研究人员开发了cgDDI，一个旨在生成多样化皮肤病学图像以改进恶性肿瘤分类的框架。这种混合方法可以合成逼真的健康皮肤，将罕见的病变映射到新的肤色上，并允许在最少训练数据的情况下高效生成。该框架支持自动分割掩码，并在Diverse Dermatology Images (DDI)和Fitzpatrick17k (F17k)数据集上进行了验证，取得了最先进的性能和领先的公平性指标。 AI
影响 通过解决代表性不足人群的数据稀缺性问题，增强了AI驱动的皮肤病学诊断的公平性和效率。
排序理由 该集群包含一篇详细介绍新框架和方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
Accurate dermatological diagnosis naturally necessitates equitable performance across diverse populations, yet a systematic lack of expertly annotated images, especially for underrepresented skin tones and rare diseases, impedes progress toward measurably fair methods. We introdu…
arXiv:2607.12987v1 Announce Type: new Abstract: Accurate dermatological diagnosis naturally necessitates equitable performance across diverse populations, yet a systematic lack of expertly annotated images, especially for underrepresented skin tones and rare diseases, impedes pro…
Accurate dermatological diagnosis naturally necessitates equitable performance across diverse populations, yet a systematic lack of expertly annotated images, especially for underrepresented skin tones and rare diseases, impedes progress toward measurably fair methods. We introdu…