用生成图像评估皮肤癌模型公平性，效果接近真实数据。
Towards Facilitated Fairness Assessment of AI-based Skin Lesion Classifiers Through GenAI-based Image Synthesis
- 用先进生成模型可控合成皮肤病变图像。
- 三种模型在真实与合成图像上真阳性率趋势一致。
- 适合关注AI公平性的研究者和医疗算法开发者。
深度学习与设备端推理的进展有望改变皮肤癌的常规筛查。然而，技术带来的潜在风险源于未预见且固有的偏见。主要障碍在于构建能准确反映性别、年龄、种族等关键人口统计特征的评估数据集。为此，我们训练了一个先进的生成模型，以可控方式生成合成数据，用于评估公开皮肤癌分类器的公平性。为验证合成图像能否作为公平性测试数据集，我们准备了真实图像数据集（MILK10K）作为基准，并对比了三种模型（DeepGuide、MelaNet、SkinLesionDensnet）在真实与生成图像上的真阳性率结果。结果显示，各模型在真实与生成图像上对不同属性数据集的分类倾向表现出相似模式。我们证实，高度逼真的合成图像可有效支持模型公平性验证。
原文摘要 · Abstract (English)
Recent advances in deep learning and on-device inference could transform routine screening for skin cancers. Along with the anticipated benefits of this technology, potential dangers arise from unforeseen and inherent biases. A significant obstacle is building evaluation datasets that accurately reflect key demographics, including sex, age, and race, as well as other underrepresented groups. To address this, we train a state-of-the-art generative model to generate synthetic data in a controllable manner to assess the fairness of publicly available skin cancer classifiers. To evaluate whether synthetic images can be used as a fairness testing dataset, we prepare a real-image dataset (MILK10K) as a benchmark and compare the True Positive Rate result of three models (DeepGuide, MelaNet, and SkinLesionDensnet). As a result, the classification tendencies observed in each model when tested on real and generated images showed similar patterns across different attribute data sets. We confirm that highly realistic synthetic images facilitate model fairness verification.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。