文献速递胸部技术与安全DR

放射科医生训练的AI模型识别不合格胸片

Radiologist-Trained AI Model for Identifying Suboptimal Chest-Radiographs.
PubMed 文献 · Acad Radiol · 2023-04-03

该回顾性多中心研究纳入3278张成人胸片,由胸部放射科医生标注不合格原因,训练并测试5个AI模型区分合格与不合格胸片;AI对各类不合格原因的分类AUC达0.87–0.94,有望前置部署于摄片设备以提示技师必要时重拍。

要点

  • AI可准确识别胸片不合格原因,AUC最高达0.94。
  • 低肺容积和患者旋转的识别敏感度分别为96%和92%。
  • 模型可前置部署于设备端,辅助技师决定是否重拍。

核心结论

  • 放射科医生训练的AI模型能准确分类合格与不合格胸片,可前置部署于摄片设备以辅助技师必要时重拍。

研究设计与样本

  • IRB批准的回顾性多中心研究,纳入5个中心3278张成人胸片(平均年龄55±20岁),由胸部放射科医生审核不合格原因。
  • 训练集2202张(合格807张,不合格1395张),测试集1076张(不合格729张,合格347张),训练并测试5个AI模型。
  • 以AUC分析模型正确分类合格与不合格胸片的能力。

诊断标准与关键数值

  • 缺失解剖结构:敏感度78%、特异度95%、准确率91%、AUC 0.87(95%CI 0.82–0.92)。
  • 胸部解剖被遮挡:敏感度91%、特异度97%、准确率95%、AUC 0.94(95%CI 0.90–0.97)。
  • 曝光不足:敏感度90%、特异度93%、准确率92%、AUC 0.91(95%CI 0.88–0.95)。
  • 低肺容积:敏感度96%、特异度92%、准确率93%、AUC 0.94(95%CI 0.92–0.96)。
  • 患者旋转:敏感度92%、特异度96%、准确率95%、AUC 0.94(95%CI 0.91–0.98)。

临床应用与阅片要点

  • AI模型可用于胸片质控前端,辅助技师在发现不合格征象时决定是否重拍,减少关键征象漏读。
  • 阅片时可关注AI提示的不合格原因(如缺失解剖、遮挡、曝光不足、低肺容积、旋转),结合临床判断图像质量。

局限性

  • 回顾性研究设计,样本来自5个中心但未报告外部验证。
  • 训练与测试集划分基于同一批数据来源,可能存在选择偏倚。

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

RATIONALE AND OBJECTIVES: Suboptimal chest radiographs (CXR) can limit interpretation of critical findings. Radiologist-trained AI models were evaluated for differentiating suboptimal(sCXR) and optimal(oCXR) chest radiographs.

MATERIALS AND METHODS: Our IRB-approved study included 3278 CXRs from adult patients (mean age 55 ± 20 years) identified from a retrospective search of CXR in radiology reports from 5 sites. A chest radiologist reviewed all CXRs for the cause of suboptimality. The de-identified CXRs were uploaded into an AI server application for training and testing 5 AI models. The training set consisted of 2202 CXRs (n = 807 oCXR; n = 1395 sCXR) while 1076 CXRs (n = 729 sCXR; n = 347 oCXR) were used for testing. Data were analyzed with the Area under the curve (AUC) for the model's ability to classify oCXR and sCXR correctly.

RESULTS: For the two-class classification into sCXR or oCXR from all sites, for CXR with missing anatomy, AI had sensitivity, specificity, accuracy, and AUC of 78%, 95%, 91%, 0.87(95% CI 0.82-0.92), respectively. AI identified obscured thoracic anatomy with 91% sensitivity, 97% specificity, 95% accuracy, and 0.94 AUC (95% CI 0.90-0.97). Inadequate exposure with 90% sensitivity, 93% specificity, 92% accuracy, and AUC of 0.91 (95% CI 0.88-0.95). The presence of low lung volume was identified with 96% sensitivity, 92% specificity, 93% accuracy, and 0.94 AUC (95% CI 0.92-0.96). The sensitivity, specificity, accuracy, and AUC of AI in identifying patient rotation were 92%, 96%, 95%, and 0.94 (95% CI 0.91-0.98), respectively.

CONCLUSION: The radiologist-trained AI models can accurately classify optimal and suboptimal CXRs. Such AI models at the front end of radiographic equipment can enable radiographers to repeat sCXRs when necessary.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Dasegowda, Bizzo, Gupta, et al. Radiologist-Trained AI Model for Identifying Suboptimal Chest-Radiographs. Acad Radiol. 2023. PMID: 37019698. doi:10.1016/j.acra.2023.03.006

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。