文献速递腹部泌尿生殖CT

探索主动脉强化归一化方法在评估肾细胞癌组织学亚型中的增量价值:一项多中心大队列研究

Exploring the Incremental Value of Aorta Enhancement Normalization Method in Evaluating Renal Cell Carcinoma Histological Subtypes: A Multi-center Large Cohort Study.
PubMed 文献 · Acad Radiol · 2025-03-28

本研究纳入8个队列共1628例经病理证实行肾切除术的肾细胞癌患者,提出基于病灶与主动脉强化比值的「主动脉强化归一化」(AEN)方法,并构建自动病灶分割模型和多尺度CT特征提取器,采用随机森林、LightGBM、CatBoost和XGBoost等机器学习算法建立分类模型,比较AEN与传统方法在评估组织学亚型(透明细胞肾细胞癌 vs. 非透明细胞肾细胞癌)中的性能。结果表明AEN方法在全部四种算法上均优于传统归一化方法,XGBoost模型中AEN在内部和外部验证集上AUROC分别达0.89、0.81和0.80,SHAP分析显示多尺度CT特征在模型决策中起关键作用。

要点

  • AEN方法基于病灶与主动脉强化比值,可减少成像参数差异对模型的影响。
  • XGBoost模型中AEN的AUROC在内部和外部验证集分别为0.89、0.81和0.80。
  • 多尺度CT特征在模型决策中起关键作用,SHAP分析提升了模型可解释性。

核心结论

  • AEN方法有效减少成像参数差异的影响,显著提高组织学亚型(透明细胞肾细胞癌 vs. 非透明细胞肾细胞癌)模型的鲁棒性和泛化性。
  • 该方法为多中心数据分析提供了新思路,并显示出有前景的临床适用性。

研究设计与样本

  • 研究纳入8个队列共1628例经病理证实行肾切除术的肾细胞癌患者,分为训练集、验证集、外部测试数据集1和外部测试数据集2。
  • 提出基于病灶与主动脉强化比值的「主动脉强化归一化」(AEN)方法,并开发自动病灶分割模型和多尺度CT特征提取器。
  • 采用随机森林、LightGBM、CatBoost和XGBoost等机器学习算法建立分类模型,比较AEN与传统方法评估组织学亚型(透明细胞肾细胞癌 vs. 非透明细胞肾细胞癌)的性能。
  • 采用SHAP分析增强模型决策的透明度和可解释性。

诊断标准与关键数值

  • AEN方法在全部四种算法上均优于传统归一化方法。
  • XGBoost模型中AEN方法在内部和外部验证集上AUROC分别为0.89、0.81和0.80。
  • SHAP分析显示多尺度CT特征在模型决策过程中起关键作用。

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: The classification of renal cell carcinoma (RCC) histological subtypes plays a crucial role in clinical diagnosis. However, traditional image normalization methods often struggle with discrepancies arising from differences in imaging parameters, scanning devices, and multi-center data, which can impact model robustness and generalizability.

MATERIALS AND METHODS: This study included 1628 patients with pathologically confirmed RCC who underwent nephrectomy across eight cohorts. These were divided into a training set, a validation set, external test dataset 1, and external test dataset 2. We proposed an "Aortic Enhancement Normalization" (AEN) method based on the lesion-to-aorta enhancement ratio and developed an automated lesion segmentation model along with a multi-scale CT feature extractor. Several machine learning algorithms, including Random Forest, LightGBM, CatBoost, and XGBoost, were used to build classification models and compare the performance of the AEN and traditional approaches for evaluating histological subtypes (clear cell renal cell carcinoma [ccRCC] vs. non-ccRCC). Additionally, we employed SHAP analysis to further enhance the transparency and interpretability of the model's decisions.

RESULTS: The experimental results demonstrated that the AEN method outperformed the traditional normalization method across all four algorithms. Specifically, in the XGBoost model, the AEN method significantly improved performance in both internal and external validation sets, achieving AUROC values of 0.89, 0.81, and 0.80, highlighting its superior performance and strong generalizability. SHAP analysis revealed that multi-scale CT features played a critical role in the model's decision-making process.

CONCLUSION: The proposed AEN method effectively reduces the impact of imaging parameter differences, significantly improving the robustness and generalizability of histological subtype (ccRCC vs. non-ccRCC) models. This approach provides new insights for multi-center data analysis and demonstrates promising clinical applicability.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Huang Z, Wang L, Mei H, et al. Exploring the Incremental Value of Aorta Enhancement Normalization Method in Evaluating Renal Cell Carcinoma Histological Subtypes: A Multi-center Large Cohort Study. Acad Radiol. 2025. PMID: 40157848. doi:10.1016/j.acra.2025.03.007

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。