Ma Tingting, Cui Jingli, Wang Lingwei, Li Hui, Ye Zhaoxiang, Gao Xujie
Department of Radiology, Tianjin Cancer Hospital Airport Hospital, Tianjin, China.
Department of Radiology, Tianjin Medical University Cancer Institute and Hospital, Tianjin, China.
Transl Cancer Res. 2022 Dec;11(12):4326-4337. doi: 10.21037/tcr-22-1690.
Accurate evaluation of human epidermal growth factor receptor 2 (HER2) status is very important for appropriate management of advanced gastric cancer (AGC) patients. In this study, we aimed to develop and validate a computed tomography (CT)-based radiomics signature for preoperative prediction of HER2 overexpression and treatment efficacy of trastuzumab in AGC.
We retrospectively enrolled 536 consecutive AGC patients (median age, 59 years; interquartile range, 52-65 years; 377 male, 159 female) and separated them into a training set (n=357) and a testing set (n=179). Radiomic features were extracted from 3 different phase images of contrast-enhanced CT scans, and a radiomics signature was built based on highly reproducible features using the least absolute shrinkage and selection operator (LASSO) method. The predictive performance of the radiomics signature was assessed in the training and testing sets. Univariable and multivariable logistical regression analyses were used to identify independent risk factors of HER2 overexpression. Univariable and multivariable Cox regression analyses were used to identify the risk factors of overall survival (OS) and progression-free survival (PFS). The predictive value of the radiomics signature for treatment efficacy of trastuzumab was also evaluated.
The radiomics signature comprised eight robust features that demonstrated good discrimination ability for HER2 overexpression in the training set [area under the curve (AUC) =0.85] and the testing set (AUC =0.81). Multivariable Cox regression analysis revealed that the radiomics signature was an independent risk factor for OS [hazard ratio (HR) =2.01, P=0.001] and PFS (HR =1.32, P=0.01). The radiomics score of patients who achieved disease control was significantly lower than that of patients with progressive disease (P=0.023).
The proposed radiomics signature showed favorable accuracy for prediction of HER2 overexpression and prognosis in AGC. It has promising potential as a noninvasive approach for selecting patients for target therapy.
准确评估人表皮生长因子受体2（HER2）状态对于晚期胃癌（AGC）患者的合理管理非常重要。在本研究中，我们旨在开发并验证一种基于计算机断层扫描（CT）的放射组学特征，用于术前预测AGC中HER2过表达及曲妥珠单抗的治疗疗效。
我们回顾性纳入了536例连续的AGC患者（中位年龄59岁；四分位间距52 - 65岁；男性377例，女性159例），并将他们分为训练集（n = 357）和测试集（n = 179）。从对比增强CT扫描的3个不同时相图像中提取放射组学特征，并使用最小绝对收缩和选择算子（LASSO）方法基于高度可重复的特征构建放射组学特征。在训练集和测试集中评估放射组学特征的预测性能。采用单变量和多变量逻辑回归分析来确定HER2过表达的独立危险因素。采用单变量和多变量Cox回归分析来确定总生存（OS）和无进展生存（PFS）的危险因素。还评估了放射组学特征对曲妥珠单抗治疗疗效的预测价值。
放射组学特征包含8个稳健特征，在训练集[曲线下面积（AUC）= 0.85]和测试集（AUC = 0.81）中对HER2过表达均表现出良好的区分能力。多变量Cox回归分析显示，放射组学特征是OS[风险比（HR）= 2.01，P = 0.001]和PFS（HR = 1.32，P = 0.01）的独立危险因素。疾病得到控制的患者的放射组学评分显著低于疾病进展的患者（P = 0.023）。
所提出的放射组学特征在预测AGC中HER2过表达和预后方面显示出良好的准确性。作为一种为靶向治疗选择患者的非侵入性方法，它具有广阔的潜力。
