一种深度卷积神经网络集成用于常规PET/CT上肺结节与偶发发现的复合识别
纳入189例序贯PET/CT患者,用卷积神经网络集成(AI-Rad Companion)评估低剂量CT序列。肺结节总体准确率0.847,敏感度0.915、特异度0.781;冠状动脉钙化、主动脉扩张、椎体高度丢失的准确率分别为0.979、0.966、0.840。结论认为该网络集成能准确评估肺结节数量及冠状动脉钙化、主动脉扩张,对椎体高度丢失高度特异但不敏感。
要点
- 肺结节总体敏感度0.915、特异度0.781,准确率0.847。
- 冠状动脉钙化敏感度0.989、特异度0.969,准确率0.979。
- 主动脉扩张敏感度0.806、特异度1,准确率0.966。
核心结论
- 神经网络集成能准确评估PET/CT低剂量CT序列上的肺结节数量及冠状动脉钙化、主动脉扩张的存在。
- 该网络对椎体高度丢失诊断高度特异但不敏感。
- 使用该AI集成可帮助放射科和核医学医师发现可能被忽略的CT表现。
研究设计与样本
- 研究类型为诊断准确性研究,纳入189例序贯接受PET/CT的患者。
- 使用卷积神经网络集成(AI-Rad Companion,Siemens Healthineers,Erlangen,德国)评估低剂量CT序列。
- 主要结局为肺结节检测,计算准确率、同一性和评分者内信度。
- 次要结局为冠状动脉钙化、主动脉扩张、椎体高度丢失的二分类检测,计算准确率和诊断性能。
诊断标准与关键数值
- 肺结节检测:总体每结节准确率0.847,总体敏感度0.915,总体特异度0.781。
- 冠状动脉钙化:每患者准确率0.979,敏感度0.989,特异度0.969。
- 主动脉扩张:每患者准确率0.966,敏感度0.806,特异度1。
- 椎体高度丢失:每患者准确率0.840。
临床应用与阅片要点
- 原文结论认为AI集成可帮助放射科和核医学医师发现可能被忽略的CT表现。
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
AIM: To evaluate primary and secondary pathologies of interest using an artificial intelligence (AI) platform, AI-Rad Companion, on low-dose computed tomography (CT) series from integrated positron-emission tomography (PET)/CT to detect CT findings that might be overlooked.
MATERIALS AND METHODS: One hundred and eighty-nine sequential patients who had undergone PET/CT were included. Images were evaluated using an ensemble of convolutional neural networks (AI-Rad Companion, Siemens Healthineers, Erlangen, Germany). The primary outcome was detection of pulmonary nodules for which the accuracy, identity, and intra-rater reliability was calculated. For secondary outcomes (binary detection of coronary artery calcium, aortic ectasia, vertebral height loss), accuracy and diagnostic performance were calculated.
RESULTS: The overall per-nodule accuracy for detection of lung nodules was 0.847. The overall sensitivity and specificity for detection of lung nodules was 0.915 and 0.781. The overall per-patient accuracy for AI detection of coronary artery calcium, aortic ectasia, and vertebral height loss was 0.979, 0.966, and 0.840, respectively. The sensitivity and specificity for coronary artery calcium was 0.989 and 0.969. The sensitivity and specificity for aortic ectasia was 0.806 and 1.
CONCLUSION: The neural network ensemble accurately assessed the number of pulmonary nodules and presence of coronary artery calcium and aortic ectasia on low-dose CT series of PET/CT. The neural network was highly specific for the diagnosis of vertebral height loss, but not sensitive. The use of the AI ensemble can help radiologists and nuclear medicine physicians to catch CT findings that might be overlooked.
引用
- Chamberlin, Smith, Schoepf, et al. A deep convolutional neural network ensemble for composite identification of pulmonary nodules and incidental findings on routine PET/CT. Clin Radiol. 2023. PMID: 36863883. doi:10.1016/j.crad.2023.01.014
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。