指南与共识肺结节与肺癌

AI测量肺结节体积倍增时间在UKLS筛查随访中的验证

AI performance for nodule volume doubling time in the follow-up of the UKLS lung cancer screening study compared to expert consensus and histological validation
RSS 订阅 · 指南共识 · 肺结节与肺癌筛查 · 2025-11-30

本研究基于UKLS肺癌筛查试验的710名参与者共939次随访低剂量CT,验证AI自动测量结节体积倍增时间(VDT)的表现。以欧洲专家小组为标准,AI在3个月随访的阴性误分类率最低(1/11,9.1%),阳性误分类率从3个月的7.8%降至12个月的0.9%;对9例筛检肺癌,AI在最早3个月随访即识别出专家 panel 判阳的全部4例癌症的VDT≤400天,而人类读者漏诊或延迟转诊1-3例。

要点

  • AI自动测量VDT在早期识别快速生长肺癌方面优于人类读者。
  • AI 3个月阴性误分类率9.1%,低于人类读者的18.2-63.6%。
  • AI阳性误分类率从3个月7.8%降至12个月0.9%。

核心结论

  • 自动AI系统在筛查随访中VDT评估表现良好,在组织学确诊癌症的早期快速生长识别上优于人类读者,支持其提升风险分层和促进更早肺癌检出的潜力。

研究设计与样本

  • 验证性研究纳入UKLS试验710名参与者的939次随访低剂量CT扫描(361次3个月和578次12个月),由AI与人类读者独立评估,以欧洲专家小组为参考标准、组织学结果为金标准。

主要发现

  • 以专家小组为标准,AI 3个月阴性误分类率为1/11(9.1%),人类读者范围为18.2-63.6%。
  • AI阳性误分类率3个月为7.8%(28/361),12个月降至0.9%(5/578)。
  • 对9例筛检肺癌的组织学结果,AI在最早3个月随访即识别出专家 panel 判阳的全部4例癌症的VDT≤400天,人类读者漏诊或延迟转诊其中1-3例。
  • AI还识别出专家 panel 判阴的5例癌症中3例的VDT≤400天,主要因其体积低于阈值(<100mm³)。

关键数值与推荐

  • 阳性发现需转诊定义为随访时最大结节实性成分≥100 mm³且VDT≤400天。

临床怎么用

  • AI自动VDT测量可用于肺癌筛查随访中的结节生长评估,辅助早期识别快速生长结节并优化风险分层。

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

Eur J Cancer. 2026 Jan;232:116137. doi: 10.1016/j.ejca.2025.116137. Epub 2025 Nov 22. ABSTRACT AIM: To validate an artificial intelligence (AI) software for automated assessment of nodule growth by volume doubling time measurement (VDT) on protocol-mandated follow-up low-dose CT (LDCT) scans from the UK lung cancer screening (UKLS) trial. METHODS: This validation study included 710 UKLS participants with 939 LDCT follow-up scans (361 3-month and 578 12-month). Follow-up scans were assessed independently by both AI and human readers. A positive finding warranting referral was defined as the largest nodule with a solid component ≥ 100 mm 3 showing VDT ≤ 400 days at follow-up. Performance was benchmarked against the European expert panel (reference standard) and then the histological outcomes (gold standard). RESULTS: Against the expert panel, AI achieved the lowest 3-month negative misclassification (NM) rate (1/11, 9.1 %), versus human readers (range: 18.2-63.6 %). AI's positive misclassification (PM) rate was initially 7.8 % (28/361) at 3 months but decreased to 0.9 % (5/578) at 12 months. Against histological outcomes of 9 screen-detected lung cancers, AI identified VDT ≤ 400 days in all 4 cancers also deemed positive by the expert panel at the earliest 3-month follow-up, while human readers missed or delayed referrals in 1-3 of these. AI also identified VDT ≤ 400 days in 3 of 5 cancers that the panel classified as negative, primarily due to their sub-threshold volume (<100mm³). CONCLUSIONS: The automated AI system showed strong VDT assessment performance in follow-up screening, outperforming human readers in the early identification of rapid growth in histologically-confirmed cancers, thus supporting its potential to enhance risk stratification and facilitate earlier lung cancer detection. PMID: 41319449 | DOI: 10.1016/j.ejca.2025.116137

来源:指南共识 · 肺结节与肺癌筛查,查看原文。版权归原作者所有。

引用

  1. 指南共识 · 肺结节与肺癌筛查:AI performance for nodule volume doubling time in the follow-up of the UKLS lung cancer screening study compared to expert consensus and histological validation

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。