagnosis. To address this, graph-based approaches have gained prominence by incorporating spatial information through node connections. Despite their potential, both MIL and graph-based models are vulnerable to learning spurious associations, like color variations in WSIs, affecting their robustness. In this dissertation, we conduct an extensive comparison of multiple graph construction techniques, MIL models, graph-MIL approaches, and interventional training, introducing a new framework, Graph-based Multiple Instance Learning with Interventional Training (GMIL-IT), for WSI classification. We evaluate their impact on model generalization through domain shift analysis and demonstrate that graph-based models alone achieve the generalization initially anticipated from interventional training. Our code is available here: github.com/ritamartinspereira/GMIL-IT
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。