让病理模型看清组织全局结构并聚焦关键区域，提升诊断准确性与可解释性。
The Next Layer: Augmenting Foundation Models with Structure-Preserving and Attention-Guided Learning for Local Patches to Global Context Awareness in Computational Pathology
- 通过空间编码与注意力引导，融合局部微环境与全局组织结构信息。
- 在10,260张切片上分类准确率最高提升3%，7种癌症生存预测中6种表现最优。
- 生成与专家标注一致的热力图，适合临床辅助决策与生物标志物发现。
基础模型在计算病理学中已成为强大的特征提取工具，但通常缺乏利用组织全局空间结构及诊断相关区域间局部上下文关系的机制——这些是理解肿瘤微环境的关键。多实例学习（MIL）仍是基础模型后的关键步骤，需将切片级特征聚合为整体预测。我们提出EAGLE-Net，一种保持结构、由注意力引导的MIL架构，以增强预测性能与可解释性。EAGLE-Net整合了多尺度绝对空间编码以捕捉全局组织架构，基于top-K邻域感知的损失函数聚焦局部微环境，以及背景抑制损失以减少误报。我们在大规模泛癌数据集上评估，涵盖三种癌症分类任务（10,260张切片）和七种癌症生存预测任务（4,172张切片），采用三种不同组织学基础模型（REMEDIES、Uni-V1、Uni2-h）。在各项任务中，EAGLE-Net实现最高达3%的分类准确率提升，并在7种癌症中6种获得最优一致性指数，生成平滑且生物学合理的注意力图，与专家标注一致，突出侵袭前沿、坏死区和免疫浸润区域。该结果表明，EAGLE-Net是一种通用、可解释的框架，可有效补充基础模型，推动生物标志物发现、预后建模与临床决策支持。
原文摘要 · Abstract (English)
Foundation models have recently emerged as powerful feature extractors in computational pathology, yet they typically omit mechanisms for leveraging the global spatial structure of tissues and the local contextual relationships among diagnostically relevant regions - key elements for understanding the tumor microenvironment. Multiple instance learning (MIL) remains an essential next step following foundation model, designing a framework to aggregate patch-level features into slide-level predictions. We present EAGLE-Net, a structure-preserving, attention-guided MIL architecture designed to augment prediction and interpretability. EAGLE-Net integrates multi-scale absolute spatial encoding to capture global tissue architecture, a top-K neighborhood-aware loss to focus attention on local microenvironments, and background suppression loss to minimize false positives. We benchmarked EAGLE-Net on large pan-cancer datasets, including three cancer types for classification (10,260 slides) and seven cancer types for survival prediction (4,172 slides), using three distinct histology foundation backbones (REMEDIES, Uni-V1, Uni2-h). Across tasks, EAGLE-Net achieved up to 3% higher classification accuracy and the top concordance indices in 6 of 7 cancer types, producing smooth, biologically coherent attention maps that aligned with expert annotations and highlighted invasive fronts, necrosis, and immune infiltration. These results position EAGLE-Net as a generalizable, interpretable framework that complements foundation models, enabling improved biomarker discovery, prognostic modeling, and clinical decision support
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。