文献速递间质性肺疾病

深度学习分类普通型间质性肺炎可预测预后

Deep Learning Classification of Usual Interstitial Pneumonia Predicts Outcomes.
PubMed 文献 · Am J Respir Crit Care Med · 2024-01-01

该研究采用多实例学习(MIL)开发可解释深度学习算法,从CT预测普通型间质性肺炎(UIP),并在三个独立队列中验证。以组织学UIP为金标准,MIL的AUC在0.77和0.79,优于视觉评估的0.65和0.71;MIL-UIP分类与死亡风险升高及FVC年下降更大显著相关。

要点

  • MIL算法从CT预测组织学UIP的AUC达0.77和0.79,优于视觉评估。
  • MIL-UIP阳性与死亡风险显著升高相关(HR 3.1和3.64)。
  • MIL-UIP阳性者FVC年下降更大(-88 ml/yr vs -45 ml/yr)。

核心结论

  • 基于多实例学习的CT评估可识别UIP的临床显著特征,可能提高间质性肺病影像评估信心并助力更早更精准诊断。

研究设计与样本

  • 研究采用多实例学习算法,使用汇总数据集(n=2,143)训练,并在三个独立人群测试:既往发表数据(n=127)、单中心临床队列(n=239)和国家肺纤维化登记队列(n=979)。
  • 以组织学UIP为金标准,采用受试者工作特征分析评估UIP分类性能,并用Cox比例风险模型和线性混合效应模型分析MIL预测与生存或纵向FVC的关联。

主要发现

  • 在两个有活检数据的队列中,MIL对组织学UIP的AUC为0.77(n=127)和0.79(n=239),视觉评估的AUC为0.65和0.71。
  • 在有生存数据的队列中,MIL-UIP分类与死亡率显著相关:n=239队列(截至2021年4月)未校正HR 3.1(95%CI 1.96-4.91,P<0.001);n=979队列(截至2022年7月)未校正HR 3.64(95%CI 2.66-4.97,P<0.001)。
  • 在n=979队列中,校正肺纤维化范围后,算法分类为UIP阳性者FVC年下降显著大于UIP阴性者(-88 ml/yr vs -45 ml/yr,P<0.01)。

临床怎么用

  • 该MIL算法可作为CT评估UIP的辅助工具,提高对间质性肺病患者影像学评估的信心。
  • MIL-UIP分类与死亡风险升高和FVC下降更快相关,可能有助于风险分层和早期识别进展性纤维化患者。

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: Computed tomography (CT) enables noninvasive diagnosis of usual interstitial pneumonia (UIP), but enhanced image analyses are needed to overcome the limitations of visual assessment. Objectives: Apply multiple instance learning (MIL) to develop an explainable deep learning algorithm for prediction of UIP from CT and validate its performance in independent cohorts. Methods: We trained an MIL algorithm using a pooled dataset (n = 2,143) and tested it in three independent populations: data from a prior publication (n = 127), a single-institution clinical cohort (n = 239), and a national registry of patients with pulmonary fibrosis (n = 979). We tested UIP classification performance using receiver operating characteristic analysis, with histologic UIP as ground truth. Cox proportional hazards and linear mixed-effects models were used to examine associations between MIL predictions and survival or longitudinal FVC. Measurements and Main Results: In two cohorts with biopsy data, MIL improved accuracy for histologic UIP (area under the curve, 0.77 [n = 127] and 0.79 [n = 239]) compared with visual assessment (area under the curve, 0.65 and 0.71). In cohorts with survival data, MIL-UIP classifications were significant for mortality (n = 239, mortality to April 2021: unadjusted hazard ratio, 3.1; 95% confidence interval [CI], 1.96-4.91; P < 0.001; and n = 979, mortality to July 2022: unadjusted hazard ratio, 3.64; 95% CI, 2.66-4.97; P < 0.001). Individuals classified as UIP positive by the algorithm had a significantly greater annual decline in FVC than those classified as UIP negative (-88 ml/yr vs. -45 ml/yr; n = 979; P < 0.01), adjusting for extent of lung fibrosis. Conclusions: Computerized assessment using MIL identifies clinically significant features of UIP on CT. Such a method could improve confidence in radiologic assessment of patients with interstitial lung disease, potentially enabling earlier and more precise diagnosis.

来源:Am J Respir Crit Care Med,查看原文。版权归原作者所有。

引用

  1. Humphries SM, Thieke D, Baraghoshi D, et al. Deep Learning Classification of Usual Interstitial Pneumonia Predicts Outcomes. Am J Respir Crit Care Med. 2024. PMID: 38207093. doi:10.1164/rccm.202307-1191OC

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。