Fusion Radiomics Features from Conventional MRI Predict MGMT Promoter Methylation Status in Lower Grade Gliomas
Fusion Radiomics Features from Conventional MRI Predict MGMT Promoter Methylation Status in Lower Grade Gliomas
复制标题
DOI：
10.1016/j.ejrad.2019.108714
复制
发表时间：
2019-12-01
影响因子：
3.3
通讯作者：
Feng, Feng
中科院分区：
文献类型：
--
作者：
Jiang, Chendan;Kong, Ziren;Feng, Feng
目的：O6-甲基鸟嘌呤-DNA甲基转移酶(MGMT)启动子甲基化状态已被证明是预测低级别胶质瘤(LGG)预后的生物标志物。本研究旨在建立一个放射组学模型，用于术前预测LGG中MGMT启动子甲基化状态。方法：回顾122例经病理证实的LGG患者，以87例本地患者作为训练数据集，35例来自肿瘤影像资料作为独立验证。从三维增强T1(3D-CE-T1)和T2加权的MRI图像中提取了1702个放射组学特征，其中形状特征14个，一阶特征18个，纹理特征75个，小波特征744个。用最小绝对收缩和选择算子算法选择放射组学特征，并用多分类器构建预测模型。结果：建立了5种放射组学预测模型，即3D-CE-T1加权单一放射组学模型、T2加权单一放射组学模型、融合放射组学模型、线性组合放射组学模型和临床综合模型。由两个序列串联而成的融合放射组学模型表现出最好的性能，在训练数据集中的精度为0.849，曲线下面积为0.970(0.9391.000)，在验证数据集中的精度为0.886，曲线下面积为0.898(0.786-1.000)。单一放射组学模型的线性组合和临床因素的整合没有改善。结论：常规MRI放射组学模型可以可靠地预测LGG患者MGMT启动子甲基化状态。融合不同序列的放射组学特征可以提高预测性能。
Purpose: The methylation status of the O6-methylguanine-DNA methyltransferase (MGMT) promoter has been proven to be a prognostic and predictive biomarker for lower grade glioma (LGG). This study aims to build a radiomics model to preoperatively predict the MGMT promoter methylation status in LGG.Method: 122 pathology-confirmed LGG patients were retrospectively reviewed, with 87 local patients as the training dataset, and 35 from The Cancer Imaging Archive as independent validation. A total of 1702 radiomics features were extracted from three-dimensional contrast-enhanced T1 (3D-CE-T1)-weighted and T2-weighted MRI images, including 14 shape, 18 first order, 75 texture, and 744 wavelet features respectively. The radiomics features were selected with the least absolute shrinkage and selection operator algorithm, and prediction models were constructed with multiple classifiers. Models were evaluated using receiver operating characteristic (ROC).Results: Five radiomics prediction models, namely, 3D-CE-T1-weighted single radiomics model, T2-weighted single radiomics model, fusion radiomics model, linear combination radiomics model, and clinical integrated model, were built. The fusion radiomics model, which constructed from the concatenation of both series, displayed the best performance, with an accuracy of 0.849 and an area under the curve (AUC) of 0.970 (0.9391.000) in the training dataset, and an accuracy of 0.886 and an AUC of 0.898 (0.786-1.000) in the validation dataset. Linear combination of single radiomics models and integration of clinical factors did not improve.Conclusions: Conventional MRI radiomics models are reliable for predicting the MGMT promoter methylation status in LGG patients. The fusion of radiomics features from different series may increase the prediction performance.