Radiomic MRI Phenotyping of Glioblastoma: Improving Survival Preciction
Radiomic MRI Phenotyping of Glioblastoma: Improving Survival Preciction
复制标题
DOI：
10.1148/radiol.2018180200
复制
发表时间：
2018-12-01
期刊：
影响因子：
19.7
通讯作者：
Lee, Seung-Koo
中科院分区：
文献类型：
--
作者：
Bae, Sohi;Choi, Yoon Seong;Lee, Seung-Koo
目的：探讨多形性胶质母细胞瘤(GBM)患者的MRI影像特征与临床和遗传学特征相结合后能否改善患者的生存预测。材料与方法：对2009年12月至2017年1月确诊的多形性胶质母细胞瘤(GBM)患者(217例)的资料进行回顾性分析，并按3：1的比例分配训练和测试集。从多参数MRI中提取放射学特征(n=796)。随机生存林(RSF)模型根据放射组学特征以及临床和遗传学特征(O-6-甲基鸟嘌呤-DNA-甲基转移酶启动子甲基化和异柠檬酸脱氢酶1突变状态)进行训练，以预测总生存期(OS)和无进展生存期(PFS)。在测试集上对RSF模型进行了验证。结果：217例患者平均年龄57.9岁，其中女性87例，年龄2281岁，男性130例，年龄1785岁。中位OS和PFS分别为352d(201809天)和264天(211809天)。在测试集上成功验证了RSF放射组学模型(OS和PFS的iAuc分别为0.652[95%可信区间{CI}，0.524，0.769]和0.590[95%CI：0.502，0.689])。与仅包含临床和遗传特征的模型相比，在临床和遗传特征中加入放射组学模型可以改善生存预测(对于OS和PFS，分别为P=0.04和0.03)。结论：当结合临床和遗传特征时，放射组学MRI表型可以提高生存预测，因此具有作为一种实用的成像生物标志物的潜力。(C)RSNA，2018年
Purpose: To investigate whether radiomic features at MRI improve survival prediction in patients with glioblastoma multiforme (GBM) when they are integrated with clinical and genetic profiles.Materials and Methods: Data in patients with a diagnosis of GBM between December 2009 and January 2017 (217 patients) were retrospectively reviewed up to May 2017 and allocated to training and test sets (3:1 ratio). Radiomic features (n = 796) were extracted from multiparametric MRI. A random survival forest (RSF) model was trained with the radiomic features along with clinical and genetic profiles (O-6-methylguanine-DNA-methyltransferase promoter methylation and isocitrate dehydrogenase 1 mutation statuses) to predict overall survival (OS) and progression-free survival (PFS). The RSF models were validated on the test set. The incremental values of radiomic features were evaluated by using the integrated area under the receiver operating characteristic curve (iAUC).Results: The 217 patients had a mean age of 57.9 years, and there were 87 female patients (age range, 2281 years) and 130 male patients (age range, 1785 years). The median OS and PFS of patients were 352 days (range, 201809 days) and 264 days (range, 211809 days), respectively. The RSF radiomics models were successfully validated on the test set (iAUC, 0.652 [95% confidence interval {CI}, 0.524, 0.769] and 0.590 [95% CI: 0.502, 0.689] for OS and PFS, respectively). The addition of a radiomics model to clinical and genetic profiles improved survival prediction when compared with models containing clinical and genetic profiles alone (P = .04 and .03 for OS and PFS, respectively).Conclusion: Radiomic MRI phenotyping can improve survival prediction when integrated with clinical and genetic profiles and thus has potential as a practical imaging biomarker. (C) RSNA, 2018