数字病理学中注意力图可解释性的表征
Characterizing the Interpretability of Attention Maps in Digital Pathology
AI总结：
本文提出通过人工混杂因素与专用指标评估ABMIL注意力图的框架，发现其能关注相关区域，但鲁棒性受混杂因素类型和数量影响。
摘要：
解释机器学习模型的决策对于医疗等高风险应用至关重要。在数字病理学中，大型全切片图像（WSI）被分解为较小的图块，基于图块得到的特征由基于注意力的多示例学习（ABMIL）模型处理，以预测WSI级标签。这些网络生成特定于图块的注意力权重，可将其可视化为注意力图以实现可解释性。然而，目前缺乏针对这些图的标准化评估框架，这使人们质疑其可靠性以及检测可能误导模型的虚假相关性的能力。本文中，我们提出一个框架，通过创建人工模型混杂因素并使用专门的可解释性指标，评估注意力网络关注数字病理学中相关特征的能力。模型在具有与WSI标签相关的图块修改的数据上进行训练和评估，从而能够分析模型对人工混杂因素的敏感性，以及注意力图突出显示这些因素的准确性。混杂因素通过合成图块修改或基于图块特定图像特征的图块消融引入，后者用于评估更具临床相关性的场景。我们还分析了在图块和WSI两个层面改变混杂因素数量的影响。结果表明，ABMIL模型在我们的框架内按预期表现。尽管注意力图通常能够突出相关区域，但其鲁棒性会受到混杂因素类型和数量的影响。我们的多功能框架有望用于评估各种方法，并探索驱动模型预测的图像特征，从而助力生物标志物发现。
英文摘要：
Interpreting machine learning model decisions is crucial for high-risk applications like healthcare. In digital pathology, large whole slide images (WSIs) are decomposed into smaller tiles and tile-derived features are processed by attention-based multiple instance learning (ABMIL) models to predict WSI-level labels. These networks generate tile-specific attention weights, which can be visualized as attention maps for interpretability. However, a standardized evaluation framework for these maps is lacking, questioning their reliability and ability to detect spurious correlations that can mislead models. We herein propose a framework to assess the ability of attention networks to attend to relevant features in digital pathology by creating artificial model confounders and using dedicated interpretability metrics. Models are trained and evaluated on data with tile modifications correlated with WSI labels, enabling the analysis of model sensitivity to artificial confounders and the accuracy of attention maps in highlighting them. Confounders are introduced either through synthetic tile modifications or through tile ablations based on their specific image-based features, with the latter being used to assess more clinically relevant scenarios. We also analyze the impact of varying confounder quantities at both the tile and WSI levels. Our results show that ABMIL models perform as desired within our framework. While attention maps generally highlight relevant regions, their robustness is affected by the type and number of confounders. Our versatile framework has the potential to be used in the evaluation of various methods and the exploration of image-based features driving model predictions, which could aid in biomarker discovery.
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。
