文献速递胸部技术与安全DR

人工智能用于床旁胸片临床解读

Artificial Intelligence for Clinical Interpretation of Bedside Chest Radiographs.
PubMed 文献 · Radiology · 2022-12-06

非放射科医生借助模型初步判读后报告一致性由κ=0.79提升至0.87(P<.001)。

要点

  • 床旁胸片结构化半定量报告可训练AI识别五种常见异常。
  • AI与专家共识一致性κ=0.86,优于单个放射科医生。
  • 非放射科医生借助AI初步判读可提升报告一致性。

核心结论

  • 基于结构化半定量报告训练的神经网络对床旁胸片五种异常判读与专家共识一致性高,可辅助非放射科医生提高解读水平。

研究设计与样本

  • 内部测试集100张来自100例患者,由6名放射科专家小组独立评估作为参考标准,比较6名专家、2名ICU非放射科医生及神经网络与参考标准的一致性。

诊断标准与关键数值

  • 神经网络识别心影增大、肺淤血、胸腔积液、肺内片状影和肺不张,采用加权Cohen κ衡量与专家小组多数投票的一致性。
  • 神经网络与专家小组多数投票一致性κ=0.86,高于单个放射科医生与专家小组多数投票一致性(κ=0.81至≤0.84)。
  • 非放射科医生在AI初步判读辅助下报告一致性κ=0.87,未辅助时κ=0.79(P<.001)。

临床应用与阅片要点

  • 在ICU床旁胸片判读中,AI可提供心影增大、肺淤血、胸腔积液、肺内片状影和肺不张的初步提示,辅助非放射科医生提高报告一致性。
  • 放射科医生可参考AI结果,但需注意模型基于结构化半定量报告训练,其输出应与临床及影像整体表现结合判断。

局限性

  • 研究为回顾性单中心设计,外部泛化性需进一步验证。
  • 参考标准基于专家小组多数投票,并非病理或临床最终诊断。
  • 模型仅评估五种预设异常,未涵盖其他床旁胸片表现。

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

Background Supine chest radiography for bedridden patients in intensive care units (ICUs) is one of the most frequently ordered imaging studies worldwide. Purpose To evaluate the diagnostic performance of a neural network-based model that is trained on structured semiquantitative radiologic reports of bedside chest radiographs. Materials and Methods For this retrospective single-center study, children and adults in the ICU of a university hospital who had been imaged using bedside chest radiography from January 2009 to December 2020 were reported by using a structured and itemized template. Ninety-eight radiologists rated the radiographs semiquantitatively for the severity of disease patterns. These data were used to train a neural network to identify cardiomegaly, pulmonary congestion, pleural effusion, pulmonary opacities, and atelectasis. A held-out internal test set (100 radiographs from 100 patients) that was assessed independently by an expert panel of six radiologists provided the ground truth. Individual assessments by each of these six radiologists, by two nonradiologist physicians in the ICU, and by the neural network were compared with the ground truth. Separately, the nonradiologist physicians assessed the images without and with preliminary readings provided by the neural network. The weighted Cohen κ coefficient was used to measure agreement between the readers and the ground truth. Results A total of 193 566 radiographs in 45 016 patients (mean age, 66 years ± 16 [SD]; 61% men) were included and divided into training (n = 122 294; 64%), validation (n = 31 243; 16%), and test (n = 40 029; 20%) sets. The neural network exhibited higher agreement with a majority vote of the expert panel (κ = 0.86) than each individual radiologist compared with the majority vote of the expert panel (κ = 0.81 to ≤0.84). When the neural network provided preliminary readings, the reports of the nonradiologist physicians improved considerably (aided vs unaided, κ = 0.87 vs 0.79, respectively; P < .001). Conclusion A neural network trained with structured semiquantitative bedside chest radiography reports allowed nonradiologist physicians improved interpretations compared with the consensus reading of expert radiologists. © RSNA, 2022 Supplemental material is available for this article. See also the editorial by Wielpütz in this issue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Khader, Han, Müller-Franzes, et al. Artificial Intelligence for Clinical Interpretation of Bedside Chest Radiographs. Radiology. 2022. PMID: 36472534. doi:10.1148/radiol.220510

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。