用注意力机制+大模型，从整张病理片预测肺癌主要生长模式。
Attention-based multiple instance learning for predominant growth pattern prediction in lung adenocarcinoma wsi using foundation models
- 基于注意力的多实例学习，整合预训练病理模型提取特征。
- 微调后模型在整片级别预测准确率κ=0.699，优于传统方法。
- 减少标注依赖，适合临床病理辅助诊断场景。
肺腺癌（LUAD）分级依赖于准确识别生长模式，这些模式是预后指标并影响治疗决策。现有深度学习方法通常依赖病灶级分类或分割，需大量标注。本研究提出一种基于注意力的多实例学习（ABMIL）框架，在整张切片层面预测主要LUAD生长模式，以降低标注负担。该方法利用预训练病理基础模型作为病灶编码器，可冻结或在标注病灶上微调，通过注意力机制聚合特征。实验表明，微调后的编码器性能更优，其中Prov-GigaPath在ABMIL下达到最高一致性（κ=0.699）。相比简单的病灶聚合基线，ABMIL通过滑片级监督和空间注意力实现更稳健的预测。未来工作将扩展至估计完整生长模式分布，并在外部队列中验证性能。
原文摘要 · Abstract (English)
Lung adenocarcinoma (LUAD) grading depends on accurately identifying growth patterns, which are indicators of prognosis and can influence treatment decisions. Common deep learning approaches to determine the predominant pattern rely on patch-level classification or segmentation, requiring extensive annotations. This study proposes an attention-based multiple instance learning (ABMIL) framework to predict the predominant LUAD growth pattern at the whole slide level to reduce annotation burden. Our approach integrates pretrained pathology foundation models as patch encoders, used either frozen or fine-tuned on annotated patches, to extract discriminative features that are aggregated through attention mechanisms. Experiments show that fine-tuned encoders improve performance, with Prov-GigaPath achieving the highest agreement (\k{appa} = 0.699) under ABMIL. Compared to simple patch-aggregation baselines, ABMIL yields more robust predictions by leveraging slide-level supervision and spatial attention. Future work will extend this framework to estimate the full distribution of growth patterns and validate performance on external cohorts.
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。