Ma Tingting, Zhao Mengran, Li Xiangli, Song Xiangchao, Wang Lingwei, Ye Zhaoxiang
Department of Radiology, Tianjin Cancer Hospital Airport Hospital, Tianjin, China.
Department of Radiology, Tianjin Medical University Cancer Institute and Hospital, Tianjin, China.
Front Med (Lausanne). 2024 Oct 18;11:1464632. doi: 10.3389/fmed.2024.1464632. eCollection 2024.
To evaluate the potential of radiomics approach for predicting No. 14v station lymph node metastasis (14vM) in gastric cancer (GC).
The contrast enhanced CT (CECT) images with corresponding clinical information of 288 GC patients were retrospectively collected. Patients were separated into training set ( = 202) and testing set ( = 86). A total of 1,316 radiomics feature were extracted from portal venous phase images of CECT. Seven machine learning (ML) algorithms including naïve Bayes (NB), -nearest neighbor (KNN), decision tree (DT), logistic regression (LR), random forest (RF), eXtreme gradient boosting (XGBoost) and support vector machine (SVM) were trained for development of optimal radiomics signature. A combined model was established by combining radiomics with important clinicopathological factors. The diagnostic ability of the signature and model were evaluated.
LR algorithm was chosen for signature construction. The radiomics signature exhibited good discrimination accuracy of 14vM with AUCs of 0.83 in the training and 0.77 in the testing set. The risk of 14vM showed significant association with higher radiomics score. A combined model exhibited increased predictive ability and good agreement in the training (AUC = 0.87) and testing (AUC = 0.85) sets.
The ML-based radiomics model provided a promising image biomarker for preoperative detection of 14vM and may help the surgeon to decide whether to add 14v dissection to lymphadenectomy.
评估放射组学方法预测胃癌（GC）中14v组淋巴结转移（14vM）的潜力。
回顾性收集288例GC患者的对比增强CT（CECT）图像及相应临床信息。将患者分为训练集（n = 202）和测试集（n = 86）。从CECT门静脉期图像中提取了总共1316个放射组学特征。对包括朴素贝叶斯（NB）、K近邻（KNN）、决策树（DT）、逻辑回归（LR）、随机森林（RF）、极端梯度提升（XGBoost）和支持向量机（SVM）在内的七种机器学习（ML）算法进行训练，以开发最佳放射组学特征。通过将放射组学与重要的临床病理因素相结合建立联合模型。评估该特征和模型的诊断能力。
选择LR算法构建特征。放射组学特征对14vM表现出良好的鉴别准确性，训练集中的AUC为0.83，测试集中为0.77。14vM的风险与较高的放射组学评分显著相关。联合模型在训练集（AUC = 0.87）和测试集（AUC = 0.85）中表现出更高的预测能力和良好的一致性。
基于ML的放射组学模型为术前检测14vM提供了一种有前景的影像生物标志物，可能有助于外科医生决定是否在淋巴结清扫术中增加14v组清扫。
