生成对抗网络用于胸部X线片上新型冠状病毒肺炎的自动定量
本研究利用50000例非COVID-19胸部CT生成虚拟X线片训练生成对抗网络(GAN),自动定量COVID-19肺炎范围。GAN驱动的肺炎范围与Brixia评分(r=0.611)及CT定量范围(r=0.640)相关,与CT范围的95%一致性界限为-27.1%至17.4%。在三组数据集中,GAN肺炎范围每增加1%对应不良结局的OR为1.05-1.18,AUC为0.614-0.842。
要点
- GAN可从胸部X线片自动生成肺炎范围(0%-100%),与Brixia评分和CT定量范围呈中度相关。
- GAN与CT肺炎范围的一致性界限较宽(-27.1%至17.4%),提示个体水平定量差异需谨慎解读。
- GAN肺炎范围与不良结局相关,每增加1%的OR为1.05-1.18,AUC为0.614-0.842。
核心结论
- 生成对抗网络可自动定量胸部X线片上的COVID-19肺炎范围,并识别不良结局患者。
研究设计与样本
- 回顾性研究,使用2015-2017年50000例连续非COVID-19胸部CT生成虚拟X线片训练两个GAN;在多个数据集(n=4707、54-375、243-1481)中验证相关性与预测效能。
诊断标准与关键数值
- GAN驱动的肺炎范围(肺炎面积/肺面积)以0%至100%表示;与Brixia X线严重度评分相关系数0.611,与CT定量肺炎范围相关系数0.640;GAN与CT范围的95%一致性界限为-27.1%至17.4%;三组数据集中每1%肺炎范围对不良结局的OR为1.05-1.18,AUC为0.614-0.842;结合人口学信息模型AUC为0.643-0.841,结合人口学与实验室信息模型AUC为0.688-0.877。
临床应用与阅片要点
- 原文未据此给出推荐。
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
PURPOSE: To develop a generative adversarial network (GAN) to quantify COVID-19 pneumonia on chest radiographs automatically.
MATERIALS AND METHODS: This retrospective study included 50,000 consecutive non-COVID-19 chest CT scans in 2015-2017 for training. Anteroposterior virtual chest, lung, and pneumonia radiographs were generated from whole, segmented lung, and pneumonia pixels from each CT scan. Two GANs were sequentially trained to generate lung images from radiographs and to generate pneumonia images from lung images. GAN-driven pneumonia extent (pneumonia area/lung area) was expressed from 0% to 100%. We examined the correlation of GAN-driven pneumonia extent with semi-quantitative Brixia X-ray severity score (one dataset, n = 4707) and quantitative CT-driven pneumonia extent (four datasets, n = 54-375), along with analyzing a measurement difference between the GAN and CT extents. Three datasets (n = 243-1481), where unfavorable outcomes (respiratory failure, intensive care unit admission, and death) occurred in 10%, 38%, and 78%, respectively, were used to examine the predictive power of GAN-driven pneumonia extent.
RESULTS: GAN-driven radiographic pneumonia was correlated with the severity score (0.611) and CT-driven extent (0.640). 95% limits of agreements between GAN and CT-driven extents were -27.1% to 17.4%. GAN-driven pneumonia extent provided odds ratios of 1.05-1.18 per percent for unfavorable outcomes in the three datasets, with areas under the receiver operating characteristic curve (AUCs) of 0.614-0.842. When combined with demographic information only and with both demographic and laboratory information, the prediction models yielded AUCs of 0.643-0.841 and 0.688-0.877, respectively.
CONCLUSION: The generative adversarial network automatically quantified COVID-19 pneumonia on chest radiographs and identified patients with unfavorable outcomes.
引用
- Yoo, Kim, Witanto, et al. Generative adversarial network for automatic quantification of Coronavirus disease 2019 pneumonia on chest radiographs. Eur J Radiol. 2023. PMID: 37209462. doi:10.1016/j.ejrad.2023.110858
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。