让病理模型看得懂、说得清，用多染色图像提升诊断可解释性。
BioX-CPath: Biologically-driven Explainable Diagnostics for Multistain IHC Computational Pathology
- 引入染色感知注意力池化模块，融合空间与语义特征生成生物合理嵌入。
- 在类风湿关节炎和干燥综合征数据集上达到当前最优分类性能。
- 通过注意力分数等指标实现病理机制对齐，适合临床可信诊断场景。
计算病理学中，构建具有生物学可解释性的模型仍是关键挑战，尤其针对多染色免疫组化（IHC）分析。本文提出BioX-CPath，一种用于全切片图像（WSI）分类的可解释图神经网络架构，利用多染色图像中的空间与语义特征。其核心是新型染色感知注意力池化（SAAP）模块，生成具有生物学意义的染色感知患者嵌入。该方法在类风湿关节炎和干燥综合征多染色数据集上均达到当前最优性能。除分类效果外，BioX-CPath通过染色注意力分数、熵值及染色交互得分提供可解释性洞察，能衡量模型与已知病理机制的一致性。这种生物学一致性与强分类能力结合，使其特别适用于对可解释性要求高的临床应用场景。源代码与文档见：https://github.com/AmayaGS/BioX-CPath。
原文摘要 · Abstract (English)
The development of biologically interpretable and explainable models remains a key challenge in computational pathology, particularly for multistain immunohistochemistry (IHC) analysis. We present BioX-CPath, an explainable graph neural network architecture for whole slide image (WSI) classification that leverages both spatial and semantic features across multiple stains. At its core, BioX-CPath introduces a novel Stain-Aware Attention Pooling (SAAP) module that generates biologically meaningful, stain-aware patient embeddings. Our approach achieves state-of-the-art performance on both Rheumatoid Arthritis and Sjogren's Disease multistain datasets. Beyond performance metrics, BioX-CPath provides interpretable insights through stain attention scores, entropy measures, and stain interaction scores, that permit measuring model alignment with known pathological mechanisms. This biological grounding, combined with strong classification performance, makes BioX-CPath particularly suitable for clinical applications where interpretability is key. Source code and documentation can be found at: https://github.com/AmayaGS/BioX-CPath.
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。