CAMEO：一种基于类激活映射的公平覆盖框架，用于公平且稳健的深度学习皮肤状况诊断
CAMEO: A Class-Activation-Mapped Equitable Overlay Framework for Fair and Robust Deep Learning-based Skin Condition Diagnosis
- Department of Electrical and Computer Engineering, University of New Brunswick, Fredericton, NB, Canada（加拿大新不伦瑞克省弗雷德里克顿市新不伦瑞克大学电气与计算机工程系）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出CAMEO框架，利用可解释AI的稳定解释分离病变与背景并替换为合成皮肤，在保持准确率的同时将背景驱动错误减少近四倍，提升皮肤病变分类的稳健性与公平性。
AI中文摘要：
针对皮肤镜皮肤病变的深度学习分类器通常能达到较高的分布内准确率，但会悄悄依赖虚假的背景线索（如肤色、设备渐晕和嵌入的标尺），而非病变形态本身。这损害了模型在不同肤色上的稳健性和公平性。本研究探讨了可解释人工智能（XAI）——通常仅用于审计已完成的模型——能否被重新用作一种主动的训练信号，在不牺牲诊断准确率的前提下纠正这种捷径学习。我们提出了CAMEO（类激活映射公平覆盖）框架，通过选择稳定的模型解释并将其用于将病变与背景分离，从而改进皮肤病变分类。该框架随后用逼真的合成皮肤替换背景，同时保持病变不变。在HAM10000和深色皮肤ISIC图像上，CAMEO保持了准确率，同时将背景驱动的错误减少了近四倍。它还使模型在背景变化时的注意力更加一致。多项测试的结果表明，减少对背景信息的依赖可提高稳健性，而基于菲茨帕特里克肤色分型的背景提供了一种逼真且可解释的方法。结果表明，XAI引导的数据增强可以使皮肤镜分类器在准确率无损失的情况下，在可测量程度上变得更加稳健和公平。这些结果还阐明，起作用的机制是具体机制本身而非特定的色调调色板，并且XAI在此处的持久贡献在于经过稳定性筛选、无需标注的病变定位，而非稳健性数值本身。
英文摘要：
Deep learning classifiers for dermoscopic skin lesions often reach high in-distribution accuracy while quietly relying on spurious background cues such as skin tone, device vignetting, and embedded rulers, rather than on lesion morphology. This undermines robustness and fairness across skin tones. This work asks whether Explainable AI (XAI), typically used only to audit a finished model, can instead be repurposed as an active training signal that corrects this shortcut without sacrificing diagnostic accuracy. We introduce CAMEO (Class Activation Mapped Equitable Overlay), a framework that improves skin-lesion classification by selecting stable model explanations and using them to separate lesions from their backgrounds. It then replaces the background with realistic synthetic skin while keeping the lesion unchanged. On HAM10000 and dark-skin ISIC images, CAMEO maintained accuracy while reducing background-driven errors by nearly four times. It also made the model's attention more consistent when backgrounds changed. Results across multiple tests show that reducing reliance on background information improves robustness, with Fitzpatrick-based backgrounds providing a realistic and interpretable approach. Results show that XAI-guided augmentation can make dermoscopic classifiers measurably more robust and fair at no cost to accuracy. They also clarify that it is the mechanism and not the specific tone palette that matters, and that the lasting contribution of XAI here lies in stability-screened, annotation-free lesion localisation rather than in the robustness number itself.
