文献速递乳腺乳腺X线

人工智能算法用于筛查乳腺X线摄影自动判读的独立外部验证:一项系统综述

Independent External Validation of Artificial Intelligence Algorithms for Automated Interpretation of Screening Mammography: A Systematic Review.
PubMed 文献 · J Am Coll Radiol · 2022-01-20

该系统综述检索5个数据库至2020年12月10日,纳入13项使用真实世界筛查检查对AI乳腺X线摄影算法进行外部验证的研究,共148361例患者。多数研究评估商业AI算法,比较显示AI单独或联合放射科医师判读的AUC有改善,但研究均为回顾性且存在偏倚风险。

要点

  • 5项比较AI单独与放射科医师的研究中,3项显示AI提高AUC,改善范围0.02-0.13。
  • 5项比较放射科医师联合AI与单独放射科医师的研究均显示联合判读提高AUC,改善范围0.028-0.115。
  • 69%的研究(n=9)在患者选择和参考标准方面存在偏倚风险或适用性担忧。

核心结论

  • 外部验证显示AI筛查乳腺X线摄影技术可能带来小幅诊断准确度提升,但研究为回顾性且存在偏倚风险与适用性担忧。

研究设计与样本

  • 系统综述,检索Embase、PubMed、IEEE Explore、Engineer Village和arXiv共5个数据库至2020年12月10日,纳入13项使用真实世界筛查检查外部验证AI乳腺X线摄影癌症检测算法的研究,共148361例患者,质量评估采用QUADAS-2工具。

关键影像表现/征象

  • 研究类型包括回顾性阅片研究46%(n=6)、回顾性模拟研究38%(n=5)及两者兼有15%(n=2)。
  • 77%的研究(n=10)评估商业可用的AI算法。
  • 仅2项研究通过区域癌症登记链接获得真实癌症结局。

诊断标准与关键数值

  • 主要结局为诊断准确度,以受试者工作特征曲线下面积(AUC)定义。
  • 5项比较AI单独与放射科医师的研究中,60%(n=3)显示AI提高准确度,AUC改善范围0.02-0.13。
  • 5项比较放射科医师联合AI与单独放射科医师的研究均显示联合判读提高准确度,AUC改善范围0.028-0.115。
  • 69%的研究(n=9)在患者选择方面存在偏倚风险或适用性担忧,69%的研究(n=9)在参考标准方面存在偏倚风险或适用性担忧。

临床应用与阅片要点

  • 作者结论指出外部验证显示AI筛查乳腺X线摄影技术可能带来小幅诊断准确度提升,但研究为回顾性且存在偏倚风险与适用性担忧。

局限性

  • 外部验证研究为回顾性性质。
  • 研究存在偏倚风险与适用性担忧:69%(n=9)的患者选择和69%(n=9)的参考标准存在偏倚风险或适用性担忧。
  • 仅2项研究通过区域癌症登记链接获得真实癌症结局。

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

PURPOSE: The aim of this study was to describe the current state of science regarding independent external validation of artificial intelligence (AI) technologies for screening mammography.

METHODS: A systematic review was performed across five databases (Embase, PubMed, IEEE Explore, Engineer Village, and arXiv) through December 10, 2020. Studies that used screening examinations from real-world settings to externally validate AI algorithms for mammographic cancer detection were included. The main outcome was diagnostic accuracy, defined by area under the receiver operating characteristic curve (AUC). Performance was also compared between radiologists and either stand-alone AI or combined radiologist and AI interpretation. Study quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 tool.

RESULTS: After data extraction, 13 studies met the inclusion criteria (148,361 total patients). Most studies (77% [n = 10]) evaluated commercially available AI algorithms. Studies included retrospective reader studies (46% [n = 6]), retrospective simulation studies (38% [n = 5]), or both (15% [n = 2]). Across 5 studies comparing stand-alone AI with radiologists, 60% (n = 3) demonstrated improved accuracy with AI (AUC improvement range, 0.02-0.13). All 5 studies comparing combined radiologist and AI interpretation with radiologists alone demonstrated improved accuracy with AI (AUC improvement range, 0.028-0.115). Most studies had risk for bias or applicability concerns for patient selection (69% [n = 9]) and the reference standard (69% [n = 9]). Only two studies obtained ground-truth cancer outcomes through regional cancer registry linkage.

CONCLUSIONS: To date, external validation efforts for AI screening mammographic technologies suggest small potential diagnostic accuracy improvements but have been retrospective in nature and suffer from risk for bias and applicability concerns.

来源:J Am Coll Radiol,查看原文。版权归原作者所有。

引用

  1. Anderson, Marinovich, Houssami, et al. Independent External Validation of Artificial Intelligence Algorithms for Automated Interpretation of Screening Mammography: A Systematic Review. J Am Coll Radiol. 2022. PMID: 35065909. doi:10.1016/j.jacr.2021.11.008

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。