Department of Radiology, West China Hospital of Sichuan University, Chengdu 610041, Sichuan Province, China.
Department of Radiology, Sichuan Science City Hospital, Mianyang 621054, Sichuan Province, China.
Eur J Radiol. 2022 Jan;146:110065. doi: 10.1016/j.ejrad.2021.110065. Epub 2021 Nov 23.
To develop and externally validate a computed tomography (CT)-based radiomics model for predicting lymphovascular invasion (LVI) before treatment in patients with rectal cancer (RC).
This retrospective study enrolled 351 patients with RC from three hospitals between March 2018 and March 2021. These patients were assigned to one of the following three groups: training set (n = 239, from hospital 1), internal validation set (n = 60, from hospital 1), and external validation set (n = 52, from hospitals 2 and 3). Large amounts of radiomics features were extracted from the intratumoral and peritumoral regions in the portal venous phase contrast-enhanced CT images. The score of radiomics features (Rad-score) was calculated by performing logistic regression analysis following the L1-based method. A combined model (Rad-score + clinical factors) was developed in the training cohort and validated internally and externally. The models were compared using the area under the receiver operating characteristic curve (AUC).
Of the 351 patients, 106 (30.2%) had an LVI + tumor. Rad-score (comprised of 22 features) was significantly higher in the LVI + group than in the LVI- group (0.60 ± 0.17 vs. 0.42 ± 0.19, P = 0.001). The combined model obtained good predictive performance in the training cohort (AUC = 0.813 [95% CI: 0.758-0.861]), with robust results in internal and external validations (AUC = 0.843 [95% CI: 0.726-0.924] and 0.807 [95% CI: 0.674-0.903]).
The proposed combined model demonstrated the potential to predict LVI preoperatively in patients with RC.
开发并验证一种基于计算机断层扫描（CT）的放射组学模型，用于预测直肠癌（RC）患者治疗前的淋巴血管侵犯（LVI）。
本回顾性研究纳入了 2018 年 3 月至 2021 年 3 月期间三家医院的 351 例 RC 患者。这些患者被分为以下三组：训练集（n=239，来自医院 1）、内部验证集（n=60，来自医院 1）和外部验证集（n=52，来自医院 2 和 3）。从门静脉期增强 CT 图像的肿瘤内和肿瘤周围区域提取大量放射组学特征。通过基于 L1 的方法进行逻辑回归分析，计算放射组学特征评分（Rad-score）。在训练队列中建立了一个联合模型（Rad-score+临床因素），并在内部和外部进行验证。使用受试者工作特征曲线下面积（AUC）比较模型。
在 351 例患者中，有 106 例（30.2%）存在 LVI+肿瘤。LVI+组的 Rad-score（包含 22 个特征）明显高于 LVI-组（0.60±0.17 比 0.42±0.19，P=0.001）。联合模型在训练队列中获得了良好的预测性能（AUC=0.813[95%CI：0.758-0.861]），内部和外部验证结果稳健（AUC=0.843[95%CI：0.726-0.924]和 0.807[95%CI：0.674-0.903]）。
该研究提出的联合模型具有预测 RC 患者术前 LVI 的潜力。
