机器学习与CT纹理特征对无CT肺气肿证据且弥散功能轻度异常既往吸烟者的分类
回顾性分析71例无COPD的既往吸烟者,利用PyRadiomics提取496个CT纹理特征并结合机器学习分类DLCO正常与轻度异常者;基于纹理特征的逻辑回归混合模型分类准确率达87%,优于常规定量CT指标,高通高通滤波高灰度游程优势纹理特征AUC为0.81。
要点
- 在无CT肺气肿证据的既往吸烟者中,基于CT纹理特征的机器学习模型可区分DLCO正常与轻度异常者。
- 高通高通滤波高灰度游程优势纹理特征AUC为0.81,优于所有临床与影像测量指标。
- 该纹理特征与DLCO(ρ=-0.29,p=.02)、MRI ADC(ρ=0.23,p=.048)及6MWD(ρ=-0.25,p=.02)相关。
核心结论
- 在无CT肺气肿证据的既往吸烟者中,仅用CT纹理特征训练的机器学习模型能准确分类弥散功能异常者,表现优于常规定量CT测量。
研究设计与样本
- 回顾性研究,纳入71例50-85岁无COPD的既往吸烟者,均接受肺功能、体积描记、胸部CT及3He MRI检查以生成VDP和ADC;使用PyRadiomics提取496个CT纹理特征,Boruta和主成分分析用于特征选择,并评估多种分类模型。
诊断标准与关键数值
- DLCO轻度异常定义为DLCO<75%pred,DLCO正常定义为DLCO≥75%pred;29例DLCO轻度异常者与42例DLCO正常者相比,MRI ADC(p<.001)、残气量/肺总量比值(p=.003)、圣乔治呼吸问卷(p=.029)和6MWD(p<.001)有显著差异,而RA950无显著差异(p=.9);基于所选纹理特征的逻辑回归机器学习混合模型分类准确率为87%;高通高通滤波高灰度游程优势纹理特征AUC=0.81。
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: Ex-smokers without spirometry or CT evidence of chronic obstructive pulmonary disease (COPD) but with mildly abnormal diffusing capacity of the lungs for carbon monoxide (DLCO) are at higher risk of developing COPD. It remains difficult to make clinical management decisions for such ex-smokers without other objective assessments consistent with COPD. Hence, our objective was to develop a machine-learning and CT texture-analysis pipeline to dichotomize ex-smokers with normal and abnormal DLCO (DLCO≥75%pred and DLCO<75%pred).
MATERIALS AND METHODS: In this retrospective study, 71 ex-smokers (50-85yrs) without COPD underwent spirometry, plethysmography, thoracic CT, and 3He MRI to generate ventilation defect percent (VDP) and apparent diffusion coefficients (ADC). PyRadiomics was utilized to extract 496 CT texture-features; Boruta and principal component analysis were used for feature selection and various models were investigated for classification. Machine-learning classifiers were evaluated using area under the receiver operator characteristic curve (AUC), sensitivity, specificity, and F1-measure.
RESULTS: Of 71 ex-smokers without COPD, 29 with mildly abnormal DLCO had significantly different MRI ADC (p < .001), residual-volume to total-lung-capacity ratio (p = .003), St. George's Respiratory Questionnaire (p = .029), and six-minute-walk distance (6MWD) (p < .001), but similar relative area of the lung < -950 Hounsfield-units (RA950) (p = .9) compared to 42 ex-smokers with normal DLCO. Logistic-regression machine-learning mixed-model trained on selected texture-features achieved the best classification accuracy of 87%. All clinical and imaging measurements were outperformed by high-high-pass filter high-gray-level-run-emphasis texture-feature (AUC=0.81), which correlated with DLCO (ρ = -0.29, p = .02), MRI ADC (ρ = 0.23, p = .048), and 6MWD (ρ = -0.25, p = .02).
CONCLUSION: In ex-smokers with no CT evidence of emphysema, machine-learning models exclusively trained on CT texture-features accurately classified ex-smokers with abnormal diffusing capacity, outperforming conventional quantitative CT measurements.
引用
- Sharma M, Kirby M, McCormack DG, et al. Machine Learning and CT Texture Features in Ex-smokers with no CT Evidence of Emphysema and Mildly Abnormal Diffusing Capacity. Acad Radiol. 2023. PMID: 38161089. doi:10.1016/j.acra.2023.11.022
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。