深度学习在胸部CT中对吸烟者进行疾病分期与预后预测
本研究利用7,983例COPDGene参与者的CT扫描训练卷积神经网络,并在1,000例COPDGene和1,672例ECLIPSE参与者中评估。CNN检测COPD的C统计量为0.856,预测急性呼吸疾病事件的C统计量在COPDGene和ECLIPSE分别为0.64和0.55,预测死亡率的C指数分别为0.72和0.60,校准良好。结论认为仅用CT影像的深度学习方法可识别吸烟者的COPD并预测急性呼吸疾病事件和死亡率。
要点
- CNN仅用CT影像检测COPD的C统计量为0.856。
- COPDGene中51.1%准确分期,74.95%在相邻一期内。
- 预测急性呼吸疾病事件和死亡率的区分度中等,校准良好。
核心结论
- 仅用CT影像数据的深度学习方法可识别吸烟者中的COPD,并预测急性呼吸疾病事件和死亡率。
- 在人群水平上,CNN分析可能是有力的风险评估工具。
研究设计与样本
- 卷积神经网络(CNN)使用7,983例COPDGene参与者的CT扫描训练。
- 在1,000例非重叠COPDGene参与者和1,672例ECLIPSE参与者中评估。
- COPD诊断和急性呼吸疾病预测用逻辑回归(C统计量和Hosmer-Lemeshow检验)评估。
- 死亡率用Cox回归(C指数和Greenwood-Nam-D'Agostino检验)评估。
主要发现
- COPDGene中检测COPD的C统计量为0.856。
- COPDGene中51.1%参与者被准确分期,74.95%在相邻一期内。
- ECLIPSE中29.4%被准确分期,74.6%在相邻一期内。
- COPDGene和ECLIPSE中急性呼吸疾病事件的C统计量分别为0.64和0.55,Hosmer-Lemeshow P值分别为0.502和0.380。
- COPDGene和ECLIPSE中CNN预测死亡率的C指数分别为0.72和0.60,Greenwood-Nam-D'Agostino P值分别为0.307和0.331。
临床怎么用
- 对于吸烟者,可利用胸部CT的CNN分析辅助识别COPD和评估急性呼吸疾病事件及死亡风险。
- CNN分析可作为人群水平风险分层的补充工具。
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)。
原文
RATIONALE: Deep learning is a powerful tool that may allow for improved outcome prediction. OBJECTIVES: To determine if deep learning, specifically convolutional neural network (CNN) analysis, could detect and stage chronic obstructive pulmonary disease (COPD) and predict acute respiratory disease (ARD) events and mortality in smokers. METHODS: A CNN was trained using computed tomography scans from 7,983 COPDGene participants and evaluated using 1,000 nonoverlapping COPDGene participants and 1,672 ECLIPSE participants. Logistic regression (C statistic and the Hosmer-Lemeshow test) was used to assess COPD diagnosis and ARD prediction. Cox regression (C index and the Greenwood-Nam-D'Agnostino test) was used to assess mortality. MEASUREMENTS AND MAIN RESULTS: In COPDGene, the C statistic for the detection of COPD was 0.856. A total of 51.1% of participants in COPDGene were accurately staged and 74.95% were within one stage. In ECLIPSE, 29.4% were accurately staged and 74.6% were within one stage. In COPDGene and ECLIPSE, the C statistics for ARD events were 0.64 and 0.55, respectively, and the Hosmer-Lemeshow P values were 0.502 and 0.380, respectively, suggesting no evidence of poor calibration. In COPDGene and ECLIPSE, CNN predicted mortality with fair discrimination (C indices, 0.72 and 0.60, respectively), and without evidence of poor calibration (Greenwood-Nam-D'Agnostino P values, 0.307 and 0.331, respectively). CONCLUSIONS: A deep-learning approach that uses only computed tomography imaging data can identify those smokers who have COPD and predict who are most likely to have ARD events and those with the highest mortality. At a population level CNN analysis may be a powerful tool for risk assessment.
引用
- González G, Ash SY, Vegas-Sánchez-Ferrero G, et al. Disease Staging and Prognosis in Smokers Using Deep Learning in Chest Computed Tomography. Am J Respir Crit Care Med. 2018. PMID: 28892454. doi:10.1164/rccm.201705-0860OC
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。