文献速递肺结节与肺癌

影像组学结合机器学习预测肺结节恶性风险

Radiomics analysis to predict pulmonary nodule malignancy using machine learning approaches.
PubMed 文献 · Thorax · 2024-03-15

LASSO模型在测试集AUC为0.93(95%CI 0.90-0.96),优于Pan-Canadian模型(AUC 0.87,95%CI 0.85-0.89),在实性和亚实性结节中均表现良好。

要点

  • 影像组学机器学习模型可高精度预测筛查发现的肺结节恶性风险。
  • LASSO模型测试集AUC 0.93,优于现有Pan-Canadian模型(AUC 0.87)。
  • 模型在实性(AUC 0.93)和亚实性结节(AUC 0.91)中均表现良好。

核心结论

  • 基于影像组学和流行病学特征的机器学习模型可准确评估筛查发现的肺结节恶性风险。

研究设计与样本

  • 提取2060个影像组学特征,经筛选后保留642个影像组学特征和9个流行病学特征用于建模。
  • 采用交叉验证和网格搜索评估三种机器学习模型(XGBoost、随机森林、LASSO)。

主要发现

  • LASSO模型在交叉验证中表现最佳,并在全训练集上拟合。
  • 影像组学模型测试集AUC为0.93(95%CI 0.90-0.96),优于Pan-Canadian模型(AUC 0.87,95%CI 0.85-0.89)。
  • 实性结节AUC为0.93(95%CI 0.89-0.97),亚实性结节AUC为0.91(95%CI 0.85-0.95)。

临床怎么用

  • 该模型可能适用于评估筛查中发现的不确定性肺结节的恶性风险。

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

BACKGROUND: Low-dose CT screening can reduce lung cancer-related mortality. However, most screen-detected pulmonary abnormalities do not develop into cancer and it often remains challenging to identify malignant nodules, particularly among indeterminate nodules. We aimed to develop and assess prediction models based on radiological features to discriminate between benign and malignant pulmonary lesions detected on a baseline screen. METHODS: Using four international lung cancer screening studies, we extracted 2060 radiomic features for each of 16 797 nodules (513 malignant) among 6865 participants. After filtering out low-quality radiomic features, 642 radiomic and 9 epidemiological features remained for model development. We used cross-validation and grid search to assess three machine learning (ML) models (eXtreme Gradient Boosted Trees, random forest, least absolute shrinkage and selection operator (LASSO)) for their ability to accurately predict risk of malignancy for pulmonary nodules. We report model performance based on the area under the curve (AUC) and calibration metrics in the held-out test set. RESULTS: The LASSO model yielded the best predictive performance in cross-validation and was fit in the full training set based on optimised hyperparameters. Our radiomics model had a test-set AUC of 0.93 (95% CI 0.90 to 0.96) and outperformed the established Pan-Canadian Early Detection of Lung Cancer model (AUC 0.87, 95% CI 0.85 to 0.89) for nodule assessment. Our model performed well among both solid (AUC 0.93, 95% CI 0.89 to 0.97) and subsolid nodules (AUC 0.91, 95% CI 0.85 to 0.95). CONCLUSIONS: We developed highly accurate ML models based on radiomic and epidemiological features from four international lung cancer screening studies that may be suitable for assessing indeterminate screen-detected pulmonary nodules for risk of malignancy.

来源:Thorax,查看原文。版权归原作者所有。

引用

  1. Warkentin MT, Al-Sawaihey H, Lam S, et al. Radiomics analysis to predict pulmonary nodule malignancy using machine learning approaches. Thorax. 2024. PMID: 38195644. doi:10.1136/thorax-2023-220226

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。