提升皮肤病变检测的公平性，尤其改善深色肤色诊断准确率
LesionTABE: Equitable AI for Skin Lesion Detection
- 用对抗去偏与皮肤病基础模型嵌入结合提升公平性
- 在多个数据集上公平性指标提升超25%，且准确率更高
- 适合关注AI医疗公平性的研究者与临床开发者
偏差仍是阻碍AI在皮肤科临床应用的主要障碍，因诊断模型在深色皮肤上的表现较差。我们提出LesionTABE，一种以公平性为核心的设计框架，结合对抗去偏与皮肤病特异性基础模型嵌入。在涵盖恶性与炎症性病变的多个数据集上评估，相比ResNet-152基线，LesionTABE在公平性指标上提升超过25%，优于现有去偏方法，同时提升了整体诊断准确率。结果表明，基础模型去偏有望推动更公平的临床AI应用。
原文摘要 · Abstract (English)
Bias remains a major barrier to the clinical adoption of AI in dermatology, as diagnostic models underperform on darker skin tones. We present LesionTABE, a fairness-centric framework that couples adversarial debiasing with dermatology-specific foundation model embeddings. Evaluated across multiple datasets covering both malignant and inflammatory conditions, LesionTABE achieves over a 25\% improvement in fairness metrics compared to a ResNet-152 baseline, outperforming existing debiasing methods while simultaneously enhancing overall diagnostic accuracy. These results highlight the potential of foundation model debiasing as a step towards equitable clinical AI adoption.
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。