Mahmoudi Keon, Kim Daniel H, Tavakkol Elham, Kihira Shingo, Bauer Adam, Tsankova Nadejda, Khan Fahad, Hormigo Adilia, Yedavalli Vivek, Nael Kambiz
Department of Radiological Sciences, David Geffen School of Medicine at University of California, Los Angeles, CA 90095, USA.
Department of Radiology, Kaiser Permanente Fontana Medical Center, Fontana, CA 92335, USA.
Cancers (Basel). 2024 Jan 30;16(3):589. doi: 10.3390/cancers16030589.
Clinical, histopathological, and imaging variables have been associated with prognosis in patients with glioblastoma (GBM). We aimed to develop a multiparametric radiogenomic model incorporating MRI texture features, demographic data, and histopathological tumor biomarkers to predict prognosis in patients with GBM.
In this retrospective study, patients were included if they had confirmed diagnosis of GBM with histopathological biomarkers and pre-operative MRI. Tumor segmentation was performed, and texture features were extracted to develop a predictive radiomic model of survival (<18 months vs. ≥18 months) using multivariate analysis and Least Absolute Shrinkage and Selection Operator (LASSO) regularization to reduce the risk of overfitting. This radiomic model in combination with clinical and histopathological data was inserted into a backward stepwise logistic regression model to assess survival. The diagnostic performance of this model was reported for the training and external validation sets.
A total of 116 patients were included for model development and 40 patients for external testing validation. The diagnostic performance (AUC/sensitivity/specificity) of the radiomic model generated from seven texture features in determination of ≥18 months survival was 0.71/69.0/70.3. Three variables remained as independent predictors of survival, including radiomics ( = 0.004), age ( = 0.039), and status ( = 0.025). This model yielded diagnostic performance (AUC/sensitivity/specificity) of 0.77/81.0/66.0 (training) and 0.89/100/78.6 (testing) in determination of survival ≥ 18 months.
Results show that our radiogenomic model generated from radiomic features at baseline MRI, age, and status can predict survival ≥ 18 months in patients with GBM.
临床、组织病理学和影像学变量已与胶质母细胞瘤（GBM）患者的预后相关。我们旨在开发一种多参数放射基因组模型，纳入MRI纹理特征、人口统计学数据和组织病理学肿瘤生物标志物，以预测GBM患者的预后。
在这项回顾性研究中，纳入了经组织病理学生物标志物确诊为GBM且术前行MRI检查的患者。进行肿瘤分割，并提取纹理特征，使用多变量分析和最小绝对收缩和选择算子（LASSO）正则化来开发生存预测性放射组学模型（<18个月与≥18个月），以降低过度拟合的风险。将该放射组学模型与临床和组织病理学数据相结合，插入向后逐步逻辑回归模型中以评估生存情况。报告了该模型在训练集和外部验证集上的诊断性能。
共纳入116例患者进行模型开发，40例患者进行外部测试验证。由七个纹理特征生成的放射组学模型在确定≥18个月生存情况时的诊断性能（AUC/敏感性/特异性）为0.71/69.0/70.3。三个变量仍然是生存的独立预测因子，包括放射组学（P = 0.004）、年龄（P = 0.039）和MGMT状态（P = 0.025）。该模型在确定生存≥18个月时的诊断性能（AUC/敏感性/特异性）在训练集中为0.77/81.0/66.0，在测试集中为0.89/100/78.6。
结果表明，我们基于基线MRI的放射组学特征、年龄和MGMT状态生成的放射基因组模型可以预测GBM患者生存≥18个月的情况。
