文献速递胸部CT

基于CT的不同深度学习模型预测非小细胞肺癌脏层胸膜侵犯的应用价值比较:一项回顾性、多中心研究

To Compare the Application Value of Different Deep Learning Models Based on CT in Predicting Visceral Pleural Invasion of Non-small Cell Lung Cancer: A Retrospective, Multicenter Study.
PubMed 文献 · Acad Radiol · 2025-07-24

本研究回顾性纳入2017年6月至2022年9月经病理证实的1931例非小细胞肺癌患者,以弹性纤维染色为脏层胸膜侵犯诊断金标准,构建二维、三维及混合三维深度学习模型。Double-head Res2Net_F6融合模型验证队列AUC最高(0.941),三种三维模型均优于二维模型(EfficientNet-B0_2D,均P<0.05)。

要点

  • Double-head Res2Net_F6融合模型验证队列AUC为0.941,高于其他模型。
  • 三种三维模型验证队列预测性能相当,且均优于二维模型(均P<0.05)。
  • 二维模型EfficientNet-B0_2D验证队列AUC为0.785,为四者中最低。

核心结论

  • 基于深度学习的预测模型用于预测非小细胞肺癌脏层胸膜侵犯是可行的,融合六个临床-CT特征的Double-head Res2Net_F6模型诊断效能最高。

研究设计与样本

  • 回顾性、多中心研究,最终纳入1931例病理确诊的非小细胞肺癌患者,以弹性纤维染色分析为脏层胸膜侵犯诊断金标准,采用EfficientNet-B0和Res2Net两种卷积神经网络架构构建模型。

诊断标准与关键数值

  • Double-head Res2Net_F6融合模型验证队列AUC为0.941,为所有模型中最高。
  • Double-head Res2Net模型验证队列AUC为0.879。
  • Double-head Res2Net_F24模型验证队列AUC为0.876。
  • EfficientNet-B0_2D模型验证队列AUC为0.785。
  • 三种三维模型验证队列预测性能相当,且均优于二维模型(EfficientNet-B0_2D,均P<0.05)。

临床应用与阅片要点

  • 作者认为基于深度学习的预测模型可用于预测非小细胞肺癌脏层胸膜侵犯,其中Double-head Res2Net_F6融合模型诊断效能最高。

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: Visceral pleural invasion (VPI) indicates poor prognosis in non-small cell lung cancer (NSCLC), and upgrades T classification of NSCLC from T1 to T2 when accompanied by VPI. This study aimed to develop and validate deep learning models for the accurate prediction of VPI in patients with NSCLC, and to compare the performance of two-dimensional (2D), three-dimensional (3D), and hybrid 3D models.

MATERIALS AND METHODS: This retrospective study included consecutive patients with pathologically confirmed lung tumor between June 2017 and September 2022. The clinical data and preoperative imaging features of these patients were investigated and their relationships with VPI were statistically compared. Elastic fiber staining analysis results were the gold standard for diagnosis of VPI. The data of non-VPI and VPI patients were randomly divided into training cohort and validation cohort based on 8:2 and 6:4, respectively. The EfficientNet-B0_2D model and Double-head Res2Net/_F6/_F24 models were constructed, optimized and verified using two convolutional neural network model architectures-EfficientNet-B0 and Res2Net, respectively, by extracting the features of original CT images and combining specific clinical-CT features. The receiver operating characteristic curve, the area under the curve (AUC), and confusion matrix were utilized to assess the diagnostic efficiency of models. Delong test was used to compare performance between models.

RESULTS: A total of 1931 patients with NSCLC were finally evaluated. By univariate analysis, 20 clinical-CT features were identified as risk predictors of VPI. Comparison of the diagnostic efficacy among the EfficientNet-b0_2D, Double-head Res2Net, Res2Net_F6, and Res2Net_F24 combined models revealed that Double-head Res2Net_F6 model owned the largest AUC of 0.941 among all models, followed by Double-head Res2Net (AUC=0.879), Double-head Res2Net_F24 (AUC=0.876), and EfficientNet-b0_2D (AUC=0.785). The three 3D-based models showed comparable predictive performance in the validation cohort and all outperformed the 2D model (EfficientNet-B0_2D, all P<0.05).

CONCLUSION: It is feasible to predict VPI in NSCLC with the predictive models based on deep learning, and the Double-head Res2Net_F6 model fused with six clinical-CT features showed greatest diagnostic efficacy.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Zhu X, Yang Y, Yan C, et al. To Compare the Application Value of Different Deep Learning Models Based on CT in Predicting Visceral Pleural Invasion of Non-small Cell Lung Cancer: A Retrospective, Multicenter Study. Acad Radiol. 2025. PMID: 40707264. doi:10.1016/j.acra.2025.07.002

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。