文献速递头颈CT

基于CT影像组学特征构建的机器学习模型用于术前预测喉及下咽癌T2/T3分期

Machine learning model to preoperatively predict T2/T3 staging of laryngeal and hypopharyngeal cancer based on the CT radiomic signature.
PubMed 文献 · Eur Radiol · 2024-01-11

本研究回顾性纳入118例经病理证实的喉及下咽鳞状细胞癌患者,基于增强CT提取851个影像组学特征,结合三种特征选择方法与七种机器学习分类器构建模型,其中方差分析联合逻辑回归模型表现最佳,训练集、验证集和测试集AUC分别为0.919、0.857和0.817;整合影像组学特征与可疑甲状软骨侵犯的列线图C指数为0.899(95%CI 0.843-0.955),校准曲线拟合良好(p>0.05),决策曲线分析证实其临床实用性。

要点

  • 基于增强CT影像组学特征联合逻辑回归的模型在测试集区分T2与T3期的AUC为0.817。
  • 整合影像组学特征与可疑甲状软骨侵犯的列线图C指数为0.899(95%CI 0.843-0.955)。
  • 可疑甲状软骨侵犯是区分T2/T3期有统计学意义的形态学影像特征。

核心结论

  • 基于增强CT影像组学模型构建的列线图对区分喉及下咽鳞状细胞癌T2与T3分期具有良好诊断性能,可提供无创且稳健的方法辅助优化临床决策。

研究设计与样本

  • 回顾性研究,纳入118例经病理证实的喉及下咽鳞状细胞癌患者,基于增强CT图像提取851个影像组学特征,采用三种特征选择方法与七种机器学习分类器组合构建多个影像组学模型,以AUC、准确率、敏感度和特异度评估模型性能。

关键影像表现/征象

  • 有统计学意义的形态学影像特征为可疑甲状软骨侵犯,该特征与影像组学特征共同纳入预测列线图。

诊断标准与关键数值

  • 方差分析联合逻辑回归分类器产生的模型最佳,训练集、验证集和测试集AUC分别为0.919、0.857和0.817;列线图C指数为0.899(95%CI 0.843-0.955),校准曲线拟合良好(p>0.05)。

临床应用与阅片要点

  • 作者指出,准确的T2/T3分期评估有助于确定是否行喉切除术或喉保留治疗,基于增强CT影像组学模型的列线图有潜力预测喉及下咽鳞状细胞癌T2/T3分期,为优化临床决策提供无创且稳健的方法。

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: To develop and assess a radiomics-based prediction model for distinguishing T2/T3 staging of laryngeal and hypopharyngeal squamous cell carcinoma (LHSCC) METHODS: A total of 118 patients with pathologically proven LHSCC were enrolled in this retrospective study. We performed feature processing based on 851 radiomic features derived from contrast-enhanced CT images and established multiple radiomic models by combining three feature selection methods and seven machine learning classifiers. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were used to assess the performance of the models. The radiomic signature obtained from the optimal model and statistically significant morphological image characteristics were incorporated into the predictive nomogram. The performance of the nomogram was assessed by calibration curve and decision curve analysis.

RESULTS: Using analysis of variance (ANOVA) feature selection and logistic regression (LR) classifier produced the best model. The AUCs of the training, validation, and test sets were 0.919, 0.857, and 0.817, respectively. A nomogram based on the model integrating the radiomic signature and a morphological imaging characteristic (suspicious thyroid cartilage invasion) exhibited C-indexes of 0.899 (95% confidence interval (CI) 0.843-0.955), fitting well in calibration curves (p > 0.05). Decision curve analysis further confirmed the clinical usefulness of the nomogram.

CONCLUSIONS: The nomogram based on the radiomics model derived from contrast-enhanced CT images had good diagnostic performance for distinguishing T2/T3 staging of LHSCC.

CLINICAL RELEVANCE STATEMENT: Accurate T2/T3 staging assessment of LHSCC aids in determining whether laryngectomy or laryngeal preservation therapy should be performed. The nomogram based on the radiomics model derived from contrast-enhanced CT images has the potential to predict the T2/T3 staging of LHSCC, which can provide a non-invasive and robust approach for guiding the optimization of clinical decision-making.

KEY POINTS: • Combining analysis of variance with logistic regression yielded the optimal radiomic model. • A nomogram based on the CT-radiomic signature has good performance for differentiating T2 from T3 staging of laryngeal and hypopharyngeal squamous cell carcinoma. • It provides a non-invasive and robust approach for guiding the optimization of clinical decision-making.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Liu Q, Liu S, Mao Y, et al. Machine learning model to preoperatively predict T2/T3 staging of laryngeal and hypopharyngeal cancer based on the CT radiomic signature. Eur Radiol. 2024. PMID: 38206403. doi:10.1007/s00330-023-10557-8

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。