Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China.
The Second School of Clinical Medicine, Southern Medical University, Guangzhou, China.
Can Assoc Radiol J. 2024 Feb;75(1):143-152. doi: 10.1177/08465371231183309. Epub 2023 Aug 8.
To evaluate the value of intra- and peritumoral deep learning (DL) features based on multi-parametric magnetic resonance imaging (MRI) for identifying telomerase reverse transcriptase (TERT) promoter mutation in glioblastoma (GBM). In this study, we included 229 patients with GBM who underwent preoperative MRI in two hospitals between November 2016 and September 2022. We used four 2D Convolutional Neural Networks (GoogLeNet, DenseNet121, VGG16, and MobileNetV3-Large) to extract intra- and peritumoral DL features. The Mann-Whitney U test, Pearson correlation analysis, least absolute shrinkage and selection operator, and logistic regression analysis were used for feature selection and construction of DL radiomics (DLR) signatures in different regions. These multi-parametric and multi-region signatures were combined to identify TERT promoter mutation. The area under the receiver operating characteristic curve (AUC) was used to evaluate the effects of the signatures. The signatures based on the DL features from the peritumoral regions with expansion distances of 2 mm, 8 mm, and 10 mm using the GoogLeNet architecture correlated with the optimal AUC values (test set: .823, .753, and .768) in the T2-weighted, T1-weighted contrast-enhanced, and T1-weighted images. Using the stacking fusion method, DLR with multi-parameter and multi-region fusion achieved the best discrimination with AUC values of .948 and .902 in the training and test sets, respectively. The radiomics model based on the fusion of multi-parameter MRI intra- and peritumoral DLR signatures may help to identify TERT promoter mutation in patients with GBM.
评估基于多参数磁共振成像（MRI）的肿瘤内和肿瘤周围深度学习（DL）特征在胶质母细胞瘤（GBM）中识别端粒酶逆转录酶（TERT）启动子突变的价值。本研究纳入了 2016 年 11 月至 2022 年 9 月在两家医院接受术前 MRI 的 229 例 GBM 患者。我们使用了四个 2D 卷积神经网络（GoogLeNet、DenseNet121、VGG16 和 MobileNetV3-Large）来提取肿瘤内和肿瘤周围的 DL 特征。采用 Mann-Whitney U 检验、Pearson 相关分析、最小绝对收缩和选择算子以及逻辑回归分析进行特征选择，并构建不同区域的 DL 放射组学（DLR）特征。将这些多参数和多区域特征组合起来以识别 TERT 启动子突变。使用受试者工作特征曲线（AUC）下面积来评估特征的效果。基于 GoogLeNet 架构的肿瘤周围区域扩展距离为 2mm、8mm 和 10mm 的 DL 特征的特征与 T2 加权像、T1 加权对比增强像和 T1 加权像的最佳 AUC 值（测试集：.823、.753 和.768）相关。使用堆叠融合方法，多参数和多区域融合的 DLR 获得了最佳的鉴别能力，在训练集和测试集中 AUC 值分别为.948 和.902。基于多参数 MRI 肿瘤内和肿瘤周围 DLR 特征融合的放射组学模型可能有助于识别 GBM 患者的 TERT 启动子突变。
