Department of Radiology, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu, China (G.Z., L.S., R.Q., H.P., W.K.).
School of Pharmacy, Chengdu Medical College, Chengdu, China (Q.M.).
Acad Radiol. 2024 Jun;31(6):2591-2600. doi: 10.1016/j.acra.2023.12.024. Epub 2024 Jan 30.
This study aimed to non-invasively predict epidermal growth factor receptor (EGFR) mutation status in patients with lung adenocarcinoma using multi-phase computed tomography (CT) radiomics features.
A total of 424 patients with lung adenocarcinoma were recruited from two hospitals who underwent preoperative non-enhanced CT (NE-CT) and enhanced CT (including arterial phase CT [AP-CT], and venous phase CT [VP-CT]). Patients were divided into training (n = 297) and external validation (n = 127) cohorts according to hospital. Radiomics features were extracted from the NE-CT, AP-CT, and VP-CT images, respectively. The Wilcoxon test, correlation analysis, and simulated annealing were used for feature screening. A clinical model and eight radiomics models were established. Furthermore, a clinical-radiomics model was constructed by incorporating multi-phase CT features and clinical risk factors. Receiver operating characteristic curves were used to evaluate the predictive performance of the models.
The predictive performance of multi-phase CT radiomics model (AUC of 0.925 [95% CI, 0.879-0.971] in the validation cohort) was higher than that of NE-CT, AP-CT, VP-CT, and clinical models (AUCs of 0.860 [95% CI,0.794-0.927], 0.792 [95% CI, 0.713-0.871], 0.753 [95% CI, 0.669-0.838], and 0.706 [95% CI, 0.620-0.791] in the validation cohort, respectively) (all P < 0.05). The predictive performance of the clinical-radiomics model (AUC of 0.927 [95% CI, 0.882-0.971] in the validation cohort) was comparable to that of multi-phase CT radiomics model (P > 0.05).
Our multi-phase CT radiomics model showed good performance in identifying the EGFR mutation status in patients with lung adenocarcinoma, which may assist personalized treatment decisions.
本研究旨在通过多期 CT 放射组学特征无创预测肺腺癌患者表皮生长因子受体（EGFR）突变状态。
共纳入 2 家医院的 424 例肺腺癌患者，均行术前平扫 CT（NE-CT）和增强 CT（包括动脉期 CT [AP-CT]和静脉期 CT [VP-CT]）检查。根据就诊医院将患者分为训练集（n=297）和外部验证集（n=127）。分别从 NE-CT、AP-CT 和 VP-CT 图像中提取放射组学特征。采用 Wilcoxon 检验、相关性分析和模拟退火算法进行特征筛选。建立临床模型和 8 个放射组学模型，并通过纳入多期 CT 特征和临床风险因素构建临床-放射组学模型。采用受试者工作特征曲线评估模型的预测性能。
多期 CT 放射组学模型（验证集 AUC 为 0.925[95%CI，0.879-0.971]）的预测性能优于 NE-CT、AP-CT、VP-CT 和临床模型（验证集 AUC 分别为 0.860[95%CI，0.794-0.927]、0.792[95%CI，0.713-0.871]、0.753[95%CI，0.669-0.838]和 0.706[95%CI，0.620-0.791]）（均 P<0.05）。临床-放射组学模型（验证集 AUC 为 0.927[95%CI，0.882-0.971]）的预测性能与多期 CT 放射组学模型相当（P>0.05）。
本研究的多期 CT 放射组学模型在识别肺腺癌患者 EGFR 突变状态方面具有良好的性能，可能有助于个体化治疗决策。
