基于机器学习的稳定期PRISm相关定量CT影像特征
研究纳入596例基线及3年随访未发生组别转换的参与者(稳定对照组274例、稳定PRISm组22例、稳定COPD组300例),用逻辑回归机器学习模型结合定量CT与影像组学特征进行分类。结果显示影像特征模型区分稳定PRISm与稳定对照的AUC为0.63–0.84、与稳定COPD的AUC为0.65–0.92,且稳定PRISm表现为%TLCCT降低、%GG+Reticulationtexture与GLDZMZDV升高。
要点
- 稳定PRISm的CT特征为肺总容积%TLCCT降低、磨玻璃与网织纹理百分比及相应影像组学特征升高。
- 加入定量CT或影像组学特征后模型优于仅用基础特征的模型(p<0.05)。
- 稳定PRISm与稳定对照组区分AUC为0.63–0.84,与稳定COPD区分AUC为0.65–0.92。
核心结论
- CT上肺容积减低及高密度、磨玻璃/网织纹理模式增多与稳定PRISm相关。
研究设计与样本
- 研究共纳入596例在基线与3年随访时未在对照、PRISm和COPD组间转换的参与者,包括稳定对照274例、稳定PRISm 22例、稳定COPD 300例。
关键影像表现/征象
- 与稳定对照和稳定COPD相比,稳定PRISm表现为%TLCCT降低、%GG+Reticulationtexture升高和GLDZMZDV升高。
诊断标准与关键数值
- 稳定PRISm vs 稳定对照的AUC为0.63–0.84,稳定PRISm vs 稳定COPD的AUC为0.65–0.92。
- 纳入影像特征的模型优于仅用基础特征的模型(p<0.05)。
- 研究使用34个定量CT特征(如%TLCCT、%GG+Reticulationtexture)和102个影像组学特征(如GLDZMZDV)。
- 模型性能用AUC评价,模型间比较用DeLong检验,特征重要性用Shapley Additive Explanations值排序。
临床应用与阅片要点
- 阅片时可关注肺总容积减低及磨玻璃/网织纹理增多等定量CT特征,这些特征与稳定PRISm相关。
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
RATIONALE AND OBJECTIVES: The structural lung features that characterize individuals with preserved ratio impaired spirometry (PRISm) that remain stable overtime are unknown. The objective of this study was to use machine learning models with computed tomography (CT) imaging to classify stable PRISm from stable controls and stable COPD and identify discriminative features.
MATERIALS AND METHODS: A total of 596 participants that did not transition between control, PRISm and COPD groups at baseline and 3-year follow-up were evaluated: n = 274 with normal lung function (stable control), n = 22 stable PRISm, and n = 300 stable COPD. Investigated features included: quantitative CT (QCT) features (n = 34), such as total lung volume (%TLCCT) and percentage of ground glass and reticulation (%GG+Reticulationtexture), as well as Radiomic (n = 102) features, including varied intensity zone distribution grainy texture (GLDZMZDV). Logistic regression machine learning models were trained using various feature combinations (Base, Base+QCT, Base+Radiomic, Base+QCT+Radiomic). Model performances were evaluated using area under receiver operator curve (AUC) and comparisons between models were made using DeLong test; feature importance was ranked using Shapley Additive Explanations values.
RESULTS: Machine learning models for all feature combinations achieved AUCs between 0.63-0.84 for stable PRISm vs. stable control, and 0.65-0.92 for stable PRISm vs. stable COPD classification. Models incorporating imaging features outperformed those trained solely on base features (p < 0.05). Compared to stable control and COPD, those with stable PRISm exhibited decreased %TLCCT and increased %GG+Reticulationtexture and GLDZMZDV.
CONCLUSION: These findings suggest that reduced lung volumes, and elevated high-density and ground glass/reticulation patterns on CT imaging are associated with stable PRISm.
引用
- Lukhumaidze L, Hogg JC, Bourbeau J, et al. Quantitative CT Imaging Features Associated with Stable PRISm using Machine Learning. Acad Radiol. 2024. PMID: 39191563. doi:10.1016/j.acra.2024.08.030
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。