文献速递胸部CT

基于CT图像的可解释机器学习预测表现为磨玻璃结节的肺腺癌侵袭性

Explainable Machine Learning for Predicting Invasiveness of Pulmonary Adenocarcinoma Presenting as Ground-Glass Nodules Using CT Images.
PubMed 文献 · Acad Radiol · 2025-10-22

双中心回顾性研究纳入516例病理证实的磨玻璃结节(≤30mm),整合平扫与增强CT的影像组学、深度学习特征及瘤内栖息特征建立综合模型,区分浸润性腺癌与浸润前病变;外部验证集AUC为0.85(95%CI: 0.80-0.91),准确率80%,敏感度80%,特异度80%,SHAP分析显示小波纹理、深度学习及栖息特征贡献显著。

要点

  • 综合模型在外部验证集区分浸润性腺癌与浸润前病变的AUC为0.85(95%CI: 0.80-0.91)。
  • 外部验证集准确率80%、敏感度80%、特异度80%,内部验证集AUC为0.90(95%CI: 0.86-0.95)。
  • DCA显示阈值概率≥0.4时列线图净获益最高,Hosmer-Lemeshow检验提示校准良好(P>0.05)。

核心结论

  • 综合模型(影像组学、深度学习、瘤内栖息特征及临床变量)能可靠预测磨玻璃结节相关肺腺癌的侵袭性,连接影像与病理,可能推动早期肺腺癌的个性化手术决策。

研究设计与样本

  • 双中心回顾性研究,纳入2018年12月至2023年9月病理证实的磨玻璃结节(≤30mm)患者516例;中心1患者随机分为训练集276例和内部验证集120例,中心2患者全部纳入外部验证集120例;对平扫和增强CT图像行瘤内栖息分析(K-means聚类),从病灶区域和聚类亚区提取影像组学特征,经微调ResNet50模型获取深度学习特征,特征选择后建立8个预测模型及动态列线图(综合模型),并用SHAP进行可解释分析;以AUC、决策曲线分析和校准曲线评估模型性能。

诊断标准与关键数值

  • 综合模型区分浸润性腺癌(IAC)与浸润前病变(AAH/AIS/MIA):训练集AUC 0.92(95%CI: 0.89-0.95)、准确率84%、敏感度85%、特异度84%;内部验证集AUC 0.90(95%CI: 0.86-0.95)、准确率82%、敏感度88%、特异度74%;外部验证集AUC 0.85(95%CI: 0.80-0.91)、准确率80%、敏感度80%、特异度80%;阈值概率≥0.4时列线图净获益最高,Hosmer-Lemeshow检验P>0.05提示校准良好。

临床应用与阅片要点

  • 作者认为综合模型可可靠预测磨玻璃结节相关肺腺癌的侵袭性,可能推动早期肺腺癌的个性化手术决策;SHAP分析显示小波纹理特征、深度学习特征和瘤内栖息特征对模型性能贡献显著。

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: Accurate prediction of the invasiveness of early-stage pulmonary adenocarcinoma presenting as ground-glass nodules (GGNs) remains highly challenging. This study aims to integrate radiomics features from non-contrast CT (NECT) and contrast-enhanced CT (CECT), deep learning features, and intratumoral habitat features to improve prediction accuracy and provide robust support for clinical personalized surgical decision-making.

MATERIALS AND METHODS: This dual-center retrospective study included 516 patients with pathologically confirmed GGNs (≤30mm) from December 2018 to September 2023. Patients from center 1 were randomly divided into training (276 patients) and internal-validation (120 patients) sets, while patients from center 2 were all included into external-validation (120 patients) set. Intratumoral habitat analysis (ITH) was performed on NECT and CECT images using the K-means clustering algorithm. Radiomic features were extracted from the lesion regions and clustered subregions, deep learning features were obtained via a fine-tuned ResNet50 model. After feature selection, eight predictive models were established. Additionally, a dynamic nomogram (the comprehensive model) was developed and subjected to explainable analysis using SHAP (SHapley Additive exPlanations). Model performance was assessed using area under the curve (AUC), decision curve analysis (DCA), and calibration curves.

RESULTS: Among eight predictive models, the comprehensive model, which utilized multi-modal data as input demonstrated the highest accuracy in distinguishing invasive adenocarcinoma (IAC) from pre-invasive lesions (AAH/AIS/MIA). In the training set, the AUC was 0.92 (95% CI: 0.89-0.95), with 84% accuracy, 85% sensitivity, and 84% specificity. In the internal-validation set, the AUC was 0.90 (95% CI: 0.86-0.95), with 82% accuracy, 88% sensitivity, and 74% specificity. In the external-validation set, the AUC was 0.85 (95% CI: 0.80-0.91), with 80% accuracy, 80% sensitivity, and 80% specificity. DCA analysis showed that the nomogram provided the highest net benefit when the threshold probability was ≥0.4, and the Hosmer-Lemeshow test confirmed good calibration (P>0.05). SHAP analysis and the selected of optimal features revealed that wavelet-based texture features, deep learning features, and ITH features made significant contributions to the model's performance.

CONCLUSION: The comprehensive model (radiomics, deep learning, ITH, clinical variables) enables reliable prediction of the invasiveness of GGNs-ADC. It bridges imaging and pathology, potentially advancing personalized surgical decision-making in early-stage lung adenocarcinoma.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Zhang H, Miao L, Ma L, et al. Explainable Machine Learning for Predicting Invasiveness of Pulmonary Adenocarcinoma Presenting as Ground-Glass Nodules Using CT Images. Acad Radiol. 2025. PMID: 41130882. doi:10.1016/j.acra.2025.10.004

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。