在病理视觉-语言模型中检测数据偏移下的性能退化
Detecting Performance Degradation under Data Shift in Pathology Vision-Language Model
AI总结：
本研究提出DomainSAT工具，通过输入数据偏移检测与输出置信度指标结合，提升病理VLM在数据偏移下的性能退化检测可靠性。
摘要：
视觉-语言模型在医学图像分析和疾病诊断中展现了强大的潜力。然而，部署后，当输入数据分布从开发期间观察到的分布发生变化时，其性能可能会下降。检测此类性能退化对于临床可靠性至关重要，但仍然是挑战，因为大型预训练VLMs在没有标注数据的情况下运行。在本研究中，我们调查了在最先进的病理VLM中数据偏移下的性能退化检测。我们检查了输入级数据偏移和输出级预测行为，以了解它们在监控模型可靠性中的各自作用。为了促进对输入数据偏移的系统分析，我们开发了DomainSAT，一个轻量级工具包，具有图形界面，集成了代表性的偏移检测算法，并启用了直观的数据偏移探索。我们的分析显示，尽管输入数据偏移检测在识别分布变化和提供早期诊断信号方面是有效的，但它并不总是与实际的性能退化相对应。受这一观察的启发，我们进一步研究了基于输出的监控，并引入了一个无标签、基于置信度的退化指标，直接捕捉模型预测置信度的变化。我们发现，该指标与性能退化之间有密切的关系，并且作为输入偏移检测的有效补充。在大规模病理数据集上进行肿瘤分类实验表明，结合输入数据偏移检测和输出置信度指标能够更可靠地检测和解释VLM在数据偏移下的性能退化。这些发现提供了一个实用且互补的框架，用于监控数字病理学中基础模型的可靠性。
英文摘要：
Vision-Language Models have demonstrated strong potential in medical image analysis and disease diagnosis. However, after deployment, their performance may deteriorate when the input data distribution shifts from that observed during development. Detecting such performance degradation is essential for clinical reliability, yet remains challenging for large pre-trained VLMs operating without labeled data. In this study, we investigate performance degradation detection under data shift in a state-of-the-art pathology VLM. We examine both input-level data shift and output-level prediction behavior to understand their respective roles in monitoring model reliability. To facilitate systematic analysis of input data shift, we develop DomainSAT, a lightweight toolbox with a graphical interface that integrates representative shift detection algorithms and enables intuitive exploration of data shift. Our analysis shows that while input data shift detection is effective at identifying distributional changes and providing early diagnostic signals, it does not always correspond to actual performance degradation. Motivated by this observation, we further study output-based monitoring and introduce a label-free, confidence-based degradation indicator that directly captures changes in model prediction confidence. We find that this indicator exhibits a close relationship with performance degradation and serves as an effective complement to input shift detection. Experiments on a large-scale pathology dataset for tumor classification demonstrate that combining input data shift detection and output confidence-based indicators enables more reliable detection and interpretation of performance degradation in VLMs under data shift. These findings provide a practical and complementary framework for monitoring the reliability of foundation models in digital pathology.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
