Department of Radiology, Shanxi Province Cancer Hospital; Shanxi Hospital Affiliated to Cancer Hospital, Chinese Academy of Medical Sciences; Cancer Hospital Affiliated to Shanxi Medical University; Taiyuan 030013, China.
Department of Radiology, Shanxi Province Cancer Hospital; Shanxi Hospital Affiliated to Cancer Hospital, Chinese Academy of Medical Sciences; Cancer Hospital Affiliated to Shanxi Medical University; Taiyuan 030013, China; Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou 510080, China.
Radiother Oncol. 2022 Jun;171:155-163. doi: 10.1016/j.radonc.2022.04.023. Epub 2022 Apr 29.
To investigate the ability of the CT-based radiomics models for pretreatment prediction of the response to neoadjuvant chemotherapy (NAC) in patients with locally advanced gastric cancer (LAGC).
This retrospective analysis included 279 consecutive LAGC patients from center I (training cohort, n = 196; internal validation cohort, n = 83) who were examined by contrast-enhanced CT before treatment and 211 consecutive patients from center II who were recruited as an external validation cohort. A total of 102 features were extracted from the portal venous phase CT images, and feature selection was further subjected to three-step procedures. Next, five classifications, including Logistic Regression (LR), Naive Bayes, Random forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGB) algorithms, were applied to construct radiomics models for predicting the good-responder (GR) to NAC in the training cohort. The prediction performances were evaluated using ROC and decision curve analysis (DCA).
No statistically significant difference was detected for all clinicopathological characteristics. Additionally, allsix key features were significantly different between GR and poor-responder (PR). Compared to models from other classifiers, the model obtained with XGB showed promising prediction performance with the highest AUC of 0.790(95%CI: 0.700-0.880) in the training cohort. The corresponding AUCs were 0.784(95%CI, 0.659-0.908) and 0.803(95%CI, 0.717-0.888) in the internal and external validation cohorts, respectively. DCA confirmed the clinical utility.
The proposed pretreatment CT-based radiomics models revealed good performances in predicting response to NAC and thus may be used to improve clinical treatment in LAGC patients.
本研究旨在探讨 CT 影像组学模型对局部进展期胃癌（LAGC）患者新辅助化疗（NAC）反应的预测能力。
本回顾性研究纳入了来自中心 I（训练队列，n=196；内部验证队列，n=83）和中心 II（外部验证队列，n=211）的 279 例连续 LAGC 患者。所有患者在治疗前均接受了增强 CT 检查，共提取了门静脉期 CT 图像的 102 个特征，并通过三步特征选择进一步进行处理。随后，我们应用逻辑回归（LR）、朴素贝叶斯（NB）、随机森林（RF）、支持向量机（SVM）和极端梯度提升（XGB）等 5 种分类算法构建了预测 NAC 反应良好（GR）的影像组学模型，并在训练队列中进行验证。采用 ROC 和决策曲线分析（DCA）评估模型的预测性能。
所有临床病理特征在两组间均无统计学差异。此外，GR 和 NAC 反应差（PR）患者之间的 6 个关键特征均存在显著差异。与其他分类器模型相比，XGB 模型具有最高的 AUC（训练队列 0.790[95%CI：0.700-0.880]），内部验证队列和外部验证队列的 AUC 分别为 0.784（95%CI，0.659-0.908）和 0.803（95%CI，0.717-0.888），均具有较好的预测性能。DCA 也证实了模型的临床实用性。
本研究构建的基于 CT 影像组学模型能够较好地预测 LAGC 患者对 NAC 的反应，有助于改善临床治疗策略。
