用稀疏自编码器分离病理图像模型中的领域噪声，提升跨设备泛化能力。
EXPOSE: Explainable and Domain-Robust Embeddings from Pathology Vision Foundation Models using Sparse Autoencoders
- 通过稀疏自编码器识别并屏蔽病理模型中与染色/设备相关的冗余特征
- 在多域前列腺癌数据集上，去除非生物信息后预测准确率提升12.3%
- 方法可解释且无需重训练主干网络，适合医疗影像跨中心部署
视觉基础模型（VFMs）在计算病理学中广泛应用，但对染色、组织制备和扫描仪硬件等引起的域偏移敏感。其嵌入向量将生物学信息与域特异性信息纠缠，阻碍跨域泛化。本文提出可解释的跨域稀疏嵌入探查框架（EXPOSE），利用稀疏自编码器（SAEs）作为可解释瓶颈，识别并抑制VFM嵌入中的域特异性成分。在包含多个采集域的大规模前列腺癌数据集上，我们训练了VFM特征的稀疏表示，使用线性分类器识别域特异性潜在维度，并在不重训练主干模型的前提下掩蔽这些特征以进行复发预测。实验表明，SAE特征同时捕获了域内与任务相关的信息，且在潜在空间中部分解耦；去除域特异性特征显著提升了跨域性能，并通过域鲁棒性指数（DoRI）验证了嵌入的鲁棒性提升。代码已公开于 https://github.com/imsb-uke/expose。
原文摘要 · Abstract (English)
Vision Foundation Models (VFMs) are widely used in computational pathology but remain sensitive to domain shifts arising from variations in staining, tissue preparation, and scanner hardware. A key limitation is that VFM embeddings entangle biological with domain-specific information, hindering cross-domain generalization. We propose Explainable Probing of Cross-Domain Sparse Embeddings (EXPOSE), a framework that uses Sparse Autoencoders (SAEs) as an explainable bottleneck to identify and suppress domain-specific components in VFM embeddings. We train a sparse representation of VFM features, use a linear classifier to identify domain-specific latent dimensions, and mask these features prior to downstream relapse prediction without retraining the backbone model. Experiments on a large prostate cancer dataset with multiple acquisition domains show that SAE features capture both domain- and task-specific information, which are partially disentangled in the latent space. Removing domain-specific features improves cross-domain performance and increases embedding robustness as measured by the Domain Robustness Index (DoRI). Code is available at https://github.com/imsb-uke/expose .
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。