基于MRI的影像组学模型预测鼻咽癌放射性颞叶损伤
回顾性分析216例鼻咽癌患者,随机分为训练组136例和验证组80例,从治疗前增强T1或脂肪抑制T2加权MRI提取影像组学特征构建模型。影像组学模型在训练组AUC为0.89、验证组AUC为0.92,优于临床模型(p<0.05);临床-影像组学联合模型AUC更高(0.93和0.95)。
要点
- 治疗前颞叶MRI影像组学特征与鼻咽癌放射性颞叶损伤相关。
- 影像组学模型预测性能优于临床模型(p<0.05)。
- 临床-影像组学联合模型在不同临床-病理亚组中均表现优异。
核心结论
- 基于治疗前颞叶MRI的影像组学模型对鼻咽癌放射性颞叶损伤显示出有说服力的预测性能。
研究设计与样本
- 回顾性研究,共纳入216例确诊鼻咽癌患者,随机分为训练组136例和验证组80例;从治疗前增强T1加权或脂肪抑制T2加权MRI提取影像组学特征,以LASSO回归、Pearson相关分析和单变量逻辑回归生成影像组学标签,临床特征经逻辑回归筛选,多变量逻辑回归在训练组构建影像组学、临床变量和临床-影像组学三种模型。
诊断标准与关键数值
- 由两个影像组学特征构成的影像组学标签与放射性颞叶损伤显著相关;影像组学模型训练组AUC为0.89、验证组AUC为0.92,优于临床预测模型(p<0.05);临床-影像组学联合模型AUC分别为0.93和0.95,校准和预测准确性更优。
临床应用与阅片要点
- 作者认为,基于治疗前颞叶MRI的影像组学模型对预测鼻咽癌放射性颞叶损伤表现出有说服力的性能。
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 validate a radiomics-based model for predicting radiation-induced temporal lobe injury (RTLI) in nasopharyngeal carcinoma (NPC) by pretreatment MRI of the temporal lobe.
METHODS: A total of 216 patients with diagnosed NPC were retrospectively reviewed. Patients were randomly allocated to the training (n = 136) and the validation cohort (n = 80). Radiomics features were extracted from pretreatment contrast-enhanced T1- or fat-suppressed T2 weighted MRI. A radiomics signature was generated by the least absolute shrinkage and selection operator (LASSO) regression algorithm, Pearson correlation analysis, and univariable logistic analysis. Clinical features were selected with logistic regression analysis. Multivariable logistic regression analysis was conducted to develop three models for RTLI prediction in the training cohort: namely radiomics signature, clinical variables, and clinical-radiomics parameters. A radiomics nomogram was used and assessed with respect to calibration, discrimination, reclassification, and clinical application.
RESULTS: The radiomics signature, composed of two radiomics features, was significantly associated with RTLI. The proposed radiomics model demonstrated favorable discrimination in both the training (AUC, 0.89) and the validation cohort (AUC, 0.92), outperforming the clinical prediction model (p < 0.05). Combining radiomics and clinical features, higher AUCs were achieved (AUC, 0.93 and 0.95), as well as a better calibration and improved accuracy of the prediction of RTLI. The clinical-radiomics model showed also excellent performance in predicting RTLI in different clinical-pathologic subgroups.
CONCLUSION: A radiomics model derived from pretreatment MRI of the temporal lobe showed persuasive performance for predicting radiation-induced temporal lobe injury in nasopharyngeal carcinoma.
KEY POINTS: • Radiomics features from pretreatment MRI are associated with radiation-induced temporal lobe injury in nasopharyngeal carcinoma. • The radiomics model shows better predictive performance than a clinical model and was similar to a clinical-radiomics model. • A clinical-radiomics model shows excellent performance in the prediction of radiation-induced temporal lobe injury in different clinical-pathologic subgroups.
引用
- Bao, Zhao, Li, et al. A MRI-based radiomics model predicting radiation-induced temporal lobe injury in nasopharyngeal carcinoma. Eur Radiol. 2022. PMID: 35639143. doi:10.1007/s00330-022-08853-w
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。