[论文解读] Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma

Tirtha Chanda, Katja Hauser+33 more|arXiv (Cornell University)|Mar 17, 2023

Explainable Artificial Intelligence (XAI)被引用 5

一句话总结

本研究开发了一种类皮肤科医生的可解释人工智能（XAI）系统，可为黑色素瘤诊断生成局部化、领域特定的文本和视觉解释，与传统AI相比，显著提升了皮肤科医生对AI的信任度和诊断信心。该系统提高了与临床医生推理的一致性，且在诊断准确率上表现出数值上的提升，但差异不显著。

ABSTRACT

Although artificial intelligence (AI) systems have been shown to improve the accuracy of initial melanoma diagnosis, the lack of transparency in how these systems identify melanoma poses severe obstacles to user acceptance. Explainable artificial intelligence (XAI) methods can help to increase transparency, but most XAI methods are unable to produce precisely located domain-specific explanations, making the explanations difficult to interpret. Moreover, the impact of XAI methods on dermatologists has not yet been evaluated. Extending on two existing classifiers, we developed an XAI system that produces text and region based explanations that are easily interpretable by dermatologists alongside its differential diagnoses of melanomas and nevi. To evaluate this system, we conducted a three-part reader study to assess its impact on clinicians' diagnostic accuracy, confidence, and trust in the XAI-support. We showed that our XAI's explanations were highly aligned with clinicians' explanations and that both the clinicians' trust in the support system and their confidence in their diagnoses were significantly increased when using our XAI compared to using a conventional AI system. The clinicians' diagnostic accuracy was numerically, albeit not significantly, increased. This work demonstrates that clinicians are willing to adopt such an XAI system, motivating their future use in the clinic.

研究动机与目标

• 为解决基于人工智能的黑色素瘤诊断缺乏透明度的问题，该问题阻碍了临床应用。
• 开发一种XAI系统，提供与皮肤科医生临床推理一致的可解释、局部化解释。
• 评估此类XAI对临床医生诊断准确率、信心及对AI辅助支持信任度的影响。
• 弥合人工智能可解释性与皮肤科真实世界临床决策之间的差距。

提出的方法

• 扩展了两种现有的深度学习分类器，以生成基于区域的注意力图和自然语言解释。
• 设计解释内容以反映与黑色素细胞病变诊断相关的皮肤科特征（例如，不对称性、边界不规则性、颜色异质性）。
• 集成双输出机制，同时输出鉴别诊断（黑色素瘤 vs. 良性痣）和关键特征的可解释性文本描述。
• 通过专家皮肤科医生的标注验证模型解释的临床相关性与一致性。
• 开展三阶段读者研究，评估皮肤科医生在使用XAI系统时的诊断表现、信心水平及信任度。

实验结果

研究问题

• RQ1 XAI系统能否生成与皮肤科医生在黑色素瘤诊断中的临床推理高度一致的解释？
• RQ2 提供类皮肤科医生的解释是否能提升临床医生对AI诊断辅助系统的信任？
• RQ3 与传统AI相比，XAI在多大程度上提升了皮肤科医生的诊断信心？
• RQ4 使用XAI是否能带来临床医生诊断准确率的可测量提升？

主要发现

• XAI系统的解释与皮肤科医生自身的解释高度一致，表明其具有强临床相关性。
• 与传统AI相比，皮肤科医生在使用XAI时对AI辅助系统表现出显著更高的信任度。
• 即使准确率提升未达统计显著性，临床医生在使用XAI系统时的诊断信心也显著提高。
• 使用XAI后，诊断准确率呈现数值上的提升，但研究队列中差异未达统计显著性。