是否存在与COVID-19相关的独特影像生物标志物?
本研究回顾性收集151例COVID-19和497例社区获得性肺炎(CAP)患者的胸部CT,用3D卷积神经网络建立分类器并由两名放射科医师视觉判读,区分COVID-19与CAP。表现最佳的模型AUC为0.70(99%CI 0.56-0.85),可在仅2%的COVID-19患者中识别出8-50%的CAP患者。作者认为人工或自动CT判读区分COVID-19与CAP的能力为中低度,但自动影像分析有助识别相当一部分非COVID-19病例。
要点
- 人和AI模型区分COVID-19与CAP的总体诊断能力仅中等偏低。
- 最佳模型AUC为0.70(99%CI 0.56-0.85)。
- 该模型可在仅2%的COVID-19患者中识别出8-50%的CAP患者。
核心结论
- 专业或自动的CT判读区分COVID-19与CAP的能力为中低度。
- 自动影像分析有望通过准确识别相当一部分非COVID-19病例来辅助针对性决策。
- 可能不存在能可靠区分所有COVID-19与CAP的独特影像特征或模式,但可能存在识别相当一部分非COVID-19病例的影像标志物。
研究设计与样本
- 回顾性收集胸部CT:COVID-19组为151例RT-PCR阳性患者的498次检查,CAP组为497例不同患者的497次检查。
- COVID-19与CAP影像集均划分为训练、验证和测试三组。
- 基于三维卷积神经网络(3D CNNs)开发多个分类器以区分COVID-19与CAP,并请两名有经验的放射科医师对测试集进行视觉判读。
- 采用受试者工作特征(ROC)分析评估计算机算法与放射科医师的分类性能,必要时使用非参数方法并进行多重性校正。
诊断标准与关键数值
- 在所考虑的模型中,一个模型显示非平凡但中等的总体诊断能力,AUC为0.70(99%CI 0.56-0.85)。
- 该模型在仅2%的COVID-19患者中识别出8-50%的CAP患者。
临床应用与阅片要点
- 原文结论指出专业或自动的CT判读区分COVID-19与CAP的能力为中低度。
- 原文结论指出自动影像分析有望通过准确识别相当一部分非COVID-19病例来辅助针对性决策。
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
OBJECTIVE: To define the uniqueness of chest CT infiltrative features associated with COVID-19 image characteristics as potential diagnostic biomarkers.
METHODS: We retrospectively collected chest CT exams including n = 498 on 151 unique patients RT-PCR positive for COVID-19 and n = 497 unique patients with community-acquired pneumonia (CAP). Both COVID-19 and CAP image sets were partitioned into three groups for training, validation, and testing respectively. In an attempt to discriminate COVID-19 from CAP, we developed several classifiers based on three-dimensional (3D) convolutional neural networks (CNNs). We also asked two experienced radiologists to visually interpret the testing set and discriminate COVID-19 from CAP. The classification performance of the computer algorithms and the radiologists was assessed using the receiver operating characteristic (ROC) analysis, and the nonparametric approaches with multiplicity adjustments when necessary.
RESULTS: One of the considered models showed non-trivial, but moderate diagnostic ability overall (AUC of 0.70 with 99% CI 0.56-0.85). This model allowed for the identification of 8-50% of CAP patients with only 2% of COVID-19 patients.
CONCLUSIONS: Professional or automated interpretation of CT exams has a moderately low ability to distinguish between COVID-19 and CAP cases. However, the automated image analysis is promising for targeted decision-making due to being able to accurately identify a sizable subsect of non-COVID-19 cases.
KEY POINTS: • Both human experts and artificial intelligent models were used to classify the CT scans. • ROC analysis and the nonparametric approaches were used to analyze the performance of the radiologists and computer algorithms. • Unique image features or patterns may not exist for reliably distinguishing all COVID-19 from CAP; however, there may be imaging markers that can identify a sizable subset of non-COVID-19 cases.
引用
- Pu J, Leader J, Bandos A, et al. Any unique image biomarkers associated with COVID-19? Eur Radiol. 2020. PMID: 32462445. doi:10.1007/s00330-020-06956-w
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。