文献速递胸部技术与安全DR

基于人工智能的正常胸片识别:多中心健康筛查队列中的模拟研究

Artificial Intelligence-Based Identification of Normal Chest Radiographs: A Simulation Study in a Multicenter Health Screening Cohort.
PubMed 文献 · Korean J Radiol · 2022-01-01

本研究利用韩国三家健康筛查中心5887例成人胸片,评估商用AI(Lunit INSIGHT CXR3)模拟剔除正常胸片的可行性;AI分诊剔除42.9%正常胸片,误删可见和清晰可见异常胸片分别为3.5%和1.8%;在480例子样本中,AI分诊剔除41.6%正常胸片且未漏诊可见异常,并提高部分读片者特异度而不降低敏感度。

要点

  • AI分诊可剔除42.9%正常胸片,误删可见异常3.5%、清晰可见异常1.8%。
  • 480例子样本中AI分诊剔除41.6%正常胸片,未漏诊可见异常。
  • AI分诊提高部分读片者特异度,敏感度未降低。

核心结论

  • 本研究提示使用AI按定制阈值分拣和剔除正常胸片具有可行性,可提高效率并减少放射科医生工作量。

研究设计与样本

  • 回顾性模拟研究,纳入韩国三家健康筛查中心5887例成人胸片(平均年龄55.4±11.8岁,男性4329例),使用商用AI(Lunit INSIGHT CXR3,版本3.5.8.8),由三名委员会认证胸部放射科医生判读参考标准。

诊断标准与关键数值

  • 可见异常定义为至少一名读片者判为异常,清晰可见异常定义为至少两名读片者判为异常;AI分诊剔除42.9%(2354/5482)正常胸片、误删3.5%(14/405)可见异常和1.8%(4/227)清晰可见异常胸片;480例子样本中AI分诊剔除41.6%(188/452)正常胸片且未漏诊可见异常。

临床应用与阅片要点

  • 作者认为,在健康筛查环境中使用AI按定制阈值分拣和剔除正常胸片,可能提高效率并减少放射科医生工作量。

局限性

  • 本研究为回顾性模拟研究。
  • 原文指出需进一步研究以验证该方法的可行性。

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

OBJECTIVE: This study aimed to investigate the feasibility of using artificial intelligence (AI) to identify normal chest radiography (CXR) from the worklist of radiologists in a health-screening environment.

MATERIALS AND METHODS: This retrospective simulation study was conducted using the CXRs of 5887 adults (mean age ± standard deviation, 55.4 ± 11.8 years; male, 4329) from three health screening centers in South Korea using a commercial AI (Lunit INSIGHT CXR3, version 3.5.8.8). Three board-certified thoracic radiologists reviewed CXR images for referable thoracic abnormalities and grouped the images into those with visible referable abnormalities (identified as abnormal by at least one reader) and those with clearly visible referable abnormalities (identified as abnormal by at least two readers). With AI-based simulated exclusion of normal CXR images, the percentages of normal images sorted and abnormal images erroneously removed were analyzed. Additionally, in a random subsample of 480 patients, the ability to identify visible referable abnormalities was compared among AI-unassisted reading (i.e., all images read by human readers without AI), AI-assisted reading (i.e., all images read by human readers with AI assistance as concurrent readers), and reading with AI triage (i.e., human reading of only those rendered abnormal by AI).

RESULTS: Of 5887 CXR images, 405 (6.9%) and 227 (3.9%) contained visible and clearly visible abnormalities, respectively. With AI-based triage, 42.9% (2354/5482) of normal CXR images were removed at the cost of erroneous removal of 3.5% (14/405) and 1.8% (4/227) of CXR images with visible and clearly visible abnormalities, respectively. In the diagnostic performance study, AI triage removed 41.6% (188/452) of normal images from the worklist without missing visible abnormalities and increased the specificity for some readers without decreasing sensitivity.

CONCLUSION: This study suggests the feasibility of sorting and removing normal CXRs using AI with a tailored cut-off to increase efficiency and reduce the workload of radiologists.

来源:Korean J Radiol,查看原文。版权归原作者所有。

引用

  1. Yoo H, Kim EY, Kim H, et al. Artificial Intelligence-Based Identification of Normal Chest Radiographs: A Simulation Study in a Multicenter Health Screening Cohort. Korean J Radiol. 2022. PMID: 36175002. doi:10.3348/kjr.2022.0189

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。