文献速递乳腺乳腺X线

对英国大型NHS乳腺筛查单位现场AI乳腺X线筛查阅片的回顾与反思

Review and reflections on live AI mammographic screen reading in a large UK NHS breast screening unit.
PubMed 文献 · Clin Radiol · 2025-03-15

英国一家筛查人口超过135,000的乳腺筛查单位参与服务评估项目,将商用AI平台作为「静默第三读者」实时运行,评估9,547例乳腺筛查X线片。AI未检出8例人类读者召回并确诊的癌症(占该期间检出癌症的8.79%),未额外检出癌症,作者认为AI性能低于人类读者且不够安全用于临床实践。

要点

  • AI作为静默第三读者未额外检出任何癌症。
  • 8例人类读者召回并确诊的癌症未被AI检出,占该期间检出癌症的8.79%。
  • 1,135例AI阳性但双读未召回的病例复核后仅1例被召回且后续评估未发现癌症。

核心结论

  • 在本单位,AI性能低于人类读者。
  • AI漏检了相当数量的癌症,使其不可靠且不安全用于临床实践。
  • AI目前准确性不足以纳入NHS乳腺筛查计划。

研究设计与样本

  • 服务评估项目,筛查人口超过135,000,共纳入9,547例乳腺筛查X线片。
  • 商用AI平台作为「静默第三读者」实时运行,不影响标准工作流程和患者照护。
  • 复核所有AI标记但标准双读未召回的病例(阳性不一致病例)及所有人类读者召回但AI未标记的病例(阴性不一致病例)。

诊断标准与关键数值

  • 阳性不一致病例1,135例复核后召回1例,该例在乳腺评估门诊进一步评估未发现癌症。
  • 阴性不一致病例139例复核后,8例人类读者召回并确诊的癌症(占该期间检出癌症的8.79%)未被AI检出。
  • 研究期间AI未额外检出癌症。

临床应用与阅片要点

  • 原文结论认为AI目前准确性不足以纳入NHS乳腺筛查计划,且不安全用于临床实践。

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)。

英文原文(摘要)· 点击展开

UNLABELLED: The Radiology team from a large Breast Screening Unit in the UK with a screening population of over 135,000 took part in a service evaluation project using artificial intelligence (AI) for reading breast screening mammograms.

AIM: To evaluate the clinical benefit AI may provide when implemented as a silent reader in a double reading breast screening programme and to evaluate feasibility and the operational impact of deploying AI into the breast screening programme. The service was one of 14 breast screening sites in the UK to take part in this project and we present our local experience with AI in breast screening.

MATERIALS AND METHODS: A commercially available AI platform was deployed and worked in real time as a 'silent third reader' so as not to impact standard workflows and patient care. All cases flagged by AI but not recalled by standard double reading (positive discordant cases) were reviewed along with all cases recalled by human readers but not flagged by AI (negative discordant cases).

RESULTS: 9,547 cases were included in the evaluation. 1,135 positive discordant cases were reviewed, and one woman was recalled from the reviews who was not found to have cancer on further assessment in the breast assessment clinic. 139 negative discordant cases were reviewed, and eight cancer cases (8.79% of total cancers detected in this period) recalled by human readers were not detected by AI. No additional cancers were detected by AI during the study.

CONCLUSION: Performance of AI was inferior to human readers in our unit. Having missed a significant number of cancers makes it unreliable and not safe to be used in clinical practice. AI is not currently of sufficient accuracy to be considered in the NHS Breast Screening Programme.

来源:Clin Radiol,查看原文。版权归原作者所有。

引用

  1. Puri S, Bagnall M, Erdelyi G, et al. Review and reflections on live AI mammographic screen reading in a large UK NHS breast screening unit. Clin Radiol. 2025. PMID: 40222163. doi:10.1016/j.crad.2025.106872

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。