Preliminary study on the ability of 18F-fluorodeoxyglucose positron emission tomography/computed tomography radiomics to predict vessels that encapsulate tumor clusters and prognosis in hepatocellular carcinoma

作者：Siqi Hu, Qiong Zou, Zijie Shen, Yujie Xie, Li Shi, Ju Jiao, Hong Zhang, Mu‐hua Cheng, Yong Zhang · 发表于：Quantitative Imaging in Medicine and Surgery · 年份：2025 · DOI：10.21037/qims-2024-2734 · 被引用次数：2 · 研究领域：Hepatocellular Carcinoma Treatment and Prognosis、Radiomics and Machine Learning in Medical Imaging、Cholangiocarcinoma and Gallbladder Cancer Studies

Background: F-FDG PET/CT) to preoperatively predict VETC and prognosis in HCC patients. Methods: F-FDG PET/CT images, followed by calculation of a radiomics score (Radscore). Univariate and multivariate logistic regression analyses were used to screen out the independent indicators. A nomogram model was developed based on Radscore and clinical indicators, and a clinical model was developed based on clinical indicators. The performance of the nomogram, clinical model, Radscore, as well as traditional PET parameter tumor-to-liver ratio (TLR) were evaluated using receiver operating characteristic (ROC) curves and decision curve analysis (DCA). Disease-free survival (DFS) and overall survival (OS) rates were assessed using Kaplan-Meier survival analysis. Results: The difference in FDG parameter TLR between VETC-positive and VETC-negative HCC was found to be statistically significant (P<0.05), which was consistent with traditional CT/MRI imaging features. The Radscore was derived by calculating 13 selected radiomics features, comprising of six PET radiomics features and seven CT radiomics features. The nomogram model exhibited an area under the curve (AUC) of 0.908 [95% confidence interval (CI): 0.852-0.963; sensitivity: 0.855; specificity: 0.833] and 0.762 (95% CI: 0.624-0.900; sensitivity: 0.739; specificity: 0.739) in the training and test cohort, respectively. The disparity in the prediction of VETC status based on the nomogram model between DFS and OS was statistically compar...