Department of Radiology, Chongqing University Cancer Hospital & Chongqing Cancer Institute & Chongqing Cancer Hospital, Chongqing 400030, People's Republic of China; Key Laboratory for Biorheological Science and Technology of Ministry of Education (Chongqing University), Chongqing University Cancer Hospital & Chongqing Cancer Institute & Chongqing Cancer Hospital, Chongqing, People's Republic of China.
College of Optoelectronic Engineering, Chongqing University, Chongqing, People's Republic of China.
Acad Radiol. 2022 Feb;29 Suppl 2:S62-S72. doi: 10.1016/j.acra.2020.12.007. Epub 2021 Jan 2.
To develop and validate a radiomics model, a clinical-semantic model and a combined model by using standard methods for the pretreatment prediction of distant metastasis (DM) in patients with non-small-cell lung cancer (NSCLC) and to explore whether the combined model provides added value compared to the individual models.
This retrospective study involved 356 patients with NSCLC. According to the image biomarker standardization initiative reference manual, we standardized the image processing and feature extraction using in-house software. Finally, 6692 radiomics features were extracted from each lesion based on contrast-enhanced chest CT images. The least absolute shrinkage selection operator and the recursive feature elimination algorithm were used to select features. The logistic regression classifier was used to build the model. Three models (radiomics model, clinical-semantic model and combined model) were constructed to predict DM in NSCLC. Area under the receiver operating characteristic curves were used to validate the ability of the three models to predict DM. A visual nomogram based on the combined model was developed for DM risk assessment in each patient.
The receiver operating characteristic curve showed predictive performance for DM of the radiomics model (area under the curve [AUC] values for training and validation were 0.76 [95% CI, 0.704 - 0.820] and 0.76 [95% CI, 0.653 - 0.858], respectively). The combined model had AUCs of 0.78 (95% CI, 0.723 - 0.835) and 0.77 (95% CI, 0.673 - 0.870) in the training and validation cohorts, respectively. Both the radiomics model and combined model performed better than the clinical-semantic model (0.70 [95% CI, 0.634 - 0.760] and 0.67 [95% CI, 0.554 - 0.787] in the training and validation cohorts, respectively).
The radiomics model and combined model may be useful for the prediction of DM in patients with NSCLC.
采用标准方法，开发并验证一种放射组学模型、一种临床语义模型和联合模型，用于预测非小细胞肺癌（NSCLC）患者远处转移（DM）的预处理，并探讨联合模型是否比单个模型提供附加价值。
本回顾性研究纳入 356 例 NSCLC 患者。根据影像生物标志物标准化倡议参考手册，使用内部软件对图像预处理和特征提取进行标准化。最后，基于增强胸部 CT 图像，从每个病灶中提取 6692 个放射组学特征。使用最小绝对收缩和选择算子（LASSO）和递归特征消除算法（RFE）进行特征选择。使用逻辑回归分类器构建模型。构建三种模型（放射组学模型、临床语义模型和联合模型），以预测 NSCLC 中的 DM。使用受试者工作特征曲线下面积（AUC）评估三种模型预测 DM 的能力。基于联合模型，开发了一种用于每位患者 DM 风险评估的可视化列线图。
受试者工作特征曲线显示，放射组学模型对 DM 具有预测性能（训练和验证队列的 AUC 值分别为 0.76[95%CI，0.704-0.820]和 0.76[95%CI，0.653-0.858]）。联合模型在训练和验证队列中的 AUC 值分别为 0.78（95%CI，0.723-0.835）和 0.77（95%CI，0.673-0.870）。放射组学模型和联合模型的性能均优于临床语义模型（训练和验证队列中的 AUC 值分别为 0.70[95%CI，0.634-0.760]和 0.67[95%CI，0.554-0.787]）。
放射组学模型和联合模型可能有助于预测 NSCLC 患者的 DM。
