Guo Grace, Deng Lifu, Tandon Animesh, Endert Alex, Kwon Bum Chul
Georgia Institute of Technology Atlanta, Georgia, USA.
Cleveland Clinic Cleveland, Ohio, USA.
FACCT 24 (2024). 2024 Jun;2024:1861-1874. doi: 10.1145/3630106.3659011. Epub 2024 Jun 5.
The recent prevalence of publicly accessible, large medical imaging datasets has led to a proliferation of artificial intelligence (AI) models for cardiovascular image classification and analysis. At the same time, the potentially significant impacts of these models have motivated the development of a range of explainable AI (XAI) methods that aim to explain model predictions given certain image inputs. However, many of these methods are not developed or evaluated with domain experts, and explanations are not contextualized in terms of medical expertise or domain knowledge. In this paper, we propose a novel framework and python library, MiMICRI, that provides domain-centered counterfactual explanations of cardiovascular image classification models. MiMICRI helps users interactively select and replace segments of medical images that correspond to morphological structures. From the counterfactuals generated, users can then assess the influence of each segment on model predictions, and validate the model against known medical facts. We evaluate this library with two medical experts. Our evaluation demonstrates that a domain-centered XAI approach can enhance the interpretability of model explanations, and help experts reason about models in terms of relevant domain knowledge. However, concerns were also surfaced about the clinical plausibility of the counterfactuals generated. We conclude with a discussion on the generalizability and trustworthiness of the MiMICRI framework, as well as the implications of our findings on the development of domain-centered XAI methods for model interpretability in healthcare contexts.
最近，可公开获取的大型医学影像数据集的普及，促使用于心血管图像分类和分析的人工智能（AI）模型大量涌现。与此同时，这些模型可能产生的重大影响，推动了一系列可解释人工智能（XAI）方法的发展，这些方法旨在解释给定某些图像输入时的模型预测。然而，这些方法中的许多并未与领域专家共同开发或评估，并且解释也未根据医学专业知识或领域知识进行情境化处理。在本文中，我们提出了一个新颖的框架和Python库MiMICRI，它为心血管图像分类模型提供以领域为中心的反事实解释。MiMICRI帮助用户交互式地选择和替换与形态结构相对应的医学图像片段。然后，从生成的反事实中，用户可以评估每个片段对模型预测的影响，并根据已知的医学事实验证模型。我们与两位医学专家对这个库进行了评估。我们的评估表明，以领域为中心的XAI方法可以增强模型解释的可解释性，并帮助专家根据相关领域知识对模型进行推理。然而，对于生成的反事实的临床合理性也出现了一些担忧。我们最后讨论了MiMICRI框架的可推广性和可信度，以及我们的发现对医疗保健背景下以领域为中心的XAI方法用于模型可解释性发展的影响。
