Zeng Sihui, Yin Shaohan, Lian Shanshan, Luo Ma, Feng Lili, Liao Yuting, Huang Zhijie, Zheng Yuquan, Xie Chuanmiao, Zhuo Shuiqing
Department of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou 510060, PR China (S.Z., S.Y., S.L., M.L., L.F., Y.Z., C.X.); State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, PR China (S.Z., S.Y., S.L., M.L., L.F., Y.Z., C.X.).
Philips Healthcare, Guangzhou 510000, PR China (Y.L., Z.H.).
Acad Radiol. 2025 Sep;32(9):5242-5253. doi: 10.1016/j.acra.2025.04.035. Epub 2025 May 5.
This study aimed to develop and validate a dual-layer spectral CT based clinical-radiomic model for pre-treatment prediction of pathological T4 (pT4) in gastric cancer (GC) patients.
This retrospective study included 148 surgically confirmed GC patients who underwent dual-layer spectral CT scanning before surgery and were divided into a training (n=104) and test (n=44) cohorts. Subjective assessments were performed based on conventional 120-kV CT images by two readers. Clinical models were developed using patient demographics, serum tumor markers, and image features from CT scans. Radiomics model included features extracted from conventional 120-kV CT and dual-layer CT-derived spectral base image (SBI), such as virtual monoenergetic images (40 keV, 70 keV, 100 keV), iodine density (ID), effective atomic number (Zeff), and electron density (ED) images for both the arterial phase (AP) and portal venous phase (PVP). A clinical-radiomic combined model was developed and visualized using a nomogram.
Tumor thickness on CT and serum level of CA19-9 levels were identified as independent predictors. The clinical-radiomic combined model demonstrated superior performance compared to subjective image interpretation and other models, with an AUC of 0.906 (95% CI, 0.848-0.963) in the training cohort and 0.873 in the test cohort. The nomogram was significantly associated with pT4 status, supporting its potential utility in clinical prediction.
The integration of clinical characteristics with radiomic features from conventional CT and dual-layer CT-derived SBI achieved a high diagnostic accuracy for predicting pT4 in GC patients. This combined approach could assist in treatment planning and patient management in GC.
本研究旨在开发并验证一种基于双层光谱CT的临床影像组学模型，用于预测胃癌（GC）患者术前病理T4（pT4）情况。
本回顾性研究纳入了148例经手术确诊的GC患者，这些患者在手术前接受了双层光谱CT扫描，并被分为训练组（n = 104）和测试组（n = 44）。由两名阅片者基于传统120 kV CT图像进行主观评估。利用患者人口统计学数据、血清肿瘤标志物以及CT扫描的图像特征建立临床模型。影像组学模型包括从传统120 kV CT和双层CT衍生的光谱基图像（SBI）中提取的特征，如动脉期（AP）和门静脉期（PVP）的虚拟单能图像（40 keV、70 keV、100 keV）、碘密度（ID）、有效原子序数（Zeff）和电子密度（ED）图像。使用列线图开发并可视化临床影像组学联合模型。
CT上的肿瘤厚度和CA19-9血清水平被确定为独立预测因素。临床影像组学联合模型在性能上优于主观图像解读和其他模型，训练组的AUC为0.906（95% CI，0.848 - 0.963），测试组为0.873。列线图与pT4状态显著相关，支持其在临床预测中的潜在效用。
将临床特征与传统CT和双层CT衍生的SBI的影像组学特征相结合，在预测GC患者的pT4方面具有较高的诊断准确性。这种联合方法可有助于GC的治疗规划和患者管理。
