Deep learning models have revolutionized medical imaging and diagnostics, yet their opaque nature poses challenges for clinical adoption and trust. Amongst approaches to improve model interpretability, concept-based explanations aim to provide concise and human understandable explanations of any arbitrary classifier. However, such methods usually require a large amount of manually collected data with concept annotation, which is often scarce in the medical domain. In this paper, we propose Conceptual Counterfactual Explanations for Chest X-ray (CoCoX) that leverage existing vision-language models (VLM) joint embedding space to explain black-box classifier outcomes without the need for annotated datasets. Specifically, we utilize textual concepts derived from chest radiography reports and a pre-trained chest radiography-based VLM to explain three common cardiothoracic pathologies. We demonstrate that the explanations generated by our method are semantically meaningful and faithful to underlying pathologies.

本文提出了利用已有的视觉-语言模型(Visual-Language Model, VLM)联合嵌入空间的概念对立解释来解释黑盒分类器结果的方法，无需注释的数据集。通过利用胸部放射学报告中的文本概念和基于胸部放射学的预训练VLM，解释了三种常见的心胸病理，证明了我们的方法生成的解释在语义上是有意义的，忠实于潜在的病理。

利用文本概念解释胸部X光病理模型