基于MR影像组学预测胶质母细胞瘤IDH1突变:手动与全自动深度学习肿瘤分割方法的比较
回顾性分析45例胶质母细胞瘤患者的治疗前T2加权MRI,手动分割肿瘤及瘤周水肿训练深度神经网络(V-Net),并纳入癌症影像档案库137例作为外部验证集。V-Net分割与手动分割在预测IDH1突变方面性能相似(AUC 0.86 vs 0.90),手动分割最佳截点准确率86.8%,V-Net为75.8%。
要点
- V-Net在T2加权MRI上对胶质母细胞瘤分割稳健,平均DSC为0.78±0.14。
- V-Net分割与手动分割预测IDH1突变的AUC分别为0.86和0.90,性能相似。
- 手动分割最佳截点准确率86.8%,V-Net分割为75.8%。
核心结论
- V-Net在T2加权MRI上对胶质母细胞瘤显示出稳健的分割能力。
- 两种分割方法提取的影像组学特征在预测IDH1突变方面性能相似(V-Net AUC=0.86 vs 手动AUC=0.90)。
研究设计与样本
- 回顾性研究,本院45例胶质母细胞瘤患者治疗前T2加权MRI用于手动分割肿瘤及瘤周水肿并训练V-Net。
- 外部独立队列137例来自癌症影像档案库,分为测试集1(n=46)和测试集2(n=91)。
- 测试集1用于计算两种分割方法的DSC,测试集2用于IDH1预测的影像组学特征选择和ROC分析。
关键影像表现/征象
- 影像组学特征基于T2加权MRI提取,未报告具体影像征象。
诊断标准与关键数值
- 测试集1中两种分割方法的平均DSC为0.78±0.14(范围0.34-0.94)。
- 从107个特征中筛选出9个全相关特征(8.4%,9/107)用于IDH1预测。
- V-Net分割预测IDH1突变的AUC=0.86,手动分割AUC=0.90。
- 最佳截点阈值下,手动分割准确率86.8%,V-Net分割准确率75.8%。
临床应用与阅片要点
- V-Net自动分割可用于胶质母细胞瘤T2加权MRI的影像组学分析,预测IDH1突变性能与手动分割相似。
- 原文未据此给出具体临床推荐。
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
PURPOSE: This study aimed to determine whether MR-based radiomics of glioblastoma can predict the isocitrate dehydrogenase-1 (IDH1) mutation status and compare predictive performances between manual and fully automatic deep-learning segmentations.
METHOD: Forty-five glioblastoma patients with pretreatment T2-weighted MRIs were retrospectively evaluated. Manual segmentations of glioblastoma and peri-tumoral edema were trained via a deep neural network (V-Net). An independent external cohort of 137 glioblastoma patients from the Cancer Imaging Archive was also included (test set 1, n = 46; test set 2, n = 91). Test set 1-without known IDH1 status-was used to calculate dice similarity coefficients (DSC) between the two segmentation methods (manual & V-Net). From test set 2, all-relevant radiomic features were selected via a random forest-based wrapper algorithm for IDH1 prediction. Receiver operating characteristics (ROC) curves with areas under the curve (AUC) were plotted as performance metrics for both methods.
RESULTS: Among 136 patients (45 and 91 patients from our institution and test set 2, respectively), 17 patients (11.2 %) had IDH1 mutations. The mean DSC of test set 1 was 0.78 ± 0.14 (range, 0.34-0.94). A subset of 9 all-relevant features (8.4 %, 9/107) was selected. V-Net segmentation of the test set 2 yielded similar performance in predicting IDH1 mutation as compared to manual segmentation (V-Net AUC = 0.86 vs. manual AUC = 0.90). The optimal cut-point threshold of AUC yielded 86.8 % accuracy for manual segmentation and 75.8 % for V-Net segmentation.
CONCLUSIONS: V-Net showed robust segmentation capability of glioblastoma on T2-weighted MRI. All-relevant radiomics features from both segmentation methods yielded a similar performance in IDH1 prediction.
引用
- Choi Y, Nam Y, Lee YS, et al. IDH1 mutation prediction using MR-based radiomics in glioblastoma: comparison between manual and fully automated deep learning-based approach of tumor segmentation. Eur J Radiol. 2020. PMID: 32417712. doi:10.1016/j.ejrad.2020.109031
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。