MiMICRI: Towards Domain-centered Counterfactual Explanations of Cardiovascular Image Classification Models

arXiv:2404.16174v1 Announce Type: cross
Abstract: 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 …

abstract analysis and analysis artificial artificial intelligence arxiv classification counterfactual cs.cv cs.hc cs.lg datasets development domain image imaging impacts intelligence medical medical imaging type