Google 将基础模型推向结核病筛查一线
原标题：Bringing foundational models to the front lines of TB screening
AI 摘要
Google Research 在 IDWeek 2026 上分享了其将基础模型用于结核病筛查的进展：从 2019 年发表胸片深度学习基准、2021 年经 Stop TB Partnership 评估进入全球领先算法行列，到 2024 年在 NEJM AI 发表多中心前瞻性验证。Google 与南非公司 Nexus AI 合作，将算法转化为获认证的临床诊断工具，目前在南非、塞拉利昂、科特迪瓦等六国约 40 家医疗机构部署，已评估超 2.5 万张胸片，并将周转时间从数周缩短至 45 秒以内。Google 还通过 HAI-DEF 开源胸片嵌入和 MedSigLIP 视觉语言模型，让各地开发者能用少量本地数据微调，推动筛查规模化。
正文节选
October 23, 2026 Preeti Singh, Lead, Technical Program Manager, and Shravya Shetty, Distinguished Software Engineer, Google Research Tuberculosis remains one of the world's deadliest infectious diseases, claiming an estimated 1.23 million lives each year. Despite decades of global investment, too many cases go undetected in the communities that carry the highest burden. Over the past five years, we’ve worked to change that trajectory, moving from early research benchmarks toward open foundation