剂量组学与放疗前多模态MRI放射组学机器学习整合用于胶质母细胞瘤生存分层
本研究回顾性纳入癌症影像档案馆74例胶质母细胞瘤患者,提取计划剂量分布GTV的剂量组学特征及放疗前多模态MRI中CET与ED/nCET亚区的放射组学特征,用L1特征选择构建逻辑回归模型。剂量组学模型平均AUC为0.80±0.12,CET亚区模型为0.90±0.09,联合剂量组学与CET模型提升至0.96±0.07(p<0.05)。
要点
- 剂量组学与放疗前MRI放射组学特征可将GBM患者分层为长期与短期生存组。
- CET亚区放射组学模型 discrimination 显著优于ED/nCET亚区(p<0.05)。
- 剂量组学联合CET模型AUC达0.96±0.07,显著提升生存预测性能(p<0.05)。
核心结论
- 剂量组学与放疗前MRI放射组学特征能够对GBM患者进行长期与短期生存分层。
- 整合剂量组学与放射组学显著增强GBM患者的生存预测。
研究设计与样本
- 回顾性纳入癌症影像档案馆74例GBM患者。
- 提取计划剂量分布GTV的剂量组学特征及放疗前多模态MRI中CET与ED/nCET亚区的放射组学特征。
- 采用L1特征选择优化特征,构建逻辑回归模型,以分层10折交叉验证评估性能。
主要发现
- 剂量组学模型平均AUC为0.80±0.12。
- CET亚区模型平均AUC为0.90±0.09,ED/nCET亚区模型为0.76±0.10,CET显著优于ED/nCET(p<0.05)。
- 基于序列的模型平均AUC:T1CE为0.86±0.12,T1为0.84±0.18,T2为0.85±0.14,FLAIR为0.76±0.21,四序列间无显著差异(p>0.05)。
- 联合剂量组学与CET模型性能提升至0.96±0.07(p<0.05)。
关键数值与推荐
- 剂量组学模型平均AUC 0.80±0.12。
- CET亚区模型平均AUC 0.90±0.09,ED/nCET亚区模型平均AUC 0.76±0.10(p<0.05)。
- 联合剂量组学与CET模型平均AUC 0.96±0.07(p<0.05)。
临床怎么用
- 可利用计划剂量分布与放疗前多模态MRI提取的剂量组学和放射组学特征辅助GBM患者生存分层。
- 建模时优先关注CET亚区放射组学特征,并考虑与剂量组学特征联合以提升预测性能。
局限性
- 回顾性研究,样本量74例,来自单一公开数据库。
- 原文未报告外部验证结果。
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)。
原文
BACKGROUND: Tumor heterogeneity is a significant factor contributing to the marked differences in survival rates among glioblastoma multiforme (GBM) patients, who face a poor prognosis. To improve personalized treatment, it is essential to identify specific tumor characteristics that capture this variability and aid in predicting survival. This study aimed to evaluate the utility of dosiomics and radiomics in predicting overall survival (OS). The central hypothesis was that integrating dosiomics and radiomics could improve survival outcome predictions. METHODS: A total of 74 GBM patients from The Cancer Imaging Archive were retrospectively included. Dosiomic features from the gross tumor volume (GTV) of planned dose distributions, along with radiomic features from the contrast-enhanced tumor (CET) and edema/non-contrast-enhanced tumor (ED/nCET) subregions across various pre-radiation MRI modalities, were extracted and optimized using L1-based feature selection. Logistic Regression (LR) models were built utilizing different feature configurations to assess the discriminative power of dosiomic and radiomic features, considering the impact of heterogeneous subregions. Model performance was assessed through stratified 10-fold cross-validation (CV). RESULTS: The dosiomic model exhibited a mean area under the receiver operating characteristic (ROC) curve (AUC) of 0.80 ± 0.12. The subregion-based models demonstrated mean AUC values of 0.90 ± 0.09 for the CET subregion and 0.76 ± 0.10 for the ED/nCET subregion, indicating that the CET subregion significantly outperformed the ED/nCET subregion (p-value < 0.05). The mean AUC values for modality-based models were as follows: 0.86 ± 0.12 for T1-weighted contrast-enhanced (T1CE), 0.84 ± 0.18 for T1-weighted (T1), 0.85 ± 0.14 for T2-weighted (T2), and 0.76 ± 0.21 for fluid-attenuated inversion recovery (FLAIR) sequences. There was no significant difference in discrimination power among the four modalities (p-value > 0.05). The combined dosiomic and CET model improved performance to 0.96 ± 0.07 (p < 0.05). CONCLUSIONS: Dosiomic and pre-radiotherapy MRI-derived radiomic features are capable of stratifying GBM patients into two long-term and short-term groups. Notably, the integration of dosiomics and radiomics significantly enhances survival prediction in GBM patients.
引用
- Mahmoudi A, Sadeghi AZ, Iraji H, et al. Machine learning-based integration of dosiomics and pre-radiotherapy multimodal MRI radiomics for survival stratification in patients with glioblastoma multiforme. Radiat Oncol. 2025. PMID: 41331644. doi:10.1186/s13014-025-02764-y
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。