发表机构
University Medical Center Hamburg-Eppendorf; University of Hamburg; German Center for Child and Adolescent Health（汉堡埃彭多夫大学医学中心; 汉堡大学; 德国儿童与青少年健康中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对病理视觉基础模型嵌入的领域偏移问题，提出EXPOSE框架，利用稀疏自编码器解耦并抑制领域特定特征，在前列腺癌数据集实验中提升了跨域性能与嵌入鲁棒性。
AI 中文摘要
视觉基础模型（VFMs）广泛应用于计算病理学，但对因染色、组织制备及扫描仪硬件差异导致的领域偏移仍较为敏感。其关键局限在于，VFM嵌入会将生物信息与领域特定信息纠缠，阻碍跨域泛化。我们提出可解释跨域稀疏嵌入探测框架EXPOSE，该框架采用稀疏自编码器（SAEs）作为可解释瓶颈，以识别并抑制VFM嵌入中的领域特定成分。我们训练VFM特征的稀疏表示，使用线性分类器识别领域特定潜在维度，并在下游复发预测前对这些特征进行掩码处理，无需重新训练骨干模型。在包含多个采集领域的大型前列腺癌数据集上的实验表明，SAE特征同时捕获领域特定和任务特定信息，且在潜在空间中部分解耦。移除领域特定特征可提升跨域性能，并通过领域鲁棒性指数（DoRI）衡量的嵌入鲁棒性。代码可在该https网址获取。
英文摘要
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 .
