临床皮肤病学的多模态视觉基础模型
Diagnosing and treating skin diseases require advanced visual skills across domains and the ability to synthesize information from multiple imaging modalities.…
要点
- PanDerm在28项皮肤科基准任务上均达当前最佳性能,部分任务仅用10%标注数据即优于现有模型。
- 在纵向分析的早期黑色素瘤检测中,PanDerm较临床医生高10.2%。
- PanDerm使临床医生皮肤癌诊断准确率提高11%,使非皮肤科医疗提供者对128种皮肤病的鉴别诊断提高16.5%。
核心结论
- PanDerm在评估的所有任务上均达当前最佳性能,显示其在不同临床场景中改善患者照护的潜力,并可作为其他医学专科开发多模态基础模型的范例,可能加速人工智能支持在医疗中的整合。
研究设计与样本
- 在28项多样化的基准上评估PanDerm,包括皮肤癌筛查、风险分层、常见与罕见皮肤病的鉴别诊断、病灶分割、纵向监测以及转移预测和预后。
- 开展三项阅读者研究以评估PanDerm的潜在临床效用。
主要发现
- PanDerm在所有评估任务上均达当前最佳性能,使用仅10%标注数据时往往优于现有模型。
- 在通过纵向分析进行的早期黑色素瘤检测中,PanDerm较临床医生高10.2%。
- PanDerm使临床医生在皮肤镜图像上的皮肤癌诊断准确率提高11%。
- PanDerm使非皮肤科医疗提供者在临床照片上对128种皮肤病的鉴别诊断提高16.5%。
关键数值与推荐
- PanDerm在早期黑色素瘤检测中较临床医生高10.2%(纵向分析)。
- PanDerm使临床医生皮肤癌诊断准确率提高11%(皮肤镜图像)。
- PanDerm使非皮肤科医疗提供者鉴别诊断提高16.5%(临床照片,128种皮肤病)。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
Diagnosing and treating skin diseases require advanced visual skills across domains and the ability to synthesize information from multiple imaging modalities. While current deep learning models excel at specific tasks such as skin cancer diagnosis from dermoscopic images, they struggle to meet the complex, multimodal requirements of clinical practice. Here we introduce PanDerm, a multimodal dermatology foundation model pretrained through self-supervised learning on over 2 million real-world skin disease images from 11 clinical institutions across 4 imaging modalities. We evaluated PanDerm on 28 diverse benchmarks, including skin cancer screening, risk stratification, differential diagnosis of common and rare skin conditions, lesion segmentation, longitudinal monitoring, and metastasis prediction and prognosis. PanDerm achieved state-of-the-art performance across all evaluated tasks, often outperforming existing models when using only 10% of labeled data. We conducted three reader studies to assess PanDerm's potential clinical utility. PanDerm outperformed clinicians by 10.2% in early-stage melanoma detection through longitudinal analysis, improved clinicians' skin cancer diagnostic accuracy by 11% on dermoscopy images and enhanced nondermatologist healthcare providers' differential diagnosis by 16.5% across 128 skin conditions on clinical photographs. These results show PanDerm's potential to improve patient care across diverse clinical scenarios and serve as a model for developing multimodal foundation models in other medical specialties, potentially accelerating the integration of artificial intelligence support in healthcare.
引用
- Yan S, Yu Z, Primiero C, et al. A multimodal vision foundation model for clinical dermatology. Nat Med. 2025. PMID: 40481209. doi:10.1038/s41591-025-03747-y
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。