基于磁共振成像(MRI)的瘤内及瘤周影像组学用于胶质瘤患者预后预测
本研究回顾性分析163例胶质瘤患者,从临床MRI提取瘤内和瘤周区域的2135个特征,采用最小冗余最大相关法和随机森林算法筛选特征,并用Cox比例风险模型评估预后因素。四种机器学习模型在测试集上评估,其中结合瘤内和瘤周影像组学的随机森林模型预测性能最佳(AUC=0.91;ACC=0.86),优于单区域模型。结论认为联合瘤内和瘤周影像组学可改善生存预测,有潜力作为指导临床决策的实用影像生物标志物。
要点
- 联合瘤内和瘤周影像组学的随机森林模型预测胶质瘤术后3年生存状态性能最佳(AUC=0.91;ACC=0.86)。
- 最终预测模型纳入13个影像组学特征和7个临床特征。
- 单因素Cox回归显示年龄(p=0.003)和肿瘤分级(p<0.001)与术后3年内死亡风险正相关。
核心结论
- 联合瘤内和瘤周影像组学可改善生存预测,有潜力作为指导临床决策的实用影像生物标志物。
研究设计与样本
- 回顾性分析163例胶质瘤患者,分为训练集(n=113)和测试集(n=50);从临床MRI提取2135个特征,采用最小冗余最大相关法和随机森林算法筛选特征,Cox比例风险模型评估预后因素,训练四种机器学习模型(随机森林、逻辑回归、支持向量机、XGBoost),测试集用受试者工作特征曲线评估。
诊断标准与关键数值
- 随机森林模型结合瘤内和瘤周影像组学在测试集上预测术后3年生存状态:AUC=0.91;ACC=0.86,优于单区域模型;最终模型纳入13个影像组学特征和7个临床特征。
临床应用与阅片要点
- 作者认为联合瘤内和瘤周影像组学可改善生存预测,有潜力作为指导临床决策的实用影像生物标志物。
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
AIM: The purpose of this study was to identify robust radiological features from intratumoral and peritumoral regions, evaluate MRI protocols, and machine learning methods for overall survival stratification of glioma patients, and explore the relationship between radiological features and the tumour microenvironment.
MATERIAL AND METHODS: A retrospective analysis was conducted on 163 glioma patients, divided into a training set (n=113) and a testing set (n=50). For each patient, 2135 features were extracted from clinical MRI. Feature selection was performed using the Minimum Redundancy Maximum Relevance method and the Random Forest (RF) algorithm. Prognostic factors were assessed using the Cox proportional hazards model. Four machine learning models (RF, Logistic Regression, Support Vector Machine, and XGBoost) were trained on clinical and radiological features from tumour and peritumoral regions. Model evaluations on the testing set used receiver operating characteristic curves.
RESULTS: Among the 163 patients, 96 had an overall survival (OS) of less than three years postsurgery, while 67 had an OS of more than three years. Univariate Cox regression in the validation set indicated that age (p=0.003) and tumour grade (p<0.001) were positively associated with the risk of death within three years postsurgery. The final predictive model incorporated 13 radiological and 7 clinical features. The RF model, combining intratumor and peritumor radiomics, achieved the best predictive performance (AUC = 0.91; ACC = 0.86), outperforming single-region models.
CONCLUSION: Combined intratumoral and peritumoral radiomics can improve survival prediction and have potential as a practical imaging biomarker to guide clinical decision-making.
引用
- Gao M, Cheng J, Qiu A, et al. Magnetic resonance imaging (MRI)-based intratumoral and peritumoral radiomics for prognosis prediction in glioma patients. Clin Radiol. 2024. PMID: 39218720. doi:10.1016/j.crad.2024.08.005
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。