BACKGROUND Quantitative chest computed tomography (CT) may be a useful predictor of outcome in rheumatoid arthritis-related interstitial lung disease (RA-ILD). RESEARCH QUESTION What is the utility of deep learning-based lung fibrosis quantitation on CT in assessing disease severity, predicting mortality and identifying progression in RA-ILD? STUDY DESIGN AND METHODS CT scans on a primary cohort of 289 and a validation cohort of 50 individuals with RA-ILD were assessed quantitatively by using the data-driven texture analysis (DTA) method. We examined associations between quantitative scores for extent of lung fibrosis and pulmonary function and survival. RESULTS DTA fibrosis score at baseline showed moderate negative correlation with forced vital capacity (FVC) percentage predicted (primary cohort rho=-0.55, validation cohort rho= -0.50, p<0.001 for both), and diffusing capacity for carbon monoxide (DLCO) percentage predicted (primary cohort rho=-0.67, validation cohort rho=-0.65, p<0.001 for both). Longitudinal change in DTA fibrosis score was associated with changes in FVC and DLCO in the primary cohort (rho=-0.46 and rho=-0.43, respectively, p<0.001 for both). Cox multivariable models adjusted for potentially influential variables showed that the baseline DTA fibrosis score was significantly associated with mortality risk (primary cohort hazard ratio [HR] 1.04, 95% confidence interval [1.03, 1.05], p<0.001; validation cohort HR 1.06, 95% confidence interval [1.01, 1.11], p=0.026). In the primary cohort increase in DTA fibrosis score on sequential scans was associated with increased risk of mortality (HR 1.04, 95% confidence interval [1.01, 1.06], p=0.003) independent of baseline DTA extent. INTERPRETATION In two cohorts of patients with RA-ILD, quantitative assessment of lung fibrosis on CT was associated with worse lung function at baseline and risk of mortality. Increase in DTA-derived lung fibrosis score on sequential scans was associated with subsequent risk of mortality. Quantitative CT should be considered for use as a clinical and research outcome assessment tool in RA-ILD.

中文翻译：

---

类风湿性关节炎相关间质性肺病的定量计算机断层扫描分析。


背景 定量胸部计算机断层扫描 （CT） 可能是类风湿性关节炎相关间质性肺病 （RA-ILD） 预后的有用预测指标。研究问题 基于深度学习的 CT 肺纤维化定量在评估疾病严重程度、预测死亡率和识别 RA-ILD 进展方面有什么用？研究设计和方法 使用数据驱动的纹理分析 （DTA） 方法定量评估 289 名主要队列和 50 名 RA-ILD 个体的验证队列的 CT 扫描。我们检查了肺纤维化程度的定量评分与肺功能和生存率之间的关联。结果 基线时的 DTA 纤维化评分显示与预测的用力肺活量 （FVC） 百分比 （主要队列 rho=-0.55，验证队列 rho= -0.50，p<0.001） 和预测的一氧化碳弥散量 （DLCO） 百分比呈中度负相关 （主要队列 rho=-0.67，验证队列 rho=-0.65，p<0.001两者）。DTA 纤维化评分的纵向变化与主要队列中 FVC 和 DLCO 的变化相关 （分别为 rho=-0.46 和 rho=-0.43，两者的 p<0.001）。针对潜在影响变量进行调整的 Cox 多变量模型显示，基线 DTA 纤维化评分与死亡风险显著相关 （主要队列风险比 [HR] 1.04,95% 置信区间 [1.03， 1.05]，p<0.001;验证队列 HR 1.06,95% 置信区间 [1.01， 1.11]，p=0.026）。在主要队列中，顺序扫描时 DTA 纤维化评分的增加与死亡风险增加相关 （HR 1.04,95% 置信区间 [1.01， 1.06]，p=0.003），与基线 DTA 程度无关。 解释 在两组 RA-ILD 患者中，CT 上肺纤维化的定量评估与基线时肺功能恶化和死亡风险相关。顺序扫描中 DTA 衍生的肺纤维化评分增加与随后的死亡风险相关。应考虑将定量 CT 用作 RA-ILD 的临床和研究结果评估工具。