重新审视皮肤病灶分类中的肤色公平性
Revisiting Skin Tone Fairness in Dermatological Lesion Classification
AI总结：
本文比较 ISIC18 上四种基于 ITA 的肤色估计方法，发现既有研究结论高度不一致且数据集多样性不足，并呼吁改进稳健估计与带标注多样化数据。
摘要：
由于皮肤病在不同肤色上的表现存在差异，因此解决基于皮肤科图像的病灶分类中的公平性问题至关重要。然而，公共数据集缺少肤色标签，这阻碍了构建公平分类器。迄今为止，在独立研究中进行公平性分析之前，这类肤色标签一直使用 Individual Typology Angle（ITA，个体类型角）来估计。简而言之，ITA 根据从皮肤图像中提取的像素计算一个角度，同时考虑明度和黄蓝色调。随后，这些角度被划分为不同肤色，并用于分析皮肤癌分类中的公平性。在本研究中，我们在 ISIC18 数据集上回顾并比较了四种基于 ITA 的肤色分类方法；ISIC18 是文献中用于评估皮肤癌分类公平性的常用基准。我们的分析揭示了既往已发表研究之间存在高度不一致，表明基于 ITA 的肤色估计方法存在风险。此外，我们调查了这些方法之间产生如此巨大差异的原因，并发现 ISIC18 数据集缺乏多样性，限制了其作为公平性分析测试平台的用途。最后，我们建议进一步研究稳健的 ITA 估计，以及获取带肤色标注的多样化数据集，以促进对皮肤科人工智能工具进行具有结论性的公平性评估。我们的代码可在 https://github.com/tkalbl/RevisitingSkinToneFairness 获取。
英文摘要：
Addressing fairness in lesion classification from dermatological images is crucial due to variations in how skin diseases manifest across skin tones. However, the absence of skin tone labels in public datasets hinders building a fair classifier. To date, such skin tone labels have been estimated prior to fairness analysis in independent studies using the Individual Typology Angle (ITA). Briefly, ITA calculates an angle based on pixels extracted from skin images taking into account the lightness and yellow-blue tints. These angles are then categorised into skin tones that are subsequently used to analyse fairness in skin cancer classification. In this work, we review and compare four ITA-based approaches of skin tone classification on the ISIC18 dataset, a common benchmark for assessing skin cancer classification fairness in the literature. Our analyses reveal a high disagreement among previously published studies demonstrating the risks of ITA-based skin tone estimation methods. Moreover, we investigate the causes of such large discrepancy among these approaches and find that the lack of diversity in the ISIC18 dataset limits its use as a testbed for fairness analysis. Finally, we recommend further research on robust ITA estimation and diverse dataset acquisition with skin tone annotation to facilitate conclusive fairness assessments of artificial intelligence tools in dermatology. Our code is available at https://github.com/tkalbl/RevisitingSkinToneFairness.
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。
