文献速递胸部神经CT

利用治疗前CT肺部影像数据预测EGFR阳性肺腺癌患者的脑转移

Predicting brain metastases in EGFR-positive lung adenocarcinoma patients using pre-treatment CT lung imaging data.
PubMed 文献 · Eur J Radiol · 2025-06-26

本研究纳入173例EGFR阳性肺腺癌患者(93例脑转移、80例无脑转移),基于治疗前肺部CT提取影像组学特征和深度学习特征构建融合模型。融合vision mamba模型预测2年内脑转移的AUC为0.86(95%CI 0.82-0.90),优于单一影像组学模型和单一深度学习模型。

要点

  • 融合vision mamba模型预测2年内脑转移AUC 0.86(95%CI 0.82-0.90),召回率0.88。
  • 该融合模型性能优于单一影像组学模型和单一深度学习模型。
  • 基于单模态治疗前肺部CT影像即可实现脑转移风险早期预警。

核心结论

  • 融合vision mamba模型利用单一CT影像数据,显著提升对EGFR阳性肺腺癌患者2年内脑转移的预测能力,融合影像组学与深度学习特征的新方法对早期检出和个体化治疗具有潜在临床价值。

研究设计与样本

  • 研究论文;筛选362例有治疗前肺部CT的EGFR阳性肺腺癌患者,最终纳入173例(93例脑转移、80例无脑转移);从手动分割的肺结节区域提取影像组学特征,并用包括vision mamba在内的多种深度学习网络处理ROI级CT图像,构建特征级融合模型;采用ROC曲线和决策曲线分析(DCA)评估性能,用DeLong检验比较AUC。

诊断标准与关键数值

  • 融合vision mamba模型分类性能最佳,AUC 0.86(95%CI 0.82-0.90),召回率0.88,F1分数0.70,准确率0.76;该融合模型优于单一影像组学模型和单一深度学习模型。

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

OBJECTIVES: This study aims to establish a dual-feature fusion model integrating radiomic features with deep learning features, utilizing single-modality pre-treatment lung CT image data to achieve early warning of brain metastasis (BM) risk within 2 years in EGFR-positive lung adenocarcinoma.

MATERIALS AND METHODS: After rigorous screening of 362 EGFR-positive lung adenocarcinoma patients with pre-treatment lung CT images, 173 eligible participants were ultimately enrolled in this study, including 93 patients with BM and 80 without BM. Radiomic features were extracted from manually segmented lung nodule regions, and a selection of features was used to develop radiomics models. For deep learning, ROI-level CT images were processed using several deep learning networks, including the novel vision mamba, which was applied for the first time in this context. A feature-level fusion model was developed by combining radiomic and deep learning features. Model performance was assessed using receiver operating characteristic (ROC) curves and decision curve analysis (DCA), with statistical comparisons of area under the curve (AUC) values using the DeLong test.

RESULTS: Among the models evaluated, the fused vision mamba model demonstrated the best classification performance, achieving an AUC of 0.86 (95% CI: 0.82-0.90), with a recall of 0.88, F1-score of 0.70, and accuracy of 0.76. This fusion model outperformed both radiomics-only and deep learning-only models, highlighting its superior predictive accuracy for early BM risk detection in EGFR-positive lung adenocarcinoma patients.

CONCLUSION: The fused vision mamba model, utilizing single CT imaging data, significantly enhances the prediction of brain metastasis within two years in EGFR-positive lung adenocarcinoma patients. This novel approach, combining radiomic and deep learning features, offers promising clinical value for early detection and personalized treatment.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. He X, Guan C, Chen T, et al. Predicting brain metastases in EGFR-positive lung adenocarcinoma patients using pre-treatment CT lung imaging data. Eur J Radiol. 2025. PMID: 40592110. doi:10.1016/j.ejrad.2025.112265

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。