Song Yancheng, Li Jie, Wang Hexiang, Liu Bo, Yuan Chentong, Liu Hao, Zheng Ziwen, Min Fanyi, Li Yu
Department of Gastrointestinal Surgery, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, Shandong.
Department of Radiology, The Affiliated Hospital of Qingdao University, Shandong, Shandong.
Acad Radiol. 2022 Jun;29(6):806-816. doi: 10.1016/j.acra.2021.05.005. Epub 2021 Jul 5.
Contrast-enhanced computed tomography (CE-CT) was used to establish radiomics nomogram to evaluate the malignant potential of gastrointestinal stromal tumors (GISTs).
A total of 500 GIST patients were enrolled in this study and divided into training cohort (n = 346, our center) and validation cohort (n = 154, another center). Minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) algorithms were used to select the feature subset with the best discriminant features from the three phases image, and five classifiers were used to establish four radiomics signatures. Preoperative radiomics nomogram was constructed by adding the clinical features determined by multivariate logistic regression analysis. The performance of radiomics signatures and nomogram were evaluated by area under the curve (AUC) of the receiver operating characteristic (ROC). The calibration of nomogram was appraised by calibration curve.
A total of 13 radiomic features were extracted from tri-phase combined CE-CT images. Tri-phase combined CE-CT features + Support Vector Machine (SVM) was the best combination at predicting the malignant potential of GIST, with an AUC of 0.895 (95% CI 0.858-0.931) in the training cohort and 0.847 (95% CI 0.778-0.917) in the validation cohort. The nomogram also had good calibration. In the training cohort and the validation cohort, preoperative radiomics nomogram reached AUCs of 0.927 and 0.905, respectively, which were higher than clinical.
The radiomics nomogram had a good predictive effect and generalization on the malignant potential of GIST, which could effectively help guide preoperative clinical decision.
采用对比增强计算机断层扫描（CE-CT）建立放射组学列线图，以评估胃肠道间质瘤（GIST）的恶性潜能。
本研究共纳入500例GIST患者，分为训练队列（n = 346，来自我们中心）和验证队列（n = 154，来自另一中心）。使用最小冗余最大相关性（mRMR）和最小绝对收缩和选择算子（LASSO）算法从三期图像中选择具有最佳判别特征的特征子集，并使用五个分类器建立四个放射组学特征。通过添加多因素逻辑回归分析确定的临床特征构建术前放射组学列线图。通过受试者操作特征（ROC）曲线下面积（AUC）评估放射组学特征和列线图的性能。通过校准曲线评估列线图的校准情况。
从三期联合CE-CT图像中提取了总共13个放射组学特征。三期联合CE-CT特征 + 支持向量机（SVM）在预测GIST恶性潜能方面是最佳组合，在训练队列中的AUC为0.895（95%CI 0.858 - 0.931），在验证队列中的AUC为0.847（95%CI 0.778 - 0.917）。列线图也具有良好的校准。在训练队列和验证队列中，术前放射组学列线图的AUC分别达到0.927和0.905，均高于临床指标。
放射组学列线图对GIST的恶性潜能具有良好的预测效果和泛化能力，可有效帮助指导术前临床决策。
